You are on page 1of 1

Unit 1

23 February 2024 18:50

What is ANN? 3 Basic Components or Entities of ANN:- Sigmoid Activation Function Solved Example
• It may be defined as an information processing model that is inspired by the way biological 1. The model's synaptic interconnections
nervous system, such as brain, process information. 2. The training or learning rules adopted for updating and adjusting the
• Model tries to replicate only the basic functions of the brain. connection weights
• Composed of large number of highly interconnected processing units(neurons) working in 3. Their activation functions
unison to solve specific problems.
• It learns by experiences. 1. Connections:-
• Configured for specific applications such as spam classification, face recognition, pattern An ANN consists of a set of highly interconnected processing neurons such
recognition through learning process. that each processing element output is found to be connected through
• Each neuron is connected with the other by a connection link. weights to other or to itself; delay lead and lag-free connections are allowed
• Each connection link is associated with weights which contains information about the input Hence arrangements of these processing elements and geometry of their
signal. interconnections are essential.
• Information is used by neuron network to solve particular problem. There exist five basic types of neuron connection architectures:
• Characterized by the ability to learn, recall and generalize training patterns or data similar a. Single layer feed forward network
to that of a human brain.
• ANN processing elements are called as neurons or artificial neurons.
• Each neuron has an internal state of its own known as activation level of neuron.
• The activation signal is transmitted to other neurons.

• a.

2. Learning
• The main property of ANN is its capability to learn. Implement AND function using McCulloch–Pitts neuron
• Learning or training is a process by means of which a neural network adapts itself to a stimulus b. Multilayer feed forward network
by making proper parameter adjustments, resulting in the production of desired response.
• Two kinds of learning in ANNs:
• a. Parameter Learning: Updates the connecting weights in neural network
• b. Structure Learning: Focuses on the change in network structure
3. Activation Function
a.

c. Single node with its own feedback

a. Identity Function: It is a linear function and defined as f(x) = x for all x, the output here
remains the same as input. The input layer uses the identity activation function. a.

d. Single layer recurrent network

a.

e. Multilayer recurrent network

a.

Soft Computing Page 1

You might also like