In the name of ALLAH the most
beneficent the most merciful.
Artificial Neural
Network(ANN)
Presented By:
Malik Masood Ahmad
MSCS-F14-M039
The Biological Brain
 Neurons: Fundamental information-
processing units of the brain.
 Neurons contain axons (the transmission
lines) and dendrites, (the receptive zones).
 Electrical signal flows from dendrites to
axon.
Basic Idea of ANN
The neuron receives signals from
other neurons, collects the input
signals, and transforms the
collected input signal
The single neuron then transmits
the transformed signal to other
neurons
Three major learning
paradigms
 Supervised learning
 Unsupervised learning
 Reinforcement learning
Supervised learning
Compute
Output
Adjust Weights
Stop
Is
Desired
Output
Achieve
d
Yes
No
Feed forward network
Compute Output
Adjust weights/Back propagation
Gradient descent
Error
Gradient
Adjust weights/Back propagation
Results/Examples
Computational power
 The universal approximation theorem states
that a feed-forward network with a single
hidden layer containing a finite number
of neurons can approximate continuous
functions, under mild assumptions on the
activation function.
 A specific recurrent architecture with rational
valued weights (as opposed to full
precision real number-valued weights) has the
full power of a Universal Turing Machine.[1]
[1]. Work by Hava Siegelmann and Eduardo D. Sontag
Matlab code
Time Complexity
O(V.E)
Broader Applications:
 Function approximation
 Fitness approximation and modelling.
 Classification.
 Novelty detection and sequential decision
making.
 Data processing, including filtering, clustering
and compression.
 Robotics, including directing manipulators.
 Control
Practical implementations:
 Vehicle control, Process control, Natural
resources management.
 Game-playing and Decision making.
 Radar systems, Face identification, Object
recognition.
 Medical diagnosis, financial applications.
End of the Story
 “ Artificial neural networks are still far
away from biological neural networks ,
but what we know today about artificial
neural networks is sufficient to solve many
problems that were previously unsolvable
or inefficiently solvable at best. ”
Artificial neural network

Artificial neural network