|
|
| Line 1: |
Line 1: |
| {{Redirect|Neural network|networks of living neurons|Biological neural network|the journal|Neural Networks (journal)}}
| | The one who wrote the article is called Alysha when individuals make use of the full name and she feels comfortable. Her husband and her livein South Dakota but she will have to go oneday or another. Kayaking is what she loves doing. Dataprocessing is her day-job now.<br><br>my web site :: [http://yofui.com/?evento=2342&foto=152564 jaun pablo schiappacasse canepa] |
| {{Machine learning bar}}
| |
| {{Use dmy dates|date=June 2013}}
| |
| | |
| [[Image:Colored neural network.svg|thumb|300px|An artificial neural network is an interconnected group of nodes, akin to the vast network of [[neuron]]s in a [[brain]]. Here, each circular node represents an artificial neuron and an arrow represents a connection from the output of one neuron to the input of another.]]
| |
| | |
| In [[computer science]] and related fields, '''artificial neural networks''' are computational [[Statistical model|models]] inspired by animals' [[central nervous system]]s (in particular the [[brain]]) that are capable of [[machine learning]] and [[pattern recognition]]. They are usually presented as systems of interconnected "[[artificial neuron|neuron]]s" that can compute values from inputs by feeding information through the network.
| |
| | |
| For example, in a neural network for [[handwriting recognition]], a set of input neurons may be activated by the pixels of an input image representing a letter or digit. The activations of these neurons are then passed on, weighted and transformed by some function determined by the network's designer, to other neurons, etc., until finally an output neuron is activated that determines which character was read.
| |
| | |
| Like other machine learning methods, neural networks have been used to solve a wide variety of tasks that are hard to solve using ordinary rule-based programming, including [[computer vision]] and [[speech recognition]].
| |
| | |
| ==Background==
| |
| The inspiration for the neural networks came from examination of [[central nervous system]]s. In an artificial neural network, simple artificial [[Node (neural networks)|nodes]], called "[[artificial neuron|neurons]]", "neurodes", "processing elements" or "units", are connected together to form a network which mimics a biological neural network.
| |
| | |
| There is no single formal definition of what an artificial neural network is. Commonly, a class of statistical models may be called "neural" if they
| |
| # consist of sets of [[adaptive systems|adaptive]] weights, i.e. numerical parameters that are tuned by a learning [[algorithm]], and
| |
| # are capable of [[approximation theory|approximating]] non-linear functions of their inputs.
| |
| The adaptive weights are conceptually connection strengths between neurons, which are activated during training and prediction.
| |
| | |
| Neural networks are also similar to biological neural networks in performing functions collectively and in parallel by the units, rather than there being a clear delineation of subtasks to which various units are assigned. The term "neural network" usually refers to models employed in [[statistics]], [[cognitive psychology]] and [[artificial intelligence]]. Neural network models which emulate the central nervous system are part of [[theoretical neuroscience]] and [[computational neuroscience]].
| |
| | |
| In modern [[Neural network software|software implementations]] of artificial neural networks, the approach inspired by biology has been largely abandoned for a more practical approach based on statistics and signal processing. In some of these systems, neural networks or parts of neural networks (like artificial neurons) form components in larger systems that combine both adaptive and non-adaptive elements. While the more general approach of such systems is more suitable for real-world problem solving, it has little to do with the traditional artificial intelligence connectionist models. What they do have in common, however, is the principle of non-linear, distributed, parallel and local processing and adaptation. Historically, the use of neural networks models marked a paradigm shift in the late eighties from high-level (symbolic) [[artificial intelligence]], characterized by [[expert system]]s with knowledge embodied in ''if-then'' rules, to low-level (sub-symbolic) [[machine learning]], characterized by knowledge embodied in the parameters of a [[Cognitive Model#Dynamical systems|dynamical system]].
| |
| | |
| ==History==
| |
| [[Warren McCulloch]] and [[Walter Pitts]]<ref>{{cite journal|last=McCulloch|first=Warren|coauthors=Walter Pitts|title=A Logical Calculus of Ideas Immanent in Nervous Activity|journal=Bulletin of Mathematical Biophysics|year=1943|volume=5|pages=115–133|doi=10.1007/BF02478259|issue=4}}</ref> (1943) created a computational model for neural networks based on [[mathematics]] and algorithms. They called this model [[threshold logic]]. The model paved the way for neural network research to split into two distinct approaches. One approach focused on biological processes in the brain and the other focused on the application of neural networks to artificial intelligence.
| |
| | |
| In the late 1940s psychologist [[Donald Hebb]]<ref>{{cite book|last=Hebb|first=Donald|title=The Organization of Behavior|year=1949|publisher=Wiley|location=New York}}</ref> created a hypothesis of learning based on the mechanism of neural plasticity that is now known as [[Hebbian learning]]. Hebbian learning is considered to be a 'typical' [[unsupervised learning]] rule and its later variants were early models for [[long term potentiation]]. These ideas started being applied to computational models in 1948 with [[unorganized machine|Turing's B-type machines]].
| |
| | |
| Farley and Clark<ref>{{cite journal|last=Farley|first=B|coauthors=W.A. Clark|title=Simulation of Self-Organizing Systems by Digital Computer|journal=IRE Transactions on Information Theory|year=1954|volume=4|pages=76–84|doi=10.1109/TIT.1954.1057468|issue=4}}</ref> (1954) first used computational machines, then called calculators, to simulate a Hebbian network at MIT. Other neural network computational machines were created by Rochester, Holland, Habit, and Duda<ref>{{cite journal|last=Rochester|first=N.|coauthors=J.H. Holland, L.H. Habit, and W.L. Duda|title=Tests on a cell assembly theory of the action of the brain, using a large digital computer|journal=IRE Transactions on Information Theory|year=1956|volume=2|pages=80–93|doi=10.1109/TIT.1956.1056810|issue=3}}</ref> (1956).
| |
| | |
| [[Frank Rosenblatt]]<ref>{{cite journal|last=Rosenblatt|first=F.|title=The Perceptron: A Probalistic Model For Information Storage And Organization In The Brain|journal=Psychological Review|year=1958|volume=65|pages=386–408|doi=10.1037/h0042519|pmid=13602029|issue=6}}</ref> (1958) created the [[perceptron]], an algorithm for pattern recognition based on a two-layer learning computer network using simple addition and subtraction. With mathematical notation, Rosenblatt also described circuitry not in the basic perceptron, such as the [[exclusive-or]] circuit, a circuit whose mathematical computation could not be processed until after the [[backpropagation]] algorithm was created by [[Paul Werbos]]<ref name="Werbos 1975">{{cite book|last=Werbos|first=P.J.|title=Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences|year=1975}}</ref> (1975).
| |
| | |
| Neural network research stagnated after the publication of machine learning research by [[Marvin Minsky]] and [[Seymour Papert]]<ref>{{cite book|last=Minsky|first=M.|title=An Introduction to Computational Geometry|year=1969|publisher=MIT Press|isbn=0-262-63022-2|coauthors=S. Papert}}</ref> (1969). They discovered two key issues with the computational machines that processed neural networks. The first issue was that single-layer neural networks were incapable of processing the exclusive-or circuit. The second significant issue was that computers were not sophisticated enough to effectively handle the long run time required by large neural networks. Neural network research slowed until computers achieved greater processing power. Also key later advances was the [[backpropagation]] algorithm which effectively solved the exclusive-or problem (Werbos 1975).<ref name="Werbos 1975"/>
| |
| | |
| The [[connectionism|parallel distributed processing]] of the mid-1980s became popular under the name [[connectionism]]. The text by [[David E. Rumelhart]] and [[James McClelland (psychologist)|James McClelland]]<ref>{{cite book|last=Rumelhart|first=D.E|title=Parallel Distributed Processing: Explorations in the Microstructure of Cognition|year=1986|publisher=MIT Press|location=Cambridge|coauthors=James McClelland}}</ref> (1986) provided a full exposition on the use of connectionism in computers to simulate neural processes.
