Neural networks Neural networks An artificial neural network (ANN), also called a simulated neural network (SNN) (but the term neural network (NN) is grounded in biology and refers to very real, highly complex plexus), is an interconnected group of artificial neurons that uses a mathematical or computational model for information processing based on a connectionist approach to computation. There is no precise agreed definition among researchers as to what a neural network is, but most would agree that it involves a network of simple processing elements ( neurons) which can exhibit complex global behaviour, determined by the connections between the processing elements and element parameters. Since anything approaching a full appreciation of neuronal function remains a distant dream, and since the factors producing global output result from many non-linear, modulating, and poorly understood real-time feedback signals within a single neuron, the greatly simplified artificial networks (where 'neurons' are modeled as input/output nodes) are perceived as academic research tools rather than even a distant representation of brain function. The original inspiration for the technique was from examination of the central nervous system and the neurons (and their axons, dendrites and synapses) which constitute one of its most significant information processing elements (see Neuroscience). In a neural network model, simple nodes (called variously "neurons", "neurodes", "PEs" ("processing elements") or "units") are connected together to form a network of nodes — hence the term "neural network". The term also includes implementations purely in software that may run on general purpose computers. ...more on Wikipedia about "Artificial neural network"
An artificial neuron (also called a "node") is a basic unit in an artificial neural network. Artificial neurons are simulations of biological neurons, and they are typically functions from many dimensions to one dimension. They receive one or more inputs and sum them to produce an output. Usually the sums of each node are weighted, and the sum is passed through a non-linear function known as an activation or transfer function. The canonical form of transfer functions is the sigmoid, but they may also take the form of other non-linear functions, piecewise linear functions, or step functions. Generally, transfer functions are monotonically increasing. ...more on Wikipedia about "Artificial neuron"
Backpropagation is a supervised learning technique used for training artificial neural networks. It is most useful for feed-forward networks (networks that have no feedback, or simply, that have no connections that loop). The term is an abbreviation for "backwards propagation of errors". Backpropagation requires that the transfer function used by the artificial neurons (or "nodes") be differentiable. ...more on Wikipedia about "Backpropagation"
A Boltzmann machine is a type of stochastic recurrent neural network originally invented by Geoffrey Hinton and Terry Sejnowski. Boltzmann machines can be seen as the stochastic, generative counterpart of Hopfield nets. They were an early example of neural networks capable of forming internal representations. Because they are very slow to simulate on serial computers they are not currently very useful for most practical purposes. They were proposed in the pre- personal computer era as physical, parallel hardware machines for solving combinatorics problems. However, they are still theoretically intriguing due to the biological plausibility of their training algorithm and the future possbility of parallel hardware. Their operation is a form of simulated annealing. ...more on Wikipedia about "Boltzmann machine"
Cascade-Correlation is an architecture and supervised learning algorithm for artificial neural networks. ...more on Wikipedia about "Cascade correlation algorithm"
A cortical column is a group of neurons in the brain cortex which can be successively penetrated by a probe inserted perpendicularly to the cortical surface, and which have nearly identical receptive fields. The cortical column is composed of 6 layers. Each layer receives and sends signals to different parts of the brain. The cerebral cortex is a roughly 2 mm thick sheet of neuronal cell bodies that forms the external surface of the telencephalon. The columnar functional organization, as originallly framed by Vernon Mountcastle, states that neurons that are horizontally more than a half mm from each other do not have overlapping sensory receptive fields. An important distinction is that this rule is functional in origin, and reflects the local connectivity of the cerebral cortex. Connections "up" and "down" within the thickness of the cortex are dramatically denser than connections that spread from side to side. ...more on Wikipedia about "Cortical column"
The delta rule is a rule for updating the weights of the neurons in a single-layer perceptron. For a neuron with activation function the delta rule for 's th weight is given by ...more on Wikipedia about "Delta rule"
In machine learning, early stopping is a form of regularization used when a machine learning model (such as a neural network) is trained by on-line gradient descent. In early stopping, the training set is split into a new training set and a validation set. Gradient descent is applied to the new training set. After each sweep through the new training set, the network is evaluated on the validation set. The network with the best performance on the validation set is then used for actual testing. ...more on Wikipedia about "Early stopping"
