You are on page 1of 7

ARTIFICIAL NEURAL

NETWORK (ANN)

1
BIOLOGICAL NEURAL NETWORK

1. New models of computing to perform various engineering related


tasks are inspired by the structure and performance of our biological
neural network.
2. But these models are not expected to reach anywhere near the
performance of the biological network for several reasons.
3. Moreover, it is nearly impossible to simulate:
1. The number of neurons and their interconnections as it exists in a
Asynchronous means that you can execute
biological network
multiple things at a time
2. Their operations in the natural asynchronous mode. 2
BIOLOGICAL NEURAL NETWORK -
FEATURES
1. Robustness and fault tolerance: The decay of nerve cells does not
seem to affect the performance significantly.
2. Flexibility: The network automatically adjusts to a new environment
without using any pre-programmed instructions.
3. Ability to deal with a variety of data situations: The network can deal
with information that is fuzzy, probabilistic, noisy and inconsistent.
4. Collective computation: The network performs routinely many
operations in parallel and also a given task in a distributed manner.
3
THE HUMAN BRAIN

1. The human brain consists of a large number (more than a billion) of


neural cells that process information's.
2. Each cell works like a simple processor and only the massive
interaction between all cells and their parallel processing makes the
brain's abilities possible.
3. A neuron consists of a core, dendrites for incoming information and
an axon with dendrites for outgoing information that is passed to
connected neurons.
4
Soma or cell body:- cell nucleus is located
Dendrites:- nerve connected to cell body
Axon: carries impulses of the neuron 5
THE HUMAN BRAIN

4. An electrical impulse travels along an axon.


5. This triggers the nerve-ending of a neuron to release chemical
messengers called neurotransmitters.
6. Where two neurons meet there is a small gap called a synapse.
7. These chemicals diffuse across the synapse (the gap) and bind with
receptor molecules on the membrane of the next neuron.
8. The binding of neurotransmitter to the receptors stimulates the
second neuron to transmit an electrical impulse along its axon.
6
Threshold
Minimum or maximum value
(established for an attribute,
THE HUMAN BRAIN characteristic, or parameter)
which serves as a benchmark
for comparison or guidance
9. Information is transported between neurons in form of electrical
stimulations along the dendrites.
10. Incoming information’s that reach the neuron's dendrites is added up
and then delivered along the neuron's axon to the dendrites at its end,
where the information is passed to other neurons if the stimulation
has exceeded a certain threshold. Thus the neuron is activated.
11. If the incoming stimulation had been too low, the information will
not be transported any further. In this case, the neuron is said to be
inhibited. 7

You might also like