Artificial Neural Network *
In machine learning and cognitive science, artificial neural networks (ANNs) are a family of statistical learning models inspired by biological neural networks (the central nervous systems of animals, in particular the brain) and are used to estimate or approximate functions that can depend on a large number of inputs and are generally unknown. Artificial neural networks are generally presented as systems of interconnected "neurons" which send messages to each other. The connections have numeric weights that can be tuned based on experience, making neural nets adaptive to inputs and capable of learning.
For example, a neural network for handwriting recognition is defined by a set of input neurons which may be activated by the pixels of an input image.After being weighted and transformed by a function (determined by the network's designer), the activations of these neurons are then passed on to other neurons. This process is repeated until finally, an output neuron is activated. This determines which character was read.
Like other machine learning methods  systems that learn from data  neural networks have been used to solve a wide variety of tasks that are hard to solve using ordinary rulebased programming, including computer vision and speech recognition.
Background
Examinations of the human's central nervous system inspired the concept of neural networks. In an Artificial Neural Network, simple artificial nodes, known as "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. However, a class of statistical models may commonly be called "Neural" if they possess the following characteristics:
1 consist of sets of adaptive weights, i.e. numerical parameters that are tuned by a learning algorithm, and
2 are capable of approximating nonlinear functions of their inputs.
The adaptive weights are conceptually connection strengths between neurons, which are activated during training and prediction.
An artificial neural network is an interconnected group of nodes, akin to the vast network of neurons 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.
Neural networks are 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 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 nonadaptive elements.While the more general approach of such systems is more suitable for realworld 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 nonlinear, distributed, parallel and local processing and adaptation. Historically, the use of neural networks models marked a paradigm shift in the late eighties from highlevel (symbolic) AI, characterized by expert systems with knowledge embodied in ifthen rules, to lowlevel (subsymbolic) machine learning, characterized by knowledge embodied in the parameters of a dynamical system.
History
Warren McCulloch and Walter Pitts[1] (1943) created a computational model for neural networks based on mathematics and algorithms called threshold logic. This 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[2] 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 Turing's Btype machines.
Farley and Wesley A. Clark[3] (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[4] (1956).
Frank Rosenblatt[5] (1958) created the perceptron, an algorithm for pattern recognition based on a twolayer learning computer network using simple addition and subtraction. With mathematical notation, Rosenblatt also described circuitry not in the basic perceptron, such as the exclusiveor circuit, a circuit whose mathematical computation could not be processed until after the backpropagation algorithm was created by Paul Werbos[6] (1975).
Neural network research stagnated after the publication of machine learning research by Marvin Minsky and Seymour Papert[7] (1969), who discovered two key issues with the computational machines that processed neural networks. The first was that singlelayer neural networks were incapable of processing the exclusiveor 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 exclusiveor problem (Werbos 1975).[6]
The parallel distributed processing of the mid1980s became popular under the name connectionism. The text by David E. Rumelhart and James McClelland[8] (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.[9]
Neural networks were gradually overtaken in popularity in machine learning by support vector machines and other, much simpler methods such as linear classifiers. Renewed interest in neural nets was sparked in the late 2000s by the advent of deep learning.
Improvements since 2006
Computational devices have been created in CMOS, for both biophysical simulation and neuromorphic computing. More recent efforts show promise for creating nanodevices[10] for very large scale principal components analyses and convolution. If successful, these efforts could usher in a new era of neural computing[11] that is a step beyond digital computing, because it depends on learning rather than programming and because it is fundamentally analog rather than digital even though the first instantiations may in fact be with CMOS digital devices.
Between 2009 and 2012, the recurrent neural networks and deep feedforward neural networks developed in the research group of Jürgen Schmidhuber at the Swiss AI Lab IDSIA have won eight international competitions in pattern recognition and machine learning.[12][13] For example, the bidirectional and multidimensional long short term memory (LSTM)[14][15][16][17] 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 GPUbased 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,[18][19] the ISBI 2012 Segmentation of Neuronal Structures in Electron Microscopy Stacks challenge,[20] and others. Their neural networks also were the first artificial pattern recognizers to achieve humancompetitive or even superhuman performance[21] on important benchmarks such as traffic sign recognition (IJCNN 2012), or the MNIST handwritten digits problem of Yann LeCun at NYU.
Deep, highly nonlinear neural architectures similar to the 1980 neocognitron by Kunihiko Fukushima[22] and the "standard architecture of vision",[23] inspired by the simple and complex cells identified by David H. Hubel and Torsten Wiesel in the primary visual cortex, can also be pretrained by unsupervised methods[24][25] of Geoff Hinton's lab at University of Toronto.[26][27] A team from this lab won a 2012 contest sponsored by Merck to design software to help find molecules that might lead to new drugs.[28]