| |
| | |
| Neural networks, as used in artificial intelligence, have traditionally been viewed as simplified models of [[neural processing]] in the brain, even though the relation between this model and brain biological architecture is debated, as it is not clear to what degree artificial neural networks mirror brain function.<ref>{{cite web|last= Russell|first= Ingrid|title= Neural Networks Module|url= http://uhaweb.hartford.edu/compsci/neural-networks-definition.html|accessdate= 2012}}</ref>
| |
| | |
| In the 1990s, neural networks were overtaken in popularity in machine learning by [[support vector machine]]s and other, much simpler methods such as [[linear classifier]]s. Renewed interest in neural nets was sparked in the 2000s by the advent of [[deep learning]].
| |
| | |
| ===Recent improvements===
| |
| [[Biophysics|Biophysical]] models, such as [[BCM theory]], have been important in understanding mechanisms for [[synaptic plasticity]], and have had applications in both computer science and neuroscience. Research is ongoing in understanding the computational algorithms used in the brain, with some recent biological evidence for [[radial basis networks]] and [[neural backpropagation]] as mechanisms for processing data.
| |
| | |
| Computational devices have been created in CMOS, for both biophysical simulation and [[neuromorphic computing]]. More recent efforts show promise for creating [[nanodevice]]s<ref>Yang, J. J.; Pickett, M. D.; Li, X. M.; Ohlberg, D. A. A.; Stewart,
| |
| D. R.; Williams, R. S. Nat. Nanotechnol. 2008, 3, 429–433.</ref> for very large scale [[principal component]]s analyses and [[convolution]]. If successful, these efforts could usher in a new era of [[neural computing]]<ref>Strukov, D. B.; Snider, G. S.; Stewart, D. R.; Williams, R. S. Nature 2008, 453, 80–83.</ref> that is a step beyond digital computing, because it depends on [[learning]] rather than [[programming language|programming]] and because it is fundamentally [[Analog signal|analog]] rather than [[Digital data|digital]] even though the first instantiations may in fact be with CMOS digital devices.
| |
| | |
| Between 2009 and 2012, the [[recurrent neural network]]s and deep feedforward neural networks developed in the research group of [[Jürgen Schmidhuber]] at the [[IDSIA|Swiss AI Lab IDSIA]] have won eight international competitions in [[pattern recognition]] and [[machine learning]].<ref>http://www.kurzweilai.net/how-bio-inspired-deep-learning-keeps-winning-competitions 2012 Kurzweil AI Interview with [[Jürgen Schmidhuber]] on the eight competitions won by his Deep Learning team 2009–2012</ref> For example, multi-dimensional [[long short term memory]] (LSTM)<ref>Graves, Alex; and Schmidhuber, Jürgen; ''Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks'', in Bengio, Yoshua; Schuurmans, Dale; Lafferty, John; Williams, Chris K. I.; and Culotta, Aron (eds.), ''Advances in Neural Information Processing Systems 22 (NIPS'22), December 7th–10th, 2009, Vancouver, BC'', Neural Information Processing Systems (NIPS) Foundation, 2009, pp. 545–552</ref><ref>A. Graves, M. Liwicki, S. Fernandez, R. Bertolami, H. Bunke, J. Schmidhuber. A Novel Connectionist System for Improved Unconstrained Handwriting Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, no. 5, 2009.</ref> won three competitions in connected handwriting recognition at the 2009 International Conference on Document Analysis and Recognition (ICDAR), without any prior knowledge about the three different languages to be learned.
| |
| | |
| Variants of the [[back-propagation]] algorithm as well as unsupervised methods by [[Geoff Hinton]] and colleagues at the [[University of Toronto]]<ref>http://www.scholarpedia.org/article/Deep_belief_networks /</ref><ref>{{cite journal
| |
| |doi=10.1162/neco.2006.18.7.1527
| |
| |last1=Hinton |first1=G. E. |authorlink1=Geoffrey Hinton
| |
| |last2=Osindero |first2=S.
| |
| |last3=Teh |first3=Y.
| |
| |year=2006
| |
| |title=A fast learning algorithm for deep belief nets
| |
| |journal=[[Neural Computation]]
| |
| |volume=18
| |
| |issue=7 |pages=1527–1554
| |
| |url=http://www.cs.toronto.edu/~hinton/absps/fastnc.pdf
| |
| |pmid=16764513
| |
| }}</ref> can be used to train deep, highly nonlinear neural architectures similar to the 1980 [[Neocognitron]] by [[Kunihiko Fukushima]],<ref name="K. Fukushima. Neocognitron 1980">{{cite journal| author = Fukushima, K. | year = 1980 | title = Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position | journal = Biological Cybernetics | volume=36 | issue=4 | pages=93–202 | doi = 10.1007/BF00344251 }} <!-- K. Fukushima. Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological Cybernetics, 36(4): 93-202, 1980.--></ref> and the "standard architecture of vision",<ref name="M Riesenhuber, 1999">M Riesenhuber, [[Tomaso Poggio|T Poggio]]. Hierarchical models of object recognition in cortex. Nature neuroscience, 1999.</ref> inspired by the simple and complex cells identified by [[David H. Hubel]] and [[Torsten Wiesel]] in the primary [[visual cortex]].
| |
| | |
| [[Deep learning]] feedforward networks, such as [[convolutional neural network]]s, alternate [[convolution]]al layers and max-pooling layers, topped by several pure [[Statistical classification|classification]] layers. Fast [[GPU]]-based implementations of this approach have won several pattern recognition contests, including the IJCNN 2011 Traffic Sign Recognition Competition<ref>D. C. Ciresan, U. Meier, J. Masci, J. Schmidhuber. Multi-Column Deep Neural Network for Traffic Sign Classification. Neural Networks, 2012.</ref> and the ISBI 2012 Segmentation of Neuronal Structures in Electron Microscopy Stacks challenge.<ref name="D. Ciresan, A. Giusti 2012">D. Ciresan, A. Giusti, L. Gambardella, J. Schmidhuber. Deep Neural Networks Segment Neuronal Membranes in Electron Microscopy Images. In Advances in Neural Information Processing Systems (NIPS 2012), Lake Tahoe, 2012.</ref> Such neural networks also were the first artificial pattern recognizers to achieve human-competitive or even superhuman performance<ref name="C. Ciresan, U. Meier 2012">D. C. Ciresan, U. Meier, [[Jürgen Schmidhuber|J. Schmidhuber]]. Multi-column Deep Neural Networks for Image Classification. IEEE Conf. on Computer Vision and Pattern Recognition CVPR 2012.</ref> on benchmarks such as traffic sign recognition (IJCNN 2012), or the [[MNIST dataset|MNIST handwritten digits problem]] of [[Yann LeCun]] and colleagues at [[NYU]].
