Scribd
Upload
70 views4 pages

Neural Network Neural Network

1. A neural network is a massively parallel system that is inspired by the human brain. It learns from its environment through a learning process and stores knowledge in the strengths of connections between neurons. 2. The human brain contains around 10 billion neurons and 60 trillion synapses. It is much more energy efficient than a computer. A neuron has synapses, an adder, and an activation function that limits its output. 3. Neural networks learn by adjusting the strengths of connections between neurons. Hebbian learning strengthens connections between simultaneously active neurons. Competitive learning selects a single winning neuron for each input pattern.

Uploaded by

Faysal Hossain
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
70 views4 pages

Neural Network Neural Network

1. A neural network is a massively parallel system that is inspired by the human brain. It learns from its environment through a learning process and stores knowledge in the strengths of connections between neurons. 2. The human brain contains around 10 billion neurons and 60 trillion synapses. It is much more energy efficient than a computer. A neuron has synapses, an adder, and an activation function that limits its output. 3. Neural networks learn by adjusting the strengths of connections between neurons. Hebbian learning strengthens connections between simultaneously active neurons. Competitive learning selects a single winning neuron for each input pattern.

Uploaded by

Faysal Hossain
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 4

Neural Network Neural Network

What is Neural Network?

A neural network is a massively parallel distributed processor made up of simple processing units, which has a
natural propensity for storing experimental knowledge and making it available for use.

It resembles the brain in two respects:

1. Knowledge is acquired by the network from its environment through a learning process,
2. Interneuron connection strengths, known as synaptic weights, are used to store the acquired knowledge.
Benefits of Neural Network
1. Nonlinearity 2. Input-Output Mapping 3. Adaptivity
4. Evidential Response 5. Fault Tolerance 6. VLSI Implementation
Human Brain
The human nervous system may be viewed as a three-stage system. Central to the system is brain, represented by
the neural (nerve) net, which continually receives information, perceives it, and makes appropriate decisions.

Figure: Block diagram representation of nervous system

Human Brain

Real Neuron

Human Brain
Comparative View Comparative View
Human Brain Computer
10 billion neurons
60 trillion synapses
Events happen:
10-3 s 10-9 s
Energetic Efficiency:
10-16 joules/oper. 10-6 joules/oper

Models of a Neuron
A neuron is an information processing unit that is fundamental to the operation of a neural network.

1. A set of synapses or connecting

links, each of which is

characterized by a weight or

strength f its own,

2. An adder for summing the

input signals,

3. An activation function for

limiting the amplitude of the

output of a neuron

Models of a Neuron

•In mathematical terms, we may describe a neuron k by-

Types of Activation Function

1. Threshold Function 2. Piecewise-Linear Function 3. Sigmoid Function


Network Architecture
Single Layer Feedforward Network Multilayer Feedforward Network

Recurrent Network

Learning
What is Learning?

Learning is a process by which the free parameters of a neural network are adapted through a process of
stimulation by the environment in which the network is embedded. The type of learning is determined by
the manner in which the parameter changes take place.

Error-Correction Learning

We can define error-correction learning through the following equation:

ek(n) = dk(n) – yk(n) Where, k is a neuron,


yk is the output signal of neuron k,
dk is the desired response of k,
ek is the error signal.
Hebbian Learning
• Introduced by neurophysiologist Hebb (1949)

1. If two neurons on either side of a synapse are activated simultaneously then the strength of that synapse
is selectively increased.

2. If two neurons on either side of a synapse are activated asynchronously then the synapse is selectively
weakened.

Competitive Learning
In Hebbian learning, several output neurons may be active simultaneously, but in competitive learning only a single
output neuron is active at any one time.

It is the feature that makes competitive learning highly suited to discover statistically salient features that may be
used to classify a set of input pattern.

Learning Rule:

1. A set of neurons that are all the same with randomly distributed synaptic weights,

2. A limit imposed on the strength of each neuron

3. A mechanism that permits the neurons to compete for the right to respond to a given subset of inputs

Supervised Learning Unsupervised Learning


Vector describing state of the environment

You might also like