2. Introduction
Understanding the Brain
Neural Networks as a
Paradigm for Parallel Processing
• The Perceptron Network
• Training a Perceptron
• Multilayer Perceptrons
• Backpropagation
Algorithm
Two-Class Discrimination
Multiclass Discrimination
Multiple Hidden Layers
• Training Procedures
Improving Convergence
Momentum
Adaptive Learning Rate
• Learning Time
Time Delay Neural Networks
Recurrent Networks
3. Massive parallelism
Brain computer as an
information or signal processing
system, is composed of a large
number of a simple processing
elements, called neurons. These
neurons are interconnected by
numerous direct links, which are
called connection, and cooperate
which other to perform a parallel
distributed processing (PDP) in
order to soft a desired
computation tasks.
Connectionism
Brain computer is a highly
interconnected neurons system in
such a way that the state of one
neuron affects the potential of the
large number of other neurons
which are connected according to
weights or strength. The key idea of
such principle is the functional
capacity of biological neural nets
determs mostly not so of a single
neuron but of its connections
Associative distributed memory
Storage of information in a brain
is supposed to be concentrated
in synaptic connections of brain
neural network, or more
precisely, in the pattern of these
connections and strengths
(weights) of the synaptic
connections.
A process of pattern
recognition and pattern
manipulation is based
on:
How our brain
manipulates with
patterns ?
Processing:-
3
Human brain
contains a
massively
interconnected
net of 1010
-1011
(10 billion)
neurons
4. The Biological Neuron:-
The schematic
model of a
biological neuron
Synapses
Dendrites
Soma
Axon
Dendrit
e from
other
Axon from
other
neuron
1. Soma or body cell - is a large, round central body in which almost all the logical functions of the neuron
are realized.
2. The axon (output), is a nerve fibre attached to the soma which can serve as a final output channel of the
neuron. An axon is usually highly branched.
3. The dendrites (inputs)- represent a highly branching tree of fibres. These long irregularly shaped nerve
fibres (processes) are attached to the soma.
4. Synapses are specialized contacts on a neuron which are the termination points for the axons from other
neurons.
6. ?
Brain-Like Computer
Brain-like computer –
is a mathematical model of humane-brain
principles of computations. This computer consists
of those elements which can be called the
biological neuron prototypes, which are
interconnected by direct links called connections
and which cooperate to perform parallel
distributed processing (PDP) in order to solve a
desired computational task.
Neurons and Neural Net
The new paradigm of computing
mathematics consists of the combination
of such artificial neurons into some
artificial neuron net.
Artificial Neural Network – Mathematical
Paradigms of Brain-Like Computer
Brain-like Computer
7. NN as an model of brain-
like Computer
An artificial neural network (ANN) is a massively
parallel distributed processor that has a natural
propensity for storing experimental knowledge and
making it available for use. It means that:
Knowledge is acquired by the network through a
learning (training) process;
The strength of the interconnections between neurons is
implemented by means of the synaptic weights used to
store the knowledge.
The learning process is a procedure of the adapting the
weights with a learning algorithm in order to capture the
knowledge. On more mathematically, the aim of the
learning process is to map a given relation between inputs
and output (outputs) of the network.
Brain
The human brain is still not well
understood and indeed its behavior is very
complex!
There are about 10 billion neurons in the
human cortex and 60 trillion synapses of
connections
The brain is a highly complex, nonlinear
and parallel computer (information-
processing system)
ANN as a Brain-Like Computer
7
10. Perceptrons
Multiple input nodes
Single output node
Takes a weighted sum of the inputs, call this S
Unit function calculates the output for the network
Useful to study because
We can use perceptrons to build larger networks
Perceptrons have limited representational abilities
We will look at concepts they can’t learn later
11. 1( ,..., )nf x x
0 1( , ,..., )nw w w
- unknown multi-factor decision rule
Learning process using a representative learning set
- a set of weighting vectors is the result
of the learning process
1
0 1 1
ˆ( ,..., )
( ... )
n
n n
f x x
P w w x w x
=
= + + +
- a partially defined function, which
is an approximation of the decision
rule function 11
Why neural network?
12. Artificial Neuron
f is a function to be earned
are the inputs
φ is the activation function
1x
nx
1( ,..., )nxf x.