| |
| | |
| ===Successes in pattern recognition contests since 2009===
| |
| Between 2009 and 2012, the [[recurrent neural network]]s and deep feedforward neural networks developed in the research group of [[Jürgen Schmidhuber]] at the [[IDSIA|Swiss AI Lab IDSIA]] have won eight international competitions in [[pattern recognition]] and [[machine learning]].<ref>[http://www.kurzweilai.net/how-bio-inspired-deep-learning-keeps-winning-competitions 2012 Kurzweil AI Interview] with [[Jürgen Schmidhuber]] on the eight competitions won by his Deep Learning team 2009–2012</ref> For example, the bi-directional and [[multi-dimensional]] [[long short term memory]] (LSTM)<ref>
| |
| Graves, Alex; and Schmidhuber, Jürgen; ''Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks'', in Bengio, Yoshua; Schuurmans, Dale; Lafferty, John; Williams, Chris K. I.; and Culotta, Aron (eds.), ''Advances in Neural Information Processing Systems 22 (NIPS'22), 7–10 December 2009, Vancouver, BC'', Neural Information Processing Systems (NIPS) Foundation, 2009, pp. 545–552.
| |
| </ref><ref>
| |
| A. Graves, M. Liwicki, S. Fernandez, R. Bertolami, H. Bunke, [[Jürgen Schmidhuber|J. Schmidhuber]]. A Novel Connectionist System for Improved Unconstrained Handwriting Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, no. 5, 2009.
| |
| </ref>
| |
| of Alex Graves et al. won three competitions in connected handwriting recognition at the 2009 International Conference on Document Analysis and Recognition (ICDAR), without any prior knowledge about the three different languages to be learned. Fast [[GPU]]-based implementations of this approach by Dan Ciresan and colleagues at [[IDSIA]] have won several pattern recognition contests, including the IJCNN 2011 Traffic Sign Recognition Competition,<ref>
| |
| D. C. Ciresan, U. Meier, J. Masci, [[Jürgen Schmidhuber|J. Schmidhuber]]. Multi-Column Deep Neural Network for Traffic Sign Classification. Neural Networks, 2012.
| |
| </ref>
| |
| the ISBI 2012 Segmentation of Neuronal Structures in Electron Microscopy Stacks challenge,<ref name="D. Ciresan, A. Giusti 2012"/>
| |
| and others. Their neural networks also were the first artificial pattern recognizers to achieve human-competitive or even superhuman performance<ref name="C. Ciresan, U. Meier 2012"/>
| |
| on important benchmarks such as traffic sign recognition (IJCNN 2012), or the [[MNIST database|MNIST handwritten digits problem]] of [[Yann LeCun]] at [[NYU]]. Deep, highly nonlinear neural architectures similar to the 1980 [[neocognitron]] by [[Kunihiko Fukushima]]<ref name="K. Fukushima. Neocognitron 1980"/>
| |
| and the "standard architecture of vision"<ref name="M Riesenhuber, 1999"/>
| |
| can also be pre-trained by unsupervised methods<ref>[http://www.scholarpedia.org/article/Deep_belief_networks Deep belief networks] at Scholarpedia.
| |
| </ref><ref>{{cite doi|10.1162/neco.2006.18.7.1527}}</ref>
| |
| of [[Geoff Hinton]]'s lab at [[University of Toronto]]. A team from this lab won a 2012 contest sponsored by [[Merck & Co.|Merck]] to design software to help find molecules that might lead to new drugs.<ref>{{cite news |url=http://www.nytimes.com/2012/11/24/science/scientists-see-advances-in-deep-learning-a-part-of-artificial-intelligence.html |author=John Markoff |newspaper=New York Times |date=November 23, 2012 |title=Scientists See Promise in Deep-Learning Programs}}</ref>
| |
| | |
| ==Models==
| |
| Neural network models in artificial intelligence are usually referred to as artificial neural networks (ANNs); these are essentially simple mathematical models defining a function <math>\scriptstyle f : X \rightarrow Y </math> or a distribution over <math>\scriptstyle X</math> or both <math>\scriptstyle X</math> and <math>\scriptstyle Y</math>, but sometimes models are also intimately associated with a particular learning algorithm or learning rule. A common use of the phrase ANN model really means the definition of a ''class'' of such functions (where members of the class are obtained by varying parameters, connection weights, or specifics of the architecture such as the number of neurons or their connectivity).
| |
| | |
| ===Network function===
| |
| {{See also|Graphical models}}
| |
| | |
| The word ''network'' in the term 'artificial neural network' refers to the inter–connections between the neurons in the different layers of each system. An example system has three layers. The first layer has input neurons which send data via synapses to the second layer of neurons, and then via more synapses to the third layer of output neurons. More complex systems will have more layers of neurons with some having increased layers of input neurons and output neurons. The synapses store parameters called "weights" that manipulate the data in the calculations.
| |
| | |
| An ANN is typically defined by three types of parameters:
| |
| | |
| # The interconnection pattern between the different layers of neurons
| |
| # The learning process for updating the weights of the interconnections
| |
| # The activation function that converts a neuron's weighted input to its output activation.
| |
| | |
| Mathematically, a neuron's network function <math>\scriptstyle f(x)</math> is defined as a composition of other functions <math>\scriptstyle g_i(x)</math>, which can further be defined as a composition of other functions. This can be conveniently represented as a network structure, with arrows depicting the dependencies between variables. A widely used type of composition is the ''nonlinear weighted sum'', where <math>\scriptstyle f (x) = K \left(\sum_i w_i g_i(x)\right) </math>, where <math>\scriptstyle K</math> (commonly referred to as the [[activation function]]<ref>{{cite web|url=http://www.cse.unsw.edu.au/~billw/mldict.html#activnfn|title=The Machine Learning Dictionary}}</ref>) is some predefined function, such as the [[hyperbolic tangent]]. It will be convenient for the following to refer to a collection of functions <math>\scriptstyle g_i</math> as simply a vector <math>\scriptstyle g = (g_1, g_2, \ldots, g_n)</math>.
| |
| | |
| [[Image:Ann dependency (graph).svg|thumb|150px|ANN dependency graph]]
| |
| | |
| This figure depicts such a decomposition of <math>\scriptstyle f</math>, with dependencies between variables indicated by arrows. These can be interpreted in two ways.
| |
| | |
| The first view is the functional view: the input <math>\scriptstyle x</math> is transformed into a 3-dimensional vector <math>\scriptstyle h</math>, which is then transformed into a 2-dimensional vector <math>\scriptstyle g</math>, which is finally transformed into <math>\scriptstyle f</math>. This view is most commonly encountered in the context of [[Mathematical optimization|optimization]].
| |
| | |
| The second view is the probabilistic view: the [[random variable]] <math>\scriptstyle F = f(G) </math> depends upon the random variable <math>\scriptstyle G = g(H)</math>, which depends upon <math>\scriptstyle H=h(X)</math>, which depends upon the random variable <math>\scriptstyle X</math>. This view is most commonly encountered in the context of [[graphical models]].
| |
| | |
| The two views are largely equivalent. In either case, for this particular network architecture, the components of individual layers are independent of each other (e.g., the components of <math>\scriptstyle g</math> are independent of each other given their input <math>\scriptstyle h</math>). This naturally enables a degree of parallelism in the implementation.