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 f : X > Y or a distribution over \textstyle X or both X and Y, 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
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:
1 The interconnection pattern between the different layers of neurons
2 The learning process for updating the weights of the interconnections
3 The activation function that converts a neuron's weighted input to its output activation.
Mathematically, a neuron's network function f(x) is defined as a composition of other functions g_{i}(x), 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 f (x) = K (∑_{i} w_{i} g_{i}(x)) , where K (commonly referred to as the activation function[29]) is some predefined function, such as the hyperbolic tangent. It will be convenient for the following to refer to a collection of functions g_{i} as simply a vector g = (g_{1,}g_{2,.......}g_{n})
This figure depicts such a decomposition of f , with dependencies between variables indicated by arrows. These can be interpreted in two ways.
The first view is the functional view: the input x , is transformed into a 3dimensional vector h , which is then transformed into a 2dimensional vector g , which is finally transformed into f. This view is most commonly encountered in the context of optimization.
The second view is the probabilistic view: the random variable F= f(G) depends upon the random variable
, which depends upon
, which depends upon the random variable X . 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 g are independent of each other given their input h). This naturally enables a degree of parallelism in the implementation.
Networks such as the previous one are commonly called feedforward, because their graph is a directed acyclic graph. Networks with cycles are commonly called recurrent. Such networks are commonly depicted in the manner shown at the top of the figure, where f s 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
, learning means using a set of observations to find
which solves the task in some optimal sense.
This entails defining a cost function
such that, for the optimal solution
– i.e., no solution has a cost less than the cost of the optimal solution
The cost function
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
, which minimizes
, for data pairs
drawn from some distribution
. In practical situations we would only have
samples from
and thus, for the above example, we would only minimize
. Thus, the cost is minimized over a sample of the data rather than the entire data set.
When
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
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.
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 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 main categories of learning tasks is provided below:
Learning paradigms
There are three major learning paradigms, 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
and the aim is to find a function
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 meansquared 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 perceptrons, one obtains the common and wellknown backpropagation algorithm for training neural networks.
Tasks that fall within the paradigm of supervised learning are pattern recognition (also known as classification) and 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 x , is given and the cost function to be minimized, that can be any function of the data x , and the network's output, f.
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 f(x)= a where a is a constant and the cost
. Minimizing this cost will give us a value of a 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 x and f(x) , 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 estimation problems; the applications include clustering, the estimation of statistical distributions, compression and filtering.
Reinforcement learning
In reinforcement learning, data x are usually not given, but generated by an agent's interactions with the environment. At each point in time t, the agent performs an action y_{t} and the environment generates an observation x_{t} and an instantaneous cost c_{t}, according to some (usually unknown) dynamics. The aim is to discover a policy for selecting actions that minimizes some measure of a longterm cost; i.e., the expected cumulative cost. The environment's dynamics and the longterm 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
and actions
with the following probability distributions: the instantaneous cost distribution
, the observation distribution
and the transition
, 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.[30][31] Dynamic programming has been coupled with ANNs (Neuro dynamic programming) by Bertsekas and Tsitsiklis[32] and applied to multidimensional nonlinear problems such as those involved in vehicle routing,[33] natural resources management[34][35] or medicine[36] 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, games and other sequential decision making tasks.
Learning algorithms
Training a neural network model essentially means selecting one model from the set of allowed models (or, in a 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 optimization theory and statistical estimation.
Most of the algorithms used in training artificial neural networks employ some form of gradient descent, using backpropagation to compute the actual gradients. 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 gradientrelated direction.
Evolutionary methods,[37] gene expression programming,[38] simulated annealing,[39] expectationmaximization, nonparametric methods and particle swarm optimization[40] are some commonly used methods for training neural networks.
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 tradeoffs between learning algorithms. Almost any algorithm will work well with the correct hyperparameters 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 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.
Reallife 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.

