Scribd
Upload
152 views14 pages

UNIT - 2 (Part1) : Fundamental Concept of Artificial Networks

The document discusses the fundamental concepts of artificial neural networks including their basic entities: synaptic connections, training/learning rules, and activation functions. It describes various models of synaptic connections including single and multilayer feedforward and recurrent networks. It also outlines different learning rules such as supervised, unsupervised, and reinforcement learning and lists common activation functions used in neural networks.

Uploaded by

Netaji Gandi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
152 views14 pages

UNIT - 2 (Part1) : Fundamental Concept of Artificial Networks

The document discusses the fundamental concepts of artificial neural networks including their basic entities: synaptic connections, training/learning rules, and activation functions. It describes various models of synaptic connections including single and multilayer feedforward and recurrent networks. It also outlines different learning rules such as supervised, unsupervised, and reinforcement learning and lists common activation functions used in neural networks.

Uploaded by

Netaji Gandi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 14

UNIT -2(Part1)

FUNDAMENTAL CONCEPT OF ARTIFICIAL NETWORKS


Models of ANN :-
Model of ANN are specified by the three basic entities namely:-
(1) Model’s Synaptic Connection
(2) Training or Learning Rules adopted for updating and adjusting the
connection weights
(3) Activation functions
• (1)Model’s Synaptic Connection

(A) Single Layer Feed Forward network


(B) Multilayers Feed Forward Network
(C) Single node with its own feedback
(D) Single Layer recurrent network
(E) Multilayer recurrent network
• (2) Training or Learning Rules
 Supervised Learning - Providing the
network with a series of sample inputs and
comparing the output with the expected
responses.

 Unsupervised Learning - Most similar input


vector is assigned to the same output unit.

 Reinforcement Learning - Right answer is


not provided but indication of whether ‘right’
or ‘wrong’ is provided.
• (3) Activation functions:

(A) Identity

(B) Binary step

(C) Bipolar step

(D) Binary sigmoidal

(E) Bipolar sigmoidal

(F) Ramp
Questions
Important terminologies of ANN
• 1)Threshold
• 2)Learning rate

• 3) Momentum factor
Basic notations
THANK YOU

You might also like