| |
| | |
| [[Image:Recurrent ann dependency graph.png|thumb|120px| Two separate depictions of the recurrent ANN dependency graph]]
| |
| | |
| Networks such as the previous one are commonly called [[feedforward neural network|feedforward]], because their graph is a [[directed acyclic graph]]. Networks with [[path (graph theory)|cycles]] are commonly called [[Recurrent neural network|recurrent]]. Such networks are commonly depicted in the manner shown at the top of the figure, where <math>\scriptstyle f</math> is shown as being dependent upon itself. However, an implied temporal dependence is not shown.
| |
| | |
| ===Learning===
| |
| What has attracted the most interest in neural networks is the possibility of ''learning''. Given a specific ''task'' to solve, and a ''class'' of functions <math>\scriptstyle F</math>, learning means using a set of ''observations'' to find <math>\scriptstyle f^{*} \in F</math> which solves the task in some ''optimal'' sense.
| |
| | |
| This entails defining a cost function <math>\scriptstyle C : F \rightarrow \mathbb{R}</math> such that, for the optimal solution <math>\scriptstyle f^*</math>, <math>\scriptstyle C(f^*) \leq C(f)</math> <math>\scriptstyle \forall f \in F</math> – i.e., no solution has a cost less than the cost of the optimal solution (see [[Mathematical optimization]]).
| |
| | |
| The cost function <math>\scriptstyle C</math> is an important concept in learning, as it is a measure of how far away a particular solution is from an optimal solution to the problem to be solved. Learning algorithms search through the solution space to find a function that has the smallest possible cost.
| |
| | |
| For applications where the solution is dependent on some data, the cost must necessarily be a ''function of the observations'', otherwise we would not be modelling anything related to the data. It is frequently defined as a [[statistic]] to which only approximations can be made. As a simple example, consider the problem of finding the model <math>\scriptstyle f</math>, which minimizes <math>\scriptstyle C=E\left[(f(x) - y)^2\right]</math>, for data pairs <math>\scriptstyle (x,y)</math> drawn from some distribution <math>\scriptstyle \mathcal{D}</math>. In practical situations we would only have <math>\scriptstyle N</math> samples from <math>\scriptstyle \mathcal{D}</math> and thus, for the above example, we would only minimize <math>\scriptstyle \hat{C}=\frac{1}{N}\sum_{i=1}^N (f(x_i)-y_i)^2</math>. Thus, the cost is minimized over a sample of the data rather than the entire data set.
| |
| | |
| When <math>\scriptstyle N \rightarrow \infty</math> some form of [[online machine learning]] must be used, where the cost is partially minimized as each new example is seen. While online machine learning is often used when <math>\scriptstyle \mathcal{D}</math> is fixed, it is most useful in the case where the distribution changes slowly over time. In neural network methods, some form of online machine learning is frequently used for finite datasets.
| |
| | |
| {{See also|Mathematical optimization|Estimation theory|Machine learning}}
| |
| | |
| ====Choosing a cost function====
| |
| While it is possible to define some arbitrary [[ad hoc]] cost function, frequently a particular cost will be used, either because it has desirable properties (such as [[Convex function|convexity]]) or because it arises naturally from a particular formulation of the problem (e.g., in a probabilistic formulation the posterior probability of the model can be used as an inverse cost). Ultimately, the cost function will depend on the desired task. An overview of the three (3) main categories of learning tasks is provided below:
| |
| | |
| ===Learning paradigms===
| |
| There are three major learning paradigm, each corresponding to a particular abstract learning task. These are [[supervised learning]], [[unsupervised learning]] and [[reinforcement learning]].
| |
| | |
| ====Supervised learning====
| |
| In [[supervised learning]], we are given a set of example pairs <math>\scriptstyle (x, y), x \in X, y \in Y</math> and the aim is to find a function <math>\scriptstyle f : X \rightarrow Y </math> in the allowed class of functions that matches the examples. In other words, we wish to ''infer'' the mapping implied by the data; the cost function is related to the mismatch between our mapping and the data and it implicitly contains prior knowledge about the problem domain.
| |
| | |
| A commonly used cost is the [[mean-squared error]], which tries to minimize the average squared error between the network's output, f(x), and the target value y over all the example pairs. When one tries to minimize this cost using [[gradient descent]] for the class of neural networks called [[multilayer perceptron]]s, one obtains the common and well-known [[Backpropagation|backpropagation algorithm]] for training neural networks.
| |
| | |
| Tasks that fall within the paradigm of supervised learning are [[pattern recognition]] (also known as classification) and [[Regression analysis|regression]] (also known as function approximation). The supervised learning paradigm is also applicable to sequential data (e.g., for speech and gesture recognition). This can be thought of as learning with a "teacher," in the form of a function that provides continuous feedback on the quality of solutions obtained thus far.
| |
| | |
| ====Unsupervised learning====
| |
| In [[unsupervised learning]], some data <math>\scriptstyle x</math> is given and the cost function to be minimized, that can be any function of the data <math>\scriptstyle x</math> and the network's output, <math>\scriptstyle f</math>.
| |
| | |
| The cost function is dependent on the task (what we are trying to model) and our ''a priori'' assumptions (the implicit properties of our model, its parameters and the observed variables).
| |
| | |
| As a trivial example, consider the model <math>\scriptstyle f(x) = a</math> where <math>\scriptstyle a</math> is a constant and the cost <math>\scriptstyle C=E[(x - f(x))^2]</math>. Minimizing this cost will give us a value of <math>\scriptstyle a</math> that is equal to the mean of the data. The cost function can be much more complicated. Its form depends on the application: for example, in compression it could be related to the [[mutual information]] between <math>\scriptstyle x</math> and <math>\scriptstyle f(x)</math>, whereas in statistical modeling, it could be related to the [[posterior probability]] of the model given the data. (Note that in both of those examples those quantities would be maximized rather than minimized).
| |
| | |
| Tasks that fall within the paradigm of unsupervised learning are in general [[Approximation|estimation]] problems; the applications include [[Data clustering|clustering]], the estimation of [[statistical distributions]], [[Data compression|compression]] and [[Bayesian spam filtering|filtering]].
| |
| | |
| ====Reinforcement learning====
| |
| In [[reinforcement learning]], data <math>\scriptstyle x</math> are usually not given, but generated by an agent's interactions with the environment. At each point in time <math>\scriptstyle t</math>, the agent performs an action <math>\scriptstyle y_t</math> and the environment generates an observation <math>\scriptstyle x_t</math> and an instantaneous cost <math>\scriptstyle c_t</math>, according to some (usually unknown) dynamics. The aim is to discover a ''policy'' for selecting actions that minimizes some measure of a long-term cost; i.e., the expected cumulative cost. The environment's dynamics and the long-term cost for each policy are usually unknown, but can be estimated.
| |
| | |
| More formally the environment is modelled as a [[Markov decision process]] (MDP) with states <math>\scriptstyle {s_1,...,s_n}\in S </math> and actions <math>\scriptstyle {a_1,...,a_m} \in A</math> with the following probability distributions: the instantaneous cost distribution <math>\scriptstyle P(c_t|s_t)</math>, the observation distribution <math>\scriptstyle P(x_t|s_t)</math> and the transition <math>\scriptstyle P(s_{t+1}|s_t, a_t)</math>, while a policy is defined as conditional distribution over actions given the observations. Taken together, the two then define a [[Markov chain]] (MC). The aim is to discover the policy that minimizes the cost; i.e., the MC for which the cost is minimal.
