Highly Interconnected Processing Elements: 1. Neural Network Architectures

1.
Neural Network Architectures
An Artificial Neural Network (ANN) is a data processing system, consisting

large number of simple highly interconnected processing elements as
artificial neuron in a network structure that can be represented using a
directed graph G, an ordered 2-tuple (V, E) , consisting a set V of vertices
and a set E of edges.
- The vertices may represent neurons (input/output) and
The edges may represent synaptic links labeled by the weights attached.
Example :
e5
V1 V3
V5
e2
e4
e5
V2 V4
e3
Vertices V = { v1 , v2 , v3 , v4, v5 }
Edges E = { e1 , e2 , e3 , e4, e5 }
1. Single Layer Feed-forward Network
The Single Layer Feed-forward Network consists of a single layer of

weights , where the inputs are directly connected to the outputs, via a
series of weights. The synaptic links carrying weights connect every input
to every output , but not other way. This way it is considered a network of
feed-forward type. The sum of the products of the weights and the inputs
is calculated in each neuron node, and if the value is above some threshold
(typically 0) the neuron fires and takes the activated value (typically 1);
otherwise it takes the deactivated value (typically -1).
2.Multi Layer Feed-forward Network
The name suggests, it consists of multiple layers. The architecture of

this class of network, besides having the input and the output layers,
also have one or more intermediary layers called hidden layers. The
computational units of the hidden layer are known as hidden neurons.
- The hidden layer does intermediate computation before directing the
Input Output
hidden layer hidden layer
weights wjk y1
weights vij w11
x1 v11
w12
v21 y1 y2
x2 w11
v1m
v2m y3
vn1 w1m
ym
Vℓm
Hidden Layer
xℓ neurons yj
yn
Input Layer
neurons xi Output Layer
neurons zk
input to output layer.
- The input layer neurons are linked to the hidden layer neurons; the
weights on these links are referred to as input-hidden layer weights.

- The hidden layer neurons and the corresponding weights are referred to
as output-hidden layer weights.

- A multi-layer feed-forward network with ℓ input neurons, m1 neurons in
the first hidden layers, m2 neurons in the second hidden layers, and n
output neurons in the output layers is written as (ℓ - m1 - m2 – n ).
The Fig. above illustrates a multilayer feed-forward network with a
configuration (ℓ - m – n).
3.Recurrent Networks
The Recurrent Networks differ from feed-forward architecture. A Recurrent

network has at least one feed back loop.
Example :
y1
x1
y1 y2
x2
Yn
ym
Xℓ
Input Layer Hidden Layer Output Layer

neurons xi neurons yj neurons zk
There could be neurons with self-feedback links; that is the output of a

neuron is fed back into it self as input.
Learning Methods in Neural Networks :

• Supervised Learning
- A teacher is present during learning process and presents expected
output.
- Every input pattern is used to train the network.
- Learning process is based on comparison, between network's computed
output and the correct expected output, generating "error".

- The "error" generated is used to change network parameters that result
improved performance.
• Unsupervised Learning
- No teacher is present.
- The expected or desired output is not presented to the network.
- The system learns of it own by discovering and adapting to the structural
features in the input patterns.
• Reinforced learning
- A teacher is present but does not present the expected or desired output
but only indicated if the computed output is correct or incorrect.

- The information provided helps the network in its learning process.
- A reward is given for correct answer computed and a penalty for a wrong
answer.
• Note : The Supervised and Unsupervised learning methods are most
popular forms of learning compared to Reinforced learning.
• Hebbian Learning
Hebb proposed a rule based on correlative weight adjustment.
In this rule, the input-output pattern pairs (Xi , Yi) are associated by
the weight matrix W, known as correlation matrix computed as
n
W= Xi YiT
i=1
where YiT is the transpose of the associated output vector Yi

There are many variations of this rule proposed by the other
researchers (Kosko, Anderson, Lippman)
Hebb Network was stated by Donald Hebb in 1949. According to Hebb's rule, the weights are
found to increase proportionately to the product of input and output. It means that in a Hebb
network if two neurons are interconnected then the weights associated with these neurons can be
increased by changes in the synaptic gap.
This network is suitable for bipolar data. The Hebbian learning rule is generally applied to logic
gates.
• Gradient descent Learning
This is based on the minimization of errors E defined in terms of weights
and the activation function of the network.
- Here, the activation function of the network is required to be

differentiable, because the updates of weight is dependent on
the gradient of the error E.
- If  Wij is the weight update of the link connecting the i th and the j th
neuron of the two neighboring layers, then  Wij is defined as
 Wij =  ( E /  Wij )
where  is the learning rate parameters and ( E /  Wij ) is error

gradient with reference to the weight Wij .
Note : The Hoffs Delta rule and Back-propagation learning rule are
the examples of Gradient descent learning.
.

Highly Interconnected Processing Elements: 1. Neural Network Architectures

Uploaded by

Copyright:

Available Formats

Highly Interconnected Processing Elements: 1. Neural Network Architectures

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Highly Interconnected Processing Elements: 1. Neural Network Architectures

Uploaded by

Copyright:

Available Formats

1.

Neural Network Architectures

An Artificial Neural Network (ANN) is a data processing system, consisting

1. Single Layer Feed-forward Network

The Single Layer Feed-forward Network consists of a single layer of

The name suggests, it consists of multiple layers. The architecture of

weights on these links are referred to as input-hidden layer weights.

as output-hidden layer weights.

The Recurrent Networks differ from feed-forward architecture. A Recurrent

Input Layer Hidden Layer Output Layer

There could be neurons with self-feedback links; that is the output of a

Learning Methods in Neural Networks :

- Learning process is based on comparison, between network's computed

output and the correct expected output, generating "error".

- The expected or desired output is not presented to the network.

- The system learns of it own by discovering and adapting to the structural

features in the input patterns.

but only indicated if the computed output is correct or incorrect.

where YiT is the transpose of the associated output vector Yi

- Here, the activation function of the network is required to be

where  is the learning rate parameters and ( E /  Wij ) is error

You might also like