Feed-forward is a term describing a kind of system which reacts to changes in its environment, usually to maintain some desired state of the system. ...more on Wikipedia about "Feed-forward"
A feedforward neural network is a neural network where connections between the units do not form a directed cycle. This is different from recurrent neural networks. ...more on Wikipedia about "Feedforward neural networks"
Fuzzy cellular neural networks (FCNN) are special kinds of cellular neural networks. Each cell in an FCNN containing fuzzy operating abilities, yet, the entire network is governed by cellular computing laws. The design of FCNNs is based on fuzzy local rules. FCNNs were invented by Tao Yang in 1994 in China and populized in 1996 in USA. The first VLSI chip to implement FCNN was implemented in Taiwan, R.O.C. ...more on Wikipedia about "Fuzzy cellular neural networks"
Helmholtz machines are neural networks which learn the hidden structure of a set of data by being trained to create a generative model which can produce the original set of data. The hope is that by learning economical representations of the data, the underlying structure of the generative model should reasonably approximate the hidden structure of the data set. This is an unsupervised learning algorithm. ...more on Wikipedia about "Helmholtz machine"
A Hopfield net is a form of recurrent neural network invented by John Hopfield. Hopfield nets serve as content-addressable memory systems with binary threshold units. They are guaranteed to converge to a stable state. ...more on Wikipedia about "Hopfield net"
The memory-prediction framework is a theory of brain function that was created by Jeff Hawkins and described in his book On Intelligence. This theory concerns the role of the hippocampus, neocortex, and the thalamus in matching sensory inputs to stored memory patterns and how this process leads to predictions of what will happen next. ...more on Wikipedia about "Memory-prediction framework"
(NETtalk (artificial neural network)) > Category:Computer science stubs ...more on Wikipedia about "NETtalk (artificial neural network)"
A neural network is an interconnected group of biological neurons. In modern usage the term can also refer to artificial neural networks, which are constituted of artificial neurons. Thus the term 'Neural Network' specifies two distinct concepts: ...more on Wikipedia about "Neural network"
On Intelligence: How a New Understanding of the Brain will Lead to the Creation of Truly Intelligent Machines is a book by PalmPilot-inventor Jeff Hawkins with New York Times science writer Sandra Blakeslee. The book explains Hawkins' memory-prediction framework theory of the brain and describes some of its consequences. (Times Books: 2004, ISBN 0805074562) ...more on Wikipedia about "On Intelligence"
An optical neural network is an implementation of a neural network model with optical components. One possibility is the Hopfield neural network ** ** ...more on Wikipedia about "Optical neural network"
The perceptron is a type of artificial neural network invented in 1957 at the Cornell Aeronautical Laboratory by Frank Rosenblatt. It can be seen as the simplest ...more on Wikipedia about "Perceptron"
Radial basis functions are a means for interpolation in a stream of data. They differ from statistical approaches in that approximations must be performed on streams of data rather than on complete data sets. They are used in time-series prediction, control, and function approximation. ...more on Wikipedia about "Radial basis function"
A recurrent neural network is a neural network where the connections between the units form a directed cycle. Recurrent neural networks must be approached differently than feedforward neural networks, both when analysing their behavior and training them. Recurrent neural networks can also behave chaotically. Usually, dynamical systems theory is used to model and analyse them. ...more on Wikipedia about "Recurrent neural network"
Semantic neural network (SNN) is based on John von Neumann's neural network
A sigmoid function is a mathematical function that produces a sigmoid curve — a curve having an "S" shape. Often, sigmoid function refers to the special case of the logistic function shown at right and defined by the formula: ...more on Wikipedia about "Sigmoid function"
Stochastic neural networks are a type of artificial neural networks, which is a tool of artificial intelligence. They are built by introducing random variations into the network, either by giving the network's neurons stochastic transfer functions, or by giving them stochastic weights. This makes them useful tools for optimization problems, since the random fluctuations help it escape from local minimums. ...more on Wikipedia about "Stochastic neural network"
This article is licensed under the GNU Free Documentation License.
It uses material from the Wikipedia . Direct links to the original articles are in the text.
If you use exact copy or modified of this article you should preserve above paragraph and put also : It uses material from
the Shortopedia article about "Neural networks".
| MAIN PAGE | MAIN INDEX | CONTACT US |