| |
| | |
| ANNs are frequently used in reinforcement learning as part of the overall algorithm.<ref>{{cite conference| author = Dominic, S., Das, R., Whitley, D., Anderson, C. |date=July 1991 | title = Genetic reinforcement learning for neural networks | conference = IJCNN-91-Seattle International Joint Conference on Neural Networks | booktitle = IJCNN-91-Seattle International Joint Conference on Neural Networks | publisher = IEEE | location = Seattle, Washington, USA | url = http://dx.doi.org/10.1109/IJCNN.1991.155315 | doi = 10.1109/IJCNN.1991.155315 | accessdate = 29 July 2012 | isbn = 0-7803-0164-1 }}</ref><ref>{{cite journal|last=Hoskins|first=J.C.|coauthors=Himmelblau, D.M.|title=Process control via artificial neural networks and reinforcement learning|journal=Computers & Chemical Engineering|year=1992|volume=16|pages=241–251|doi=10.1016/0098-1354(92)80045-B|issue=4}}</ref> [[Dynamic programming]] has been coupled with ANNs (Neuro dynamic programming) by [[Dimitri Bertsekas|Bertsekas]] and Tsitsiklis<ref>{{cite book| author = Bertsekas, D.P., Tsitsiklis, J.N. | year = 1996 | title = Neuro-dynamic programming | publisher = Athena Scientific | isbn = 1-886529-10-8 | page = 512 }}</ref> and applied to multi-dimensional nonlinear problems such as those involved in [[vehicle routing]],<ref>{{cite journal|last=Secomandi|first=Nicola|coauthors=|title=Comparing neuro-dynamic programming algorithms for the vehicle routing problem with stochastic demands|journal=Computers & Operations Research|year=2000|volume=27|pages=1201–1225|doi=10.1016/S0305-0548(99)00146-X|issue=11–12}}</ref> [[natural resource management|natural resources management]]<ref>{{cite conference| author = de Rigo, D., Rizzoli, A. E., Soncini-Sessa, R., Weber, E., Zenesi, P. | year = 2001 | title = Neuro-dynamic programming for the efficient management of reservoir networks | conference = MODSIM 2001, International Congress on Modelling and Simulation | conferenceurl = http://www.mssanz.org.au/MODSIM01/MODSIM01.htm | booktitle = Proceedings of MODSIM 2001, International Congress on Modelling and Simulation | publisher = Modelling and Simulation Society of Australia and New Zealand | location = Canberra, Australia | doi = 10.5281/zenodo.7481 | url = https://zenodo.org/record/7482/files/de_Rigo_etal_MODSIM2001_activelink_authorcopy.pdf | accessdate = 29 July 2012 | isbn = 0-867405252 }}</ref><ref>{{cite conference| author = Damas, M., Salmeron, M., Diaz, A., Ortega, J., Prieto, A., Olivares, G.| year = 2000 | title = Genetic algorithms and neuro-dynamic programming: application to water supply networks | conference = 2000 Congress on Evolutionary Computation | booktitle = Proceedings of 2000 Congress on Evolutionary Computation | publisher = IEEE | location = La Jolla, California, USA | url = http://dx.doi.org/10.1109/CEC.2000.870269 | doi = 10.1109/CEC.2000.870269 | accessdate = 29 July 2012 | isbn = 0-7803-6375-2 }}</ref> or [[medicine]]<ref>{{cite journal|last=Deng|first=Geng|coauthors=Ferris, M.C.|title=Neuro-dynamic programming for fractionated radiotherapy planning|journal=Springer Optimization and Its Applications|year=2008|volume=12|pages=47–70 |doi=10.1007/978-0-387-73299-2_3}}</ref> because of the ability of ANNs to mitigate losses of accuracy even when reducing the discretization grid density for numerically approximating the solution of the original control problems.
| |
| | |
| Tasks that fall within the paradigm of reinforcement learning are control problems, [[game]]s and other [[sequential decision making]] tasks.
| |
| | |
| {{See also|dynamic programming|stochastic control}}
| |
| | |
| ===Learning algorithms===
| |
| Training a neural network model essentially means selecting one model from the set of allowed models (or, in a [[Bayesian probability|Bayesian]] framework, determining a distribution over the set of allowed models) that minimizes the cost criterion. There are numerous algorithms available for training neural network models; most of them can be viewed as a straightforward application of [[Mathematical optimization|optimization]] theory and [[statistical estimation]].
| |
| | |
| Most of the algorithms used in training artificial neural networks employ some form of [[gradient descent]]. This is done by simply taking the derivative of the cost function with respect to the network parameters and then changing those parameters in a [[gradient-related]] direction.
| |
| | |
| [[Evolutionary methods]],<ref>{{cite conference| author = de Rigo, D., Castelletti, A., Rizzoli, A.E., Soncini-Sessa, R., Weber, E. |date=January 2005 | title = A selective improvement technique for fastening Neuro-Dynamic Programming in Water Resources Network Management | conference = 16th IFAC World Congress | conferenceurl = http://www.nt.ntnu.no/users/skoge/prost/proceedings/ifac2005/Index.html | booktitle = Proceedings of the 16th IFAC World Congress – IFAC-PapersOnLine | editor = Pavel Zítek | volume = 16 | publisher = IFAC | location = Prague, Czech Republic | url = http://www.nt.ntnu.no/users/skoge/prost/proceedings/ifac2005/Papers/Paper4269.html
| |
| | accessdate = 30 December 2011 | doi = 10.3182/20050703-6-CZ-1902.02172 | isbn = 978-3-902661-75-3 }}</ref> [[gene expression programming]],<ref>{{cite web|last=Ferreira|first=C.|year=2006|title=Designing Neural Networks Using Gene Expression Programming|url= http://www.gene-expression-programming.com/webpapers/Ferreira-ASCT2006.pdf|publisher= In A. Abraham, B. de Baets, M. Köppen, and B. Nickolay, eds., Applied Soft Computing Technologies: The Challenge of Complexity, pages 517–536, Springer-Verlag}}</ref> [[simulated annealing]],<ref>{{cite conference| author = Da, Y., Xiurun, G. |date=July 2005 | title = An improved PSO-based ANN with simulated annealing technique | conference = New Aspects in Neurocomputing: 11th European Symposium on Artificial Neural Networks | conferenceurl = http://www.dice.ucl.ac.be/esann/proceedings/electronicproceedings.htm | editor = T. Villmann | publisher = Elsevier | accessdate = 30 December 2011 | doi = 10.1016/j.neucom.2004.07.002 }}</ref> [[expectation-maximization]], [[non-parametric methods]] and [[particle swarm optimization]]<ref>{{cite conference| author = Wu, J., Chen, E. |date=May 2009 | title = A Novel Nonparametric Regression Ensemble for Rainfall Forecasting Using Particle Swarm Optimization Technique Coupled with Artificial Neural Network | conference = 6th International Symposium on Neural Networks, ISNN 2009 | conferenceurl = http://www2.mae.cuhk.edu.hk/~isnn2009/ | editor = Wang, H., Shen, Y., Huang, T., Zeng, Z. | publisher = Springer | accessdate = 1 January 2012 | doi = 10.1007/978-3-642-01513-7_6 | isbn = 978-3-642-01215-0 }}</ref> are some commonly used methods for training neural networks. {{See also|machine learning}}
| |
| | |
| ==Employing artificial neural networks==
| |
| Perhaps the greatest advantage of ANNs is their ability to be used as an arbitrary function approximation mechanism that 'learns' from observed data. However, using them is not so straightforward, and a relatively good understanding of the underlying theory is essential.
