Professional Documents
Culture Documents
UNIT – I
ARTIFICIAL NEURAL NERTWORK
TOPICS
BASIC CONCEPTS
NETWORK ARCHITECTURE
LEARNING PROCESS
BACKPROPAGATION NETWORKS
SELF-ORGANIZING MAPS (NETWORKS)
HOPFIELD NETWORK
Prepared By Mr. G.Pandiaraj M.E.,
NETWORK ARCHITECTURE
Single-Layer Feed-forward Networks:
Acyclic or Strictly feed forward network
An input layer of source nodes that projects onto an output layer of neurons
15
Prepared By Mr. G.Pandiaraj M.E.,
Recurrent Networks:
A recurrent neural network distinguishes itself from a feed-forward neural network in that it has at
least one feedback loop. For example, a recurrent network may consist of a single layer of neurons with
each neuron feeding its output signal back to the inputs of all the other neurons.
LEARNING PROCESS:
16
Prepared By Mr. G.Pandiaraj M.E.,
Learning:
In the simple model of machine learning depicted in Fig. the environment supplies some
information to a learning element. The learning element then uses this information to make improvements
in a knowledge base, and finally the have to be perfect. Performance of the network degrades gracefully
within a certain range. The network is made even more robust by virtue of the "coarse coding", where each
feature is spread over several neurons.
Definition:
Learning is a process by which the free parameters of a neural network are adapted through a
process of stimulation by the environment in which the network is embedded. The type of learning is
determined by the manner in which the parameter changes take place.
A prescribed set of well-defined rules for the solution of a learning problem is called a learning
algorithm.
SUPERVISED LEARNING
17
Prepared By Mr. G.Pandiaraj M.E.,
The network parameters are adjusted under the combined influence of the training vector and the
error signal. The error signal is defined as the difference between the desired response and the actual
response of the network. This adjustment is carried out iteratively in a step-by-step fashion with the aim of
eventually making the neural network emulate the teacher; the emulation is presumed to be optimum in
some statistical sense.
For the system to improve performance over time and therefore learn from the teacher, the
operating point has to move down successively toward a minimum point of the error surface; the minimum
point may be a local minimum or a global minimum. A supervised learning system is able to do this with
the useful information it has about the gradient of the error surface corresponding to the current behavior
of the system. The gradient of an error surface at any point is a vector that points in the direction of
steepest descent.
18
Prepared By Mr. G.Pandiaraj M.E.,
(i.e., state vectors) also received from the environment, which eventually result in the generation of the
heuristic reinforcement signal. The goal of learning is to minimize a cost-to-go function, defined as the
expectation of the cumulative cost of actions taken over a sequence of steps instead of simply the
immediate cost. It may turn out that certain actions taken earlier in that sequence of time steps are in fact
the best determinants of overall system behavior. The function of the learning machine, which constitutes
the second component of the system, is to discover these actions and to feed them back to the environment.
Delayed-reinforcement learning is difficult to perform for two basic reasons:
There is no teacher to provide a desired response at each step of the learning process.
The delay incurred in the generation of the primary reinforcement signal implies that the learning
machine must solve a temporal credit assignment problem. By this we mean that the learning
machine must be able to assign credit and blame individually to each action in the sequence of
time steps that led to the final outcome, while the primary reinforcement may only evaluate the
outcome.
Reinforcement Learning
UNSUPERVISED LEARNING
In unsupervised or self-organized learning there is no external teacher or critic to oversee the
learning process. Rather, provision is made for a task- independent measure of the quality of representation
that the network is required to learn, and the free parameters of the network are optimized with respect to
that measure. Once the network has become tuned to the statistical regularities of the input data, it
develops the ability to form internal representations for encoding features of the input and thereby to create
new classes automatically.
19
Prepared By Mr. G.Pandiaraj M.E.,
Unsupervised Learning
THE PERCEPTRON:
The perceptron is the simplest form of a neural network used for the classification of patterns said
to be linearly separable (i.e., patterns that lie on opposite sides of a hyper plane). Basically, it consists of a
single neuron with adjustable synaptic weights and bias. The proof of convergence of the algorithm is
known as the perceptron convergence theorem.
The summing node of the neuronal model computes a linear combination of the inputs applied to
its synapses, and also incorporates an externally applied bias. The resulting sum, that is, the induced local
field, is applied to a hard limiter. Accordingly, the neuron produces an output equal to +1 if the hard
limiter input is positive and -1 if it is negative.
The externally applied bias is denoted by b. From the model we find that the hard limiter input or induced
local field of the neuron is
20
Prepared By Mr. G.Pandiaraj M.E.,
The goal of the perceptron is to correctly classify the set of externally applied stimuli x 1, x2, . . ., xm into
one of two classes, C1 or C2 decision rule for the classification is to assign the point represented by the
inputs x1, x2, ...,xm to class C1 if the perceptron output y is +1 and to class C 2 if it is -1. To develop insight
into the behavior of a pattern classifier, it is customary to plot a map of the decision regions in the m-
dimensional signal space spanned by the m input variables x 1, x2, ….. xm. In the simplest form of the
perceptron there are two decision regions separated by a hyper plane defined by
21
Prepared By Mr. G.Pandiaraj M.E.,
22