Classification, including 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, including Computer numerical control.
Application areas include the system identification and control (vehicle control, process control, natural resources management), quantum chemistry,[41] gameplaying 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 (e.g. automated trading systems), data mining (or knowledge discovery in databases, "KDD"), visualization and email 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.[42] 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.[43]
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 shortterm behavior of 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 longterm, and shortterm plasticity, of neural systems and their relations to learning and memory from the individual neuron to the system level.
Neural network software
Neural network software is used to simulate, research, develop and apply artificial neural networks, biological neural networks and, in some cases, a wider array of adaptive systems.
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. 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 selfteaching from writtenin rules.
Theoretical properties
Computational power
The multilayer perceptron (MLP) is a universal function approximator, as proven by the universal approximation 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 numbervalued weights) has the full power of a Universal Turing Machine[44] using a finite number of neurons and standard linear connections. Further, it has been shown that the use of irrational values for weights results in a machine with superTuring power.[45]
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.
Generalization and statistics
In applications where the goal is to create a system that generalizes well in unseen examples, the problem of overtraining has emerged. This arises in convoluted or overspecified 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 crossvalidation 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. 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.
Supervised neural networks that use a 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 componentbased 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:
Controversies
Training issues
A common criticism of neural networks, particularly in robotics, is that they require a large diversity of training for realworld operation[citation needed]. 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 "Knowledgebased 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, multilane, 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 socalled minibatches.
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 problemsolving tool." (Dewdney, p. 82)
Hardware issues
To implement large and effective software neural networks, considerable processing and storage resources need to be committed[citation needed]. While the brain has hardware tailored to the task of processing signals through a 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 memory and 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).
Computing power continues to grow roughly according to Moore's Law, which may provide sufficient resources to accomplish new tasks. Neuromorphic engineering addresses the hardware difficulty directly, by constructing nonVonNeumann chips with circuits designed to implement neural nets from the ground up.
Practical counterexamples to criticisms
Arguments against Dewdney's position are that neural networks have been successfully used to solve many complex and diverse tasks, ranging from autonomously flying aircraft[46] to detecting credit card fraud .[citation needed]
Technology writer Roger Bridgman commented on Dewdney's statements about neural nets:
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.[47]
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 nonlocal learning, as well as shallow vs deep architecture.[48]
Hybrid approaches
Some other criticisms come from advocates of hybrid models (combining neural networks and symbolic approaches), who believe that the intermix of these two approaches can better capture the mechanisms of the human mind.[49][50]
Gallery
1 2
1. A singlelayer feedforward artificial neural network. Arrows originating from
are omitted for clarity. There are p inputs to this network and q outputs. In this system, the value of the qth output,
would be calculated as
2. A twolayer feedforward artificial neural network.
References

