Scribd
Upload
109 views4 pages

Biological Neurons and ANN Overview

The document discusses artificial neural networks (ANNs) and compares them to biological neurons. ANNs are parallel computational systems consisting of many simple processing elements (artificial neurons) connected to perform tasks. Each artificial neuron is analogous to a biological neuron, with inputs, weights/interconnections, and outputs. Neural networks are networks of artificial neurons that can be used to solve artificial intelligence problems like image identification. They have properties like input-output mapping, non-linearity, adaptivity, fault tolerance, and neurobiological analogy. Common applications of ANNs include pattern classification, medical applications, forecasting, adaptive filtering, and adaptive control.

Uploaded by

shrilaxmi bhat
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
109 views4 pages

Biological Neurons and ANN Overview

The document discusses artificial neural networks (ANNs) and compares them to biological neurons. ANNs are parallel computational systems consisting of many simple processing elements (artificial neurons) connected to perform tasks. Each artificial neuron is analogous to a biological neuron, with inputs, weights/interconnections, and outputs. Neural networks are networks of artificial neurons that can be used to solve artificial intelligence problems like image identification. They have properties like input-output mapping, non-linearity, adaptivity, fault tolerance, and neurobiological analogy. Common applications of ANNs include pattern classification, medical applications, forecasting, adaptive filtering, and adaptive control.

Uploaded by

shrilaxmi bhat
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

What is ANN?

Biological Neuron:
A nerve cell called neuron is a special biological cell that processes information.
An estimation says, there are huge number of neurons, approximately 1011 with numerous
interconnections, approximately 1015.

Working of a Biological Neuron:

• a typical neuron consists of the following four parts

• Dendrites − They are tree-like branches, responsible for receiving the information from other
neurons it is connected to. In other sense, we can say that they are like the ears of neuron.

• Soma − It is the cell body of the neuron and is responsible for processing of information, they have
received from dendrites.

• Axon − It is just like a cable through which neurons send the information.

• Synapses − It is the connection between the axon and other neuron dendrites.

Similarities based on the terminology between Biological and Artificial Neurons.

Biological Neuron Artificial Neuron

Soma Node
Dendrites Input
Synapse Weights or Interconnections
Axon Output

www.pes.edu
Model of the Artificial Neuron:

Neural Network:

Neural Network is a network of artificial neurons, as found in human brains, for solving artificial
intelligence problems such as image identification. They may be a physical device or mathematical
constructs

Artificial Neural Network

In other words, Artificial Neural Network is a parallel computational system consisting of many simple
processing elements connected to perform a particular

In other words, Artificial Neural Network is a parallel computational system consisting of many simple
processing elements connected to perform a particular task.

www.pes.edu
Why ANN?
•The power of neural network lies in its ability to learn and generalize, and its massive parallel
structure.
Some of the useful properties of neural networks:
•Input-output mapping: It finds the optimal mapping between an input signal and the output.
•Non-linearity: NN could be linear or nonlinear,(e.g. speech signal) is inherently nonlinear.
•Adaptivity: A neural network could be designed to change its weights in real time, which
enables the system to operate in a nonstationary environment.
• Fault tolerance: A neural network is inherently fault tolerant or capable of robust
computation, in the sense that its performance degrades gracefully under adverse operating
conditions.
• VLSI implementability: The massively parallel nature of a neural network, makes it
potentially fast for a certain computation task, which also makes it well suited for
implementation using VLSI technology.
• Uniformity of analysis and design: Neural networks enjoy universality as information
processors
• Neurobiological analogy: The design of a neural network is motivated by analogy to the brain
(the fastest and powerful fault tolerant parallel processor).

Applications:

• Pattern Classifications
• Medical Applications
• Forecasting
• Adaptive Filtering
• Adaptive Control

www.pes.edu
Speech Recognition

Multilayer networks

Multilayer networks with recurrent connections

Kohonen self-organizing feature map

Character Recognition:

Multilayer neural networks such as Backpropagation neural networks.

1. Reference Pages 1 – 10 from, “S. Haykin, (2003), “Neural Networks: A


Comprehensive Foundation”, 2nd edition, Prentice Hall of India.

www.pes.edu

You might also like