# 1. Characteristics of ANNs, 2. Biological neuron.

Table of Contents

#### Que: State the characteristics of an ANNs (artificial neural network).

##### Answer: Characteristics of ANNs:
1. The NNs can map input patterns to their associated output patterns.
2. The NNs learn by examples. Thus, NN architectures can be trained with known examples of a problem before they are tested for their inference capability on unknown instances of the problem. They can identify ne objects that are previously untrained.
3. The NNs possess the capability to generalize. Thus, they can predict new outcomes from past trends.
4. The NNs are robust systems and are fault tolerant. They can therefore, recall full patterns from incomplete, partial or noisy systems.
5. The NNs can process information in parallel, at high speed, and distributed manner.

#### Que: What are the fundamental building blocks of the Biological neural network ? Discuss.

Answer:

In human brain, the elementary nerve cell called a neuron is the fundamental building block of biological neural network. A biological neural network has three major regions:

1. Soma or cell body: It contains the cell’s nucleus and other vital components called organelles which perform specialized tasks.
2. A set of dendrites: It forms a tree like structure that spread out from the cell. The neuron receives its input electrical signal along these set of dendrites.
3. Axon: It is tabular extension from the cell (Soma) that carries an  electrical signal away from Soma to another neuron for processing.

#### Que: What are the activation function? Explain its in neuron model.

Answer:

An activation function is the basic element in neural model. It is used for limiting the amplitude of the output of a neuron.

It is also called squashing function, because it squashes (limits) the permissible amplitude range of the output signal to some finite value.

Typically, the normalized amplitude range of the output of a neuron is written as the closed unit interval [0,1] or [-1,1].

In mathematical term the output yk

\begin{array}{l}y_k=y\left(u_k+b_k\right)\\\\\text{where}\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ u_k=\ \Sigma\\\\\\\end{array}\sum_{j=1}^m\ w_j\ x_j

called linear combiner output where y is called activation function, bk is bias used for the effect of applying an affine transformation to the output uk of the linear combiner in the model.

\begin{array}{l}V_k=u_k+b_k\\\end{array}

Vk is called induced local field or activation potential of neuron k.

Hence, from eq. 1

\begin{array}{l}V_k=y\left(V_k\right)\\\end{array}

Use of activation function is neuron model:

1. It helps neuron model in learning.
2. It helps in functional mapping between the inputs and response variable.
3. Its main purpose is to convert an input signal of a node in a neuron model to an output signal.

#### Que: Write the expression for bipolar continuous bipolar binary activation function.

Answer:

The neuron as a processing node performs the operation of summation of its weighted inputs, or the scalar product computation to obtain net. Subsequently, it performs the non-linear operation f(net) through its activation function.

Typical activation functions used are:

\begin{array}{l}f\left(net\right)≜\ \frac{2}{1+\exp\left(-\lambda\right)}-1\\f\left(net\right)\ ≜\ sgn\left(net\right)=_{ }\begin{cases}+1,net >0\\
-1,net <0\end{cases}\end{array}

Activation function (a) and (b) are known as bipolar continuous and bipolar binary function respectively.

The word bipolar is used to point out that both positive and negative response of neurons are produced for the above definition of the activation function by shifting and scaling the bipolar activation function defined in a and b.

### Download Question Paper 2020-21 Application of Soft Computing

Click here

1. Characteristics of ANNs, 2. Biological neuron.
Scroll to top