| |
| * Choice of model: This will depend on the data representation and the application. Overly complex models tend to lead to problems with learning.
| |
| * Learning algorithm: There are numerous trade-offs between learning algorithms. Almost any algorithm will work well with the ''correct [[hyperparameter]]s'' for training on a particular fixed data set. However, selecting and tuning an algorithm for training on unseen data requires a significant amount of experimentation.
| |
| * Robustness: If the model, cost function and learning algorithm are selected appropriately the resulting ANN can be extremely robust.
| |
| | |
| With the correct implementation, ANNs can be used naturally in [[online algorithm|online learning]] and large data set applications. Their simple implementation and the existence of mostly local dependencies exhibited in the structure allows for fast, parallel implementations in hardware.
| |
| | |
| ==Applications==
| |
| The utility of artificial neural network models lies in the fact that they can be used to infer a function from observations. This is particularly useful in applications where the complexity of the data or task makes the design of such a function by hand impractical.
| |
| | |
| ===Real-life applications===
| |
| The tasks artificial neural networks are applied to tend to fall within the following broad categories:
| |
| * [[Function approximation]], or [[regression analysis]], including [[time series prediction]], [[fitness approximation]] and modeling.
| |
| * [[Statistical classification|Classification]], including [[Pattern recognition|pattern]] and sequence recognition, [[novelty detection]] and sequential decision making.
| |
| * [[Data processing]], including filtering, clustering, [[blind source separation]] and compression.
| |
| * [[Robotics]], including directing manipulators, [[prosthesis]].
| |
| * [[Control engineering|Control]], including [[Computer numerical control]].
| |
| | |
| Application areas include the system identification and control (vehicle control, process control, [[natural resource]]s management), quantum chemistry,<ref name=Balabin_2009>{{Cite journal|journal=[[J. Chem. Phys.]] |volume = 131 |issue = 7 |page = 074104 |doi=10.1063/1.3206326 |title=Neural network approach to quantum-chemistry data: Accurate prediction of density functional theory energies |year=2009 |author=Roman M. Balabin, Ekaterina I. Lomakina |pmid=19708729}}</ref> game-playing and decision making (backgammon, chess, [[poker]]), pattern recognition (radar systems, face identification, object recognition and more), sequence recognition (gesture, speech, handwritten text recognition), medical diagnosis, financial applications (automated trading systems), [[data mining]] (or knowledge discovery in databases, "KDD"), visualization and [[e-mail spam]] filtering.
| |
| | |
| Artificial neural networks have also been used to diagnose several cancers. An ANN based hybrid lung cancer detection system named HLND improves the accuracy of diagnosis and the speed of lung cancer radiology.<ref>{{cite web|last=Ganesan|first=N|title=Application of Neural Networks in Diagnosing Cancer Disease Using Demographic Data|url=http://www.ijcaonline.org/journal/number26/pxc387783.pdf|publisher=International Journal of Computer Applications}}</ref> These networks have also been used to diagnose prostate cancer. The diagnoses can be used to make specific models taken from a large group of patients compared to information of one given patient. The models do not depend on assumptions about correlations of different variables. Colorectal cancer has also been predicted using the neural networks. Neural networks could predict the outcome for a patient with colorectal cancer with more accuracy than the current clinical methods. After training, the networks could predict multiple patient outcomes from unrelated institutions.<ref>{{cite web|last=Bottaci|first=Leonardo|title=Artificial Neural Networks Applied to Outcome Prediction for Colorectal Cancer Patients in Separate Institutions|url=http://www.lcc.uma.es/~jja/recidiva/042.pdf|publisher=The Lancet}}</ref>
| |
| | |
| ===Neural networks and neuroscience===
| |
| Theoretical and [[computational neuroscience]] is the field concerned with the theoretical analysis and the computational modeling of biological neural systems. Since neural systems are intimately related to cognitive processes and behavior, the field is closely related to cognitive and behavioral modeling.
| |
| | |
| The aim of the field is to create models of biological neural systems in order to understand how biological systems work. To gain this understanding, neuroscientists strive to make a link between observed biological processes (data), biologically plausible mechanisms for neural processing and learning ([[biological neural network]] models) and theory (statistical learning theory and [[information theory]]).
| |
| | |
| ====Types of models====
| |
| Many models are used in the field, defined at different levels of abstraction and modeling different aspects of neural systems. They range from models of the short-term behavior of [[biological neuron models|individual neurons]], models of how the dynamics of neural circuitry arise from interactions between individual neurons and finally to models of how behavior can arise from abstract neural modules that represent complete subsystems. These include models of the long-term, and short-term plasticity, of neural systems and their relations to learning and memory from the individual neuron to the system level.
| |
| | |
| ==Neural network software==
| |
| {{Main|Neural network software}}
| |
| | |
| '''Neural network software''' is used to [[Simulation|simulate]], [[research]], develop and apply artificial neural networks, [[biological neural network]]s and, in some cases, a wider array of [[adaptive system]]s.
| |
| | |
| ==Types of artificial neural networks==
| |
| <!-- Split to [[Types of artificial neural networks]] -->
| |
| {{Main|Types of artificial neural networks}}
| |
| | |
| Artificial neural network types vary from those with only one or two layers of single direction logic, to complicated multi–input many directional feedback loops and layers. On the whole, these systems use algorithms in their programming to determine control and organization of their functions. Some may be as simple as a one-neuron layer with an input and an output, and others can mimic complex systems such as [[List of artificial intelligence projects#Software libraries|dANN]], which can mimic chromosomal DNA through sizes at the cellular level, into artificial organisms and simulate reproduction, mutation and population sizes.<ref>{{cite web|title=DANN:Genetic Wavelets|url=http://wiki.syncleus.com/index.php/DANN:Genetic_Wavelets|publisher=dANN project|accessdate=12 July 2010| archiveurl= http://web.archive.org/web/20100821112612/http://wiki.syncleus.com/index.php/DANN:Genetic_Wavelets| archivedate= 21 August 2010 <!--DASHBot-->| deadurl= no}}</ref>
| |
| | |
| Most systems use "weights" to change the parameters of the throughput and the varying connections to the neurons. Artificial neural networks can be autonomous and learn by input from outside "teachers" or even self-teaching from written-in rules.
| |
| | |
| ==Theoretical properties==
| |
| | |
| ===Computational power===
| |
| The [[multi-layer perceptron]] (MLP) is a universal function approximator, as proven by the [[Cybenko theorem]]. However, the proof is not constructive regarding the number of neurons required or the settings of the weights.
| |
| | |
| Work by [[Hava Siegelmann]] and [[Eduardo D. Sontag]] has provided a proof that a specific recurrent architecture with rational valued weights (as opposed to full precision [[real number]]-valued weights) has the full power of a [[Universal Turing Machine]]<ref>{{Cite journal| title = Turing computability with neural nets | url = http://www.math.rutgers.edu/~sontag/FTP_DIR/aml-turing.pdf | year = 1991 | journal = Appl. Math. Lett. | pages = 77–80 | volume = 4 | issue = 6 | last1 = Siegelmann | first1 = H.T. | last2 = Sontag | first2 = E.D. | doi = 10.1016/0893-9659(91)90080-F }}</ref> using a finite number of neurons and standard linear connections. They have further shown that the use of irrational values for weights results in a machine with [[Hypercomputation|super-Turing]] power.{{Citation needed|date=August 2011}}
| |
| | |
| ===Capacity===
| |
| Artificial neural network models have a property called 'capacity', which roughly corresponds to their ability to model any given function. It is related to the amount of information that can be stored in the network and to the notion of complexity.