.
.
φ(z)
0 1 1 ... n nz w w x w x= + + +
1,..., nx x
Z is the weighted sum
1 0 1 1( ,..., ) ( ... )n n nf x x F w w x w x= + + +
14. Simple Example:
Categorising Vehicles
Input to function: pixel data from vehicle images
Output: numbers: 1 for a car; 2 for a bus; 3 for a tank
INPUT INPUT INPUT INPUT
OUTPUT = 3 OUTPUT = 2 OUTPUT = 1 OUTPUT=1
16. Calculation Example:-
Categorisation of 2x2 pixel black & white images
Into “bright” and “dark”
Representation of this rule:
If it contains 2, 3 or 4 white pixels, it is “bright”
If it contains 0 or 1 white pixels, it is “dark”
Perceptron architecture:
Four input units, one for each pixel
One output unit: +1 for white, -1 for dark
17. Calculation Example:-
Example calculation: x1=-1, x2=1, x3=1, x4=-1
S = 0.25*(-1) + 0.25*(1) + 0.25*(1) + 0.25*(-1) = 0
0 > -0.1, so the output from the ANN is +1
So the image is categorised as “bright”
18. Unit Functions
Linear Functions
Simply output the weighted sum
Threshold Functions
Output low values
Until the weighted sum gets over a threshold
Then output high values
Equivalent of “firing” of neurons
Step function:
Output +1 if S > Threshold T
Output –1 otherwise
Sigma function:
Similar to step function but differentiable
Step
Function
Sigma
Function
20. Learning Process of ANN
Learn from experience
Learning algorithms
Recognize pattern of
activities
Involves 3 tasks
Compute outputs
Compare outputs with
desired targets
Adjust the weights and
repeat the process
Compute
output
Is
Desired
Output
achieved
Stop
Adjust
Weight
yes
No
22. Worked Example
Return to the “bright” and “dark” example
Use a learning rate of η = 0.1
Suppose we have set random weights:
23. Worked Example
Use this training example, E, to update weights:
Here, x1 = -1, x2 = 1, x3 = 1, x4 = -1 as before
Propagate this information through the network:
S = (-0.5 * 1) + (0.7 * -1) + (-0.2 * +1) + (0.1 * +1) + (0.9 * -1) = -2.2
Hence the network outputs o(E) = -1
But this should have been “bright”=+1
So t(E) = +1
26. New Look Perceptron
Calculate for the example, E, again:
S = (-0.3 * 1) + (0.5 * -1) + (0 * +1) + (0.3 * +1) + (0.7 * -1) = -1.2
Still gets the wrong categorisation
But the value is closer to zero (from -2.2 to -1.2)
In a few epochs time, this example will be correctly categorised
33. is an alternative neural network architecture whose primary purpose
is to work on continuous data.
The advantage of this architecture is to adapt the network online
and hence helpful in many real time applications, like time series
prediction, online spell check, continuous speech recognition,etc.
The architecture has a continuous input that is delayed and sent as
an input to the neural network.
As an example, consider training a feed forward neural network
being trained for a time series prediction. The desired output of
the network is the present state of the time series and inputs to
the neural network are the delayed time series (past values).
Hence, the output of the neural network is the predicted next value
in the time series which is computed as the function of the past
values of the time series.
Time delay neural network (TDNN):-
35. TYPES OF ANN:-
feed-forward feedback
4.1 Feed-forward networks
Feed-forward ANNs allow signals to
travel one way only; from input to
output. There is no feedback (loops)
i.e. the output of any layer does not
affect that same layer. Feed-forward
ANNs tend to be straight forward
networks that associate inputs with
outputs. They are extensively used in
pattern recognition.
4.2 Feedback networks
Feedback networks can have signals
travelling in both directions by
introducing loops in the network.
Feedback networks are very powerful
and can get extremely complicated.
Feedback networks are dynamic;
36. Some Topologies of ANN:-
Fully-connected feed-forward Partially recurrent network
Fully recurrent network
37. Recurrent Neural Networks:-
recurrent neural network:-
is a class of neural
network where connections
between units form a
directed cycle. This
creates an internal state
of the network which
allows it to exhibit
dynamic temporal behavior
Partially recurrent network
Fully recurrent network