Scribd
Upload
15 views18 pages

Lect 2 Neural Network

The document provides an introduction to artificial neural networks including their biological motivation and inspiration from the human brain. It describes the basic structure and functioning of biological neurons and neural networks. It also discusses the history and development of artificial neural networks and their advantages over conventional computers.

Uploaded by

Souradeep Gupta
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
15 views18 pages

Lect 2 Neural Network

The document provides an introduction to artificial neural networks including their biological motivation and inspiration from the human brain. It describes the basic structure and functioning of biological neurons and neural networks. It also discusses the history and development of artificial neural networks and their advantages over conventional computers.

Uploaded by

Souradeep Gupta
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 18

Introduction to Artificial Neural

Networks
Neural Network

•Massively parallel in nature


•Perform fast computations
•Can mimic human brain
•Network with high number of interconnections
•Very complex
Biological Motivation

• Human brain is a densely interconnected


network of approximately 1011 neurons, each
connected to, on average, 104 others.

• Neuron activity is excited or inhibited through


connections to other neurons.

• The fastest neuron switching times are


known to be on the order of 10-3 sec.
Structure of Biological Neuron

The neuron is a complex biochemical and electrical signal processing


processing unit that receives and combines signals from many other
neurons through filamentary input paths, the dendrites.

Components of biological
neuron :
Dendrites – are bunched into highly complex dendrites trees
(tree links). collects input from other neurons
Axon – the output area of the neuron is a long fiber called
axon.
Soma – cell body. It sums the incoming signals
Synapse – the connecting point between a neuron axon and
another neuron’s dendrite is called a synapse
Communication of two neurons
How the brain works
• Each neuron receives inputs from other neurons
- Some neurons also connect to receptors
- Neurons use spikes to communicate
- The timing of spikes is important

• The effect of each input line on the neuron is


controlled by a synaptic weight
– The weights can be positive or negative

• The synaptic weights adapt so that the whole


network learns to perform useful computations
– Recognizing objects, understanding language, making
plans, controlling the body
Features/Specification of Brain

•Number of neurons 10 billion


•Number of interconnections 60 trillions
•Total number of synapses 100,000 billion
•Operation /sec/neuron 100
•Total number of operations 10,000 trillion/sec
•Human brain volume 300cm3
•Human brain weight 1.5 kg
•Power dissipation per neuron 25 * 10-10 W
Biological Neural Nets
• Pigeons as art experts (Watanabe et al.
1995)
– Experiment:
• Pigeon in Skinner box
• Present paintings of two different artists
• Reward for pecking when presented a particular
artist
• Pigeons were able to discriminate between two artists
with 95% accuracy (when presented with pictures they
had been trained on)

• Discrimination still 85% successful for previously unseen


paintings of the artists

• Pigeons do not simply memorise the pictures


• They can extract and recognise patterns (the ‘style’)
• They generalise from the already seen to make
predictions

• This is what neural networks (biological and artificial) are


good at prediction (unlike conventional computer)
Concept of Neural Network
A NN is a machine learning approach inspired by
the way in which the brain performs a particular
learning task:
– Knowledge about the learning task is given in the form
of examples.

– Inter neuron connection strengths (weights) are used


to store the acquired information (the training
examples).
– During the learning process the weights are modified
in order to model the particular learning task correctly
on the training examples.
History of Neural Network

The first artificial neuron was produced in 1943 by the


neurophysiologist Warren McCulloch and the logician
Walter Pits. But the technology available at that time did
not allow them to do too much.

1949 first learning rule

1969 Minsky & Papert perceptron

Limitation – death of ANN

1980’s Re-emergence of ANN – Multilayer network


Neural Network - Paradigm

Inspired by parallel architecture of Animal Brain

Neural network are a form of multiprocessor computer


system

• simple processing elements


• high degree of interconnection
• simple scalar messages
• adaptive interaction between elements
Conventional computer Vs Neural Network
Conventional computer Neural Network

processing is sequential--one task its ability to do many things at once


computers function logically with a artificial neural networks can function
set of rules and calculations via images, pictures, and concepts.
traditional computers have to learn artificial neural networks learn by
by rules example
programmable by higher level artificial neural networks can "program
languages like C or Java and then themselves."
translating that down to the
machine's assembly language neural networks are continuously
adaptable by truly altering their own
conventional computers must learn programming
only by doing different sequences
or steps in an algorithm
Why Neural Network

Neural networks, with their remarkable ability to derive


meaning from complicated or imprecise data, can be used
to extract patterns and detect trends that are too complex
to be noticed by either humans or other computer
techniques.
A trained neural network can be thought of as an "expert"
in the category of information it has been given to
analyze. This expert can then be used to provide
projections given new situations of interest and answer
"what if" questions.
Books
1. Principles of Soft computing, Sivanandam, Wiley-India
2. Principles of Soft computing , S.N Sivanandam, S.N Deepa
3. Introduction to Artificial Neural Networks, S.N Sivanandam, M
Paulraj
4. Neural Networks, Fuzzy Logic and Genetic Algorithms,
Rajasekaran
5.Artificial Neural Networks: An Introduction, Priddy, Keller
6.Understanding Neural Networks and Fuzzy Logic, Kartalopoulos

You might also like