| |
| | |
| ===Convergence===
| |
| Nothing can be said in general about convergence since it depends on a number of factors. Firstly, there may exist many local minima. This depends on the cost function and the model. Secondly, the optimization method used might not be guaranteed to converge when far away from a local minimum. Thirdly, for a very large amount of data or parameters, some methods become impractical. In general, it has been found that theoretical guarantees regarding convergence are an unreliable guide to practical application. {{Citation needed|date=March 2012}}
| |
| | |
| ===Generalization and statistics===
| |
| In applications where the goal is to create a system that generalizes well in unseen examples, the problem of over-training has emerged. This arises in convoluted or over-specified systems when the capacity of the network significantly exceeds the needed free parameters. There are two schools of thought for avoiding this problem: The first is to use [[cross-validation (statistics)|cross-validation]] and similar techniques to check for the presence of overtraining and optimally select hyperparameters such as to minimize the generalization error. The second is to use some form of ''[[regularization (mathematics)|regularization]]''. This is a concept that emerges naturally in a probabilistic (Bayesian) framework, where the regularization can be performed by selecting a larger prior probability over simpler models; but also in statistical learning theory, where the goal is to minimize over two quantities: the 'empirical risk' and the 'structural risk', which roughly corresponds to the error over the training set and the predicted error in unseen data due to overfitting.
| |
| [[Image:Synapse deployment.jpg|thumb|right|200px|Confidence analysis of a neural network]]
| |
| Supervised neural networks that use an [[Mean squared error|MSE]] cost function can use formal statistical methods to determine the confidence of the trained model. The MSE on a validation set can be used as an estimate for variance. This value can then be used to calculate the [[confidence interval]] of the output of the network, assuming a [[normal distribution]]. A confidence analysis made this way is statistically valid as long as the output [[probability distribution]] stays the same and the network is not modified.
| |
| | |
| By assigning a [[softmax activation function]], a generalization of the [[logistic function]], on the output layer of the neural network (or a softmax component in a component-based neural network) for categorical target variables, the outputs can be interpreted as posterior probabilities. This is very useful in classification as it gives a certainty measure on classifications.
| |
| | |
| The softmax activation function is:
| |
| :<math>y_i=\frac{e^{x_i}}{\sum_{j=1}^c e^{x_j}}</math>
| |
| | |
| ===Dynamic properties===
| |
| {{Expert-subject|Technology|date=November 2008}}
| |
| Various techniques originally developed for studying disordered magnetic systems (i.e., the [[spin glass]]) have been successfully applied to simple neural network architectures, such as the [[Hopfield network]]. Influential work by E. Gardner and B. Derrida has revealed many interesting properties about [[perceptron]]s with real-valued synaptic weights, while later work by W. Krauth and M. Mezard has extended these principles to binary-valued synapses.
| |
| | |
| ==Criticism==
| |
| A common criticism of neural networks, particularly in robotics, is that they require a large diversity of training for real-world operation. This is not surprising, since any learning machine needs sufficient representative examples in order to capture the underlying structure that allows it to generalize to new cases. Dean Pomerleau, in his research presented in the paper "Knowledge-based Training of Artificial Neural Networks for Autonomous Robot Driving," uses a neural network to train a robotic vehicle to drive on multiple types of roads (single lane, multi-lane, dirt, etc.). A large amount of his research is devoted to (1) extrapolating multiple training scenarios from a single training experience, and (2) preserving past training diversity so that the system does not become overtrained (if, for example, it is presented with a series of right turns – it should not learn to always turn right). These issues are common in neural networks that must decide from amongst a wide variety of responses, but can be dealt with in several ways, for example by randomly shuffling the training examples, by using a numerical optimization algorithm that does not take too large steps when changing the network connections following an example, or by grouping examples in so-called mini-batches.
| |
| | |
| [[A. K. Dewdney]], a former ''[[Scientific American]]'' columnist, wrote in 1997, "Although neural nets do solve a few toy problems, their powers of computation are so limited that I am surprised anyone takes them seriously as a general problem-solving tool." (Dewdney, p. 82)
| |
| | |
| Arguments for Dewdney's position are that to implement large and effective software neural networks, much processing and storage resources need to be committed. While the brain has hardware tailored to the task of processing signals through a [[Graph (mathematics)|graph]] of neurons, simulating even a most simplified form on [[Von Neumann]] technology may compel a neural network designer to fill many millions of [[database]] rows for its connections – which can consume vast amounts of computer [[Random-access memory|memory]] and [[Hard drive|hard disk]] space. Furthermore, the designer of neural network systems will often need to simulate the transmission of signals through many of these connections and their associated neurons – which must often be matched with incredible amounts of [[CPU]] processing power and time. While neural networks often yield ''effective'' programs, they too often do so at the cost of ''efficiency'' (they tend to consume considerable amounts of time and money).
| |
| | |
| Arguments against Dewdney's position are that neural nets have been successfully used to solve many complex and diverse tasks, ranging from autonomously flying aircraft<ref>[http://www.nasa.gov/centers/dryden/news/NewsReleases/2003/03-49.html NASA - Dryden Flight Research Center - News Room: News Releases: NASA NEURAL NETWORK PROJECT PASSES MILESTONE]. Nasa.gov. Retrieved on 2013-11-20.</ref> to detecting credit card fraud {{citation needed|date=August 2012}}.
| |
| | |
| Technology writer [[Roger Bridgman]] commented on Dewdney's statements about neural nets:
| |
| <blockquote>Neural networks, for instance, are in the dock not only because they have been hyped to high heaven, (what hasn't?) but also because you could create a successful net without understanding how it worked: the bunch of numbers that captures its behaviour would in all probability be "an opaque, unreadable table...valueless as a scientific resource".
| |
| | |
| In spite of his emphatic declaration that science is not technology, Dewdney seems here to pillory neural nets as bad science when most of those devising them are just trying to be good engineers. An unreadable table that a useful machine could read would still be well worth having.<ref>[http://members.fortunecity.com/templarseries/popper.html Roger Bridgman's defence of neural networks]</ref>
| |
| </blockquote>
| |
| In response to this kind of criticism, one should note that although it is true that analyzing what has been learned by an artificial neural network is difficult, it is much easier to do so than to analyze what has been learned by a biological neural network. Furthermore, researchers involved in exploring learning algorithms for neural networks are gradually uncovering generic principles which allow a learning machine to be successful. For example, Bengio and LeCun (2007) wrote an article regarding local vs non-local learning, as well as shallow vs deep architecture.<ref>http://www.iro.umontreal.ca/~lisa/publications2/index.php/publications/show/4</ref>
| |
| | |
| Some other criticisms came from believers of hybrid models (combining neural networks and symbolic approaches). They advocate the intermix of these two approaches and believe that hybrid models can better capture the mechanisms of the human mind (Sun and Bookman, 1990).