McCulloch, Warren; Walter Pitts (1943). "A Logical Calculus of Ideas Immanent in Nervous Activity". Bulletin of Mathematical Biophysics 5 (4): 115–133. doi:10.1007/BF02478259.

Hebb, Donald (1949). The Organization of Behavior. New York: Wiley.

Farley, B.G.; W.A. Clark (1954). "Simulation of SelfOrganizing Systems by Digital Computer". IRE Transactions on Information Theory 4 (4): 76–84. doi:10.1109/TIT.1954.1057468.

Rochester, N.; J.H. Holland, L.H. Habit, and W.L. Duda (1956). "Tests on a cell assembly theory of the action of the brain, using a large digital computer". IRE Transactions on Information Theory 2 (3): 80–93. doi:10.1109/TIT.1956.1056810.

Rosenblatt, F. (1958). "The Perceptron: A Probabilistic Model For Information Storage And Organization In The Brain". Psychological Review 65 (6): 386–408. doi:10.1037/h0042519. PMID 13602029.

Werbos, P.J. (1975). Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences.

Minsky, M.; S. Papert (1969). An Introduction to Computational Geometry. MIT Press. ISBN 0262630222.

Rumelhart, D.E; James McClelland (1986). Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Cambridge: MIT Press.

Russell, Ingrid. "Neural Networks Module". Retrieved 2012.

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.

Strukov, D. B.; Snider, G. S.; Stewart, D. R.; Williams, R. S. Nature 2008, 453, 80–83.

2012 Kurzweil AI Interview with Jürgen Schmidhuber on the eight competitions won by his Deep Learning team 2009–2012

http://www.kurzweilai.net/howbioinspireddeeplearningkeepswinningcompetitions 2012 Kurzweil AI Interview with Jürgen Schmidhuber on the eight competitions won by his Deep Learning team 2009–2012

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.

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.

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

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.

D. C. Ciresan, U. Meier, J. Masci, J. Schmidhuber. MultiColumn Deep Neural Network for Traffic Sign Classification. Neural Networks, 2012.

D. C. Ciresan, U. Meier, J. Masci, J. Schmidhuber. MultiColumn Deep Neural Network for Traffic Sign Classification. Neural Networks, 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.

D. C. Ciresan, U. Meier, J. Schmidhuber. Multicolumn Deep Neural Networks for Image Classification. IEEE Conf. on Computer Vision and Pattern Recognition CVPR 2012.

Fukushima, K. (1980). "Neocognitron: A selforganizing neural network model for a mechanism of pattern recognition unaffected by shift in position". Biological Cybernetics 36 (4): 93–202. doi:10.1007/BF00344251. PMID 7370364.

M Riesenhuber, T Poggio. Hierarchical models of object recognition in cortex. Nature neuroscience, 1999.

Deep belief networks at Scholarpedia.

Hinton, G. E.; Osindero, S.; Teh, Y. W. (2006). "A Fast Learning Algorithm for Deep Belief Nets" . Neural Computation 18 (7): 1527–1554. doi:10.1162/neco.2006.18.7.1527. PMID 16764513

http://www.scholarpedia.org/article/Deep_belief_networks

Hinton, G. E.; Osindero, S.; Teh, Y. (2006). "A fast learning algorithm for deep belief nets" . Neural Computation 18 (7): 1527–1554. doi:10.1162/neco.2006.18.7.1527. PMID 16764513.

John Markoff (November 23, 2012). "Scientists See Promise in DeepLearning Programs". New York Times.

"The Machine Learning Dictionary".

Dominic, S., Das, R., Whitley, D., Anderson, C. (July 1991). "Genetic reinforcement learning for neural networks". IJCNN91Seattle International Joint Conference on Neural Networks. IJCNN91Seattle International Joint Conference on Neural Networks. Seattle, Washington, USA: IEEE. doi:10.1109/IJCNN.1991.155315. ISBN 0780301641. Retrieved 29 July 2012.

Hoskins, J.C.; Himmelblau, D.M. (1992). "Process control via artificial neural networks and reinforcement learning". Computers & Chemical Engineering 16 (4): 241–251. doi:10.1016/00981354(92)80045B.

Bertsekas, D.P., Tsitsiklis, J.N. (1996). Neurodynamic programming. Athena Scientific. p. 512. ISBN 1886529108.

Secomandi, Nicola (2000). "Comparing neurodynamic programming algorithms for the vehicle routing problem with stochastic demands". Computers & Operations Research 27 (11–12): 1201–1225. doi:10.1016/S03050548(99)00146X.

de Rigo, D., Rizzoli, A. E., SonciniSessa, R., Weber, E., Zenesi, P. (2001). "Neurodynamic programming for the efficient management of reservoir networks" (PDF). Proceedings of MODSIM 2001, International Congress on Modelling and Simulation. MODSIM 2001, International Congress on Modelling and Simulation. Canberra, Australia: Modelling and Simulation Society of Australia and New Zealand. doi:10.5281/zenodo.7481. ISBN 0867405252. Retrieved 29 July 2012.

Damas, M., Salmeron, M., Diaz, A., Ortega, J., Prieto, A., Olivares, G. (2000). "Genetic algorithms and neurodynamic programming: application to water supply networks". Proceedings of 2000 Congress on Evolutionary Computation. 2000 Congress on Evolutionary Computation. La Jolla, California, USA: IEEE. doi:10.1109/CEC.2000.870269. ISBN 0780363752. Retrieved 29 July 2012.

Deng, Geng; Ferris, M.C. (2008). "Neurodynamic programming for fractionated radiotherapy planning". Springer Optimization and Its Applications 12: 47–70. doi:10.1007/9780387732992_3.

de Rigo, D., Castelletti, A., Rizzoli, A.E., SonciniSessa, R., Weber, E. (January 2005). "A selective improvement technique for fastening NeuroDynamic Programming in Water Resources Network Management". In Pavel Zítek. Proceedings of the 16th IFAC World Congress – IFACPapersOnLine. 16th IFAC World Congress 16. Prague, Czech Republic: IFAC. doi:10.3182/200507036CZ1902.02172. ISBN 9783902661753. Retrieved 30 December 2011.

Ferreira, C. (2006). "Designing Neural Networks Using Gene Expression Programming" . In A. Abraham, B. de Baets, M. Köppen, and B. Nickolay, eds., Applied Soft Computing Technologies: The Challenge of Complexity, pages 517–536, SpringerVerlag.

Da, Y., Xiurun, G. (July 2005). T. Villmann, ed. An improved PSObased ANN with simulated annealing technique. New Aspects in Neurocomputing: 11th European Symposium on Artificial Neural Networks. Elsevier. doi:10.1016/j.neucom.2004.07.002.

Wu, J., Chen, E. (May 2009). Wang, H., Shen, Y., Huang, T., Zeng, Z., ed. A Novel Nonparametric Regression Ensemble for Rainfall Forecasting Using Particle Swarm Optimization Technique Coupled with Artificial Neural Network. 6th International Symposium on Neural Networks, ISNN 2009. Springer. doi:10.1007/9783642015137_6. ISBN 9783642012150.

Roman M. Balabin, Ekaterina I. Lomakina (2009). "Neural network approach to quantumchemistry data: Accurate prediction of density functional theory energies". J. Chem. Phys. 131 (7): 074104. doi:10.1063/1.3206326. PMID 19708729.

Ganesan, N. "Application of Neural Networks in Diagnosing Cancer Disease Using Demographic Data" . International Journal of Computer Applications.

Bottaci, Leonardo. "Artificial Neural Networks Applied to Outcome Prediction for Colorectal Cancer Patients in Separate Institutions" . The Lancet.

Siegelmann, H.T.; Sontag, E.D. (1991). "Turing computability with neural nets". Appl. Math. Lett. 4 (6): 77–80. doi:10.1016/08939659(91)90080F.

Balcázar, José (Jul 1997). "Computational Power of Neural Networks: A Kolmogorov Complexity Characterization". Information Theory, IEEE Transactions on 43 (4): 1175–1183. doi:10.1109/18.605580. Retrieved 3 November 2014.

NASA  Dryden Flight Research Center  News Room: News Releases: NASA NEURAL NETWORK PROJECT PASSES MILESTONE. Nasa.gov. Retrieved on 20131120.

Roger Bridgman's defence of neural networks

http://www.iro.umontreal.ca/~lisa/publications2/index.php/publications/show/4

Sun and Bookman (1990)

Tahmasebi; Hezarkhani (2012). "A hybrid neural networksfuzzy logicgenetic algorithm for grade estimation". Computers & Geosciences 42: 18–27. doi:10.1016/j.cageo.2012.02.004.
* https://en.wikipedia.org/