| |
| | |
| ==Gallery==
| |
| <gallery widths="220">
| |
| Image:Single_layer_ann.svg|A single-layer feedforward artificial neural network. Arrows originating from <math>\scriptstyle x_2</math> are omitted for clarity. There are p inputs to this network and q outputs. In this system, the value of the qth output, <math>\scriptstyle y_q</math> would be calculated as <math>\scriptstyle y_q = \sum(x_i*w_{iq}) </math>
| |
| Image:Two_layer_ann.svg|A two-layer feedforward artificial neural network.
| |
| Image:Artificial_neural_network.svg
| |
| Image:Ann_dependency_(graph).svg
| |
| </gallery>
| |
| | |
| ==See also==
| |
| {{columns-list|3|
| |
| * [[20Q]]
| |
| * [[ADALINE]]
| |
| * [[Adaptive resonance theory]]
| |
| * [[Artificial life]]
| |
| * [[Associative Memory Base|Associative memory]]
| |
| * [[Autoencoder]]
| |
| * [[Backpropagation]]
| |
| * [[BEAM robotics]]
| |
| * [[Biological cybernetics]]
| |
| * [[Biologically inspired computing]]
| |
| * [[Blue brain]]
| |
| * [[Cerebellar Model Articulation Controller]]
| |
| * [[Cognitive architecture]]
| |
| * [[Cognitive science]]
| |
| * [[Connectionist expert system]]
| |
| * [[Connectomics]]
| |
| * [[Cultured neuronal networks]]
| |
| * [[Digital morphogenesis]]
| |
| * [[Encog]]
| |
| * [[Fuzzy logic]]
| |
| * [[Gene expression programming]]
| |
| * [[Genetic algorithm]]
| |
| * [[Group method of data handling]]
| |
| * [[Habituation]]
| |
| * [[In Situ Adaptive Tabulation]]
| |
| * [[Memristor]]
| |
| * [[Multilinear subspace learning]]
| |
| * [[Neuroevolution]]
| |
| * [[Neural gas]]
| |
| * [[Neural network software]]
| |
| * [[Neuroscience]]
| |
| * [[Ni1000]] chip
| |
| * [[Nonlinear system identification]]
| |
| * [[Optical neural network]]
| |
| * [[Parallel Constraint Satisfaction Processes]]
| |
| * [[Parallel distributed processing]]
| |
| * [[Radial basis function network]]
| |
| * [[Recurrent neural networks]]
| |
| * [[Self-organizing map]]
| |
| * [[Systolic array]]
| |
| * [[Tensor product network]]
| |
| * [[Time delay neural network]] (TDNN)
| |
| }}
| |
| | |
| ==References==
| |
| {{Reflist|2}}
| |
| | |
| ==Bibliography==
| |
| <div class="references-small">
| |
| * {{Cite journal| author=Bhadeshia H. K. D. H. | year=1999 |
| |
| title=Neural Networks in Materials Science | journal=ISIJ International | volume=39 |pages=966–979 | doi=10.2355/isijinternational.39.966 | url=http://www.msm.cam.ac.uk/phase-trans/abstracts/neural.review.pdf| issue=10}}
| |
| * Bishop, C.M. (1995) ''Neural Networks for Pattern Recognition'', Oxford: Oxford University Press. ISBN 0-19-853849-9 (hardback) or ISBN 0-19-853864-2 (paperback)
| |
| * Cybenko, G.V. (1989). Approximation by Superpositions of a Sigmoidal function, ''[[Mathematics of Control, Signals, and Systems]]'', Vol. 2 pp. 303–314. [http://actcomm.dartmouth.edu/gvc/papers/approx_by_superposition.pdf electronic version]
| |
| * Duda, R.O., Hart, P.E., Stork, D.G. (2001) ''Pattern classification (2nd edition)'', Wiley, ISBN 0-471-05669-3
| |
| * {{Cite journal| author=Egmont-Petersen, M., de Ridder, D., Handels, H. | year=2002 |
| |
| title=Image processing with neural networks – a review | journal=Pattern Recognition | volume=35 | pages=2279–2301 | doi = 10.1016/S0031-3203(01)00178-9 | issue=10
| |
| }}
| |
| * Gurney, K. (1997) ''An Introduction to Neural Networks'' London: Routledge. ISBN 1-85728-673-1 (hardback) or ISBN 1-85728-503-4 (paperback)
| |
| * Haykin, S. (1999) '' Neural Networks: A Comprehensive Foundation'', Prentice Hall, ISBN 0-13-273350-1
| |
| * Fahlman, S, Lebiere, C (1991). ''The Cascade-Correlation Learning Architecture'', created for [[National Science Foundation]], Contract Number EET-8716324, and [[Defense Advanced Research Projects Agency]] (DOD), ARPA Order No. 4976 under Contract F33615-87-C-1499. [http://www.cs.iastate.edu/~honavar/fahlman.pdf electronic version]
| |
| * Hertz, J., Palmer, R.G., Krogh. A.S. (1990) ''Introduction to the theory of neural computation'', Perseus Books. ISBN 0-201-51560-1
| |
| * Lawrence, Jeanette (1994) ''Introduction to Neural Networks'', California Scientific Software Press. ISBN 1-883157-00-5
| |
| * Masters, Timothy (1994) ''Signal and Image Processing with Neural Networks'', John Wiley & Sons, Inc. ISBN 0-471-04963-8
| |
| * [[Brian D. Ripley|Ripley, Brian D]]. (1996) ''Pattern Recognition and Neural Networks'', Cambridge
| |
| * Siegelmann, H.T. and [[Eduardo D. Sontag|Sontag, E.D.]] (1994). Analog computation via neural networks, ''Theoretical Computer Science'', v. 131, no. 2, pp. 331–360. [http://www.math.rutgers.edu/~sontag/FTP_DIR/nets-real.pdf electronic version]
| |
| * Sergios Theodoridis, Konstantinos Koutroumbas (2009) "Pattern Recognition", 4th Edition, Academic Press, ISBN 978-1-59749-272-0.
| |
| * Smith, Murray (1993) ''Neural Networks for Statistical Modeling'', Van Nostrand Reinhold, ISBN 0-442-01310-8
| |
| * Wasserman, Philip (1993) ''Advanced Methods in Neural Computing'', Van Nostrand Reinhold, ISBN 0-442-00461-3
| |
| * ''Computational Intelligence: A Methodological Introduction'' by Kruse, Borgelt, Klawonn, Moewes, Steinbrecher, Held, 2013, Springer, ISBN 9781447150121
| |
| * ''Neuro-Fuzzy-Systeme'' (3rd edition) by Borgelt, Klawonn, Kruse, Nauck, 2003, Vieweg, ISBN 9783528252656
| |
| | |
| </div>
| |
| | |
| ==External links==
| |
| <!--
| |
| Do not post software links here. If you must, use the Neural Network Software article. Remember however that Wikipedia is neither a link repository nor the place to promote products or show off your code.
| |
| -->
| |
| {{wikibooks|Artificial Neural Networks}}
| |
| * {{dmoz|Computers/Artificial_Intelligence/Neural_Networks|Neural Networks}}
| |
| | |
| {{DEFAULTSORT:Artificial Neural Network}}
| |
| [[Category:Computational statistics]]
| |
| [[Category:Neural networks]]
| |
| [[Category:Classification algorithms]]
| |
| [[Category:Computational neuroscience]]
| |
| [[Category:Knowledge representation]]
| |
| | |
| [[ro:Rețea neurală artificială]]
| |