Documente Academic
Documente Profesional
Documente Cultură
Introduction
G.Anuradha
Learning Objectives
Reasons to study neural computation
Comparison between biological neuron
and artificial neuron
Basic models of ANN
Different types of connections of NN,
Learning and activation function
Basic fundamental neuron model-
McCulloch-Pitts neuron and Hebb network
Reasons to study neural
computation
To understand how brain actually works
Computer simulations are used for this purpose
To understand the style of parallel
computation inspired by neurons and their
adaptive connections
Different from sequential computation
To solve practical problems by using novel
learning algorithms inspired by brain
Biological Neural Network
Neuron and a sample of pulse train
How does the brain work
Each neuron receives inputs from other neurons
Use spikes to communicate
The effect of each input line on the neuron is controlled by a
synaptic weight
Positive or negative
Synaptic weight adapts so that the whole network learns to
perform useful computations
Recognizing objects, understanding languages, making
plans, controlling the body
There are 1011 neurons with 104 weights.
Modularity and brain
Different bits of the cortex do different things
Local damage to the brain has specific effects
Early brain damage makes function relocate
Cortex gives rapid parallel computation plus
flexibility
Conventional computers requires very fast
central processors for long sequential
computations
Information flow in nervous system
ANN
ANN posess a large number of processing
elements called nodes/neurons which operate in
parallel.
Neurons are connected with others by
connection link.
Each link is associated with weights which
contain information about the input signal.
Each neuron has an internal state of its own
which is a function of the inputs that neuron
receives- Activation level
Comparison between brain verses
computer
Brain ANN
Xn Y y
x2
w2 y = f ( yin )
X2
yin = x1 w1 + x2 w2
McCulloch-Pitts Neuron Model
McCulloch Pits for And and or
model
McCulloch Pitts for NOT Model
Advantages and Disadvantages
of McCulloch Pitt model
Advantages Disadvantages
Simplistic Weights and
thresholds are fixed
Substantial computing
Not very flexible
power
Features of McCulloch-Pitts model
Allows binary 0,1 states only
Operates under a discrete-time
assumption
Weights and the neurons thresholds are
fixed in the model and no interaction
among network neurons
Just a primitive model
General symbol of neuron
consisting of processing node and
synaptic connections
Neuron Modeling for ANN
Is referred to activation function. Domain is
set of activation values net.
z = xi wi z = b+ xi wi
= -b
i i
1 if z 1 if z0
y= y=
0 otherwise 0 otherwise
Sigmoid neurons
1
z= b+ xiwi
These give a real-valued
output that is a smooth and y=
bounded function of their
total input. i
1+ e
-z
Typically they use the
logistic function
They have nice 1
derivatives which make
learning easy
y 0.5
0
0 z
Activation function
Bipolar binary and unipolar binary are
called as hard limiting activation functions
used in discrete neuron model
Unipolar continuous and bipolar
continuous are called soft limiting
activation functions are called sigmoidal
characteristics.
Activation functions
Bipolar continuous
Unipolar Binary
Common models of neurons
Binary
perceptrons
Continuous perceptrons
Quiz
Which of the following tasks are neural
networks good at?
Recognizing fragments of words in a pre-
processed sound wave.
Recognizing badly written characters.
Storing lists of names and birth dates.
logical reasoning
Neural networks are good at finding statistical regularities that
allow them to recognize patterns. They are not good at flawlessly
applying symbolic rules or storing exact numbers.
Basic models of ANN
where
EXAMPLE
Multilayer feed forward network
output
output
output
They are equivalent to very deep nets with
one hidden layer per time slice.
Except that they use the same weights at
every time slice and they get input at every
time slice.
hidden
hidden
hidden
They have the ability to remember information
in their hidden state for a long time.
But its very hard to train them to use this
potential.
input
input
input
An example of what recurrent neural nets can now do
(to whet your interest!)
Neural
X Network Y
W
(Input) (Actual output)
Error
Error
(D-Y) Signal
signals Generator (Desired Output)
Two types of supervised learning
Each training case consists of an input vector x and a
target output t.
X
Y
NN
(Input) W (Actual output)
Error
signals Error
Signal R
Generator Reinforcement signal
When Reinforcement learning is
used?
If less information is available about the
target output values (critic information)
Learning based on this critic information is
called reinforcement learning and the
feedback sent is called reinforcement
signal
Feedback in this case is only evaluative
and not instructive
Basic models of ANN
2
w
11w12 w13 w1m
...
w21w22 w23 w2m ...
T
w
3
.
. =
..................
.
.
...................
.
n1 n 2 n 3 w nm
w w w
T
...
w
n
Weights contd
wij is the weight from processing element i (source node)
to processing element j (destination node)
1
y = x w
inj i ij
i =0
X1 bj
= x 0 w0 j + x1w1 j + x 2 w2 j + .... + x n w nj
w1j
n
Xi Yj = w0 j + x i wij
wij i =1
n
Xn wnj
y = b + x w
inj j i ij
i =1
Activation Functions
Used to calculate the output response of a
neuron.
Sum of the weighted input signal is applied with
an activation to obtain the response.
Activation functions can be linear or non linear
Already dealt
Identity function
Single/binary step function
Discrete/continuous sigmoidal function.
Bias
Bias is like another weight. Its included by
adding a component x0=1 to the input
vector X.
X=(1,X1,X2Xi,Xn)
Bias is of two types
Positive bias: increase the net input
Negative bias: decrease the net input
Why Bias is required?
The relationship between input and output
given by the equation of straight line
y=mx+c
C(bias)
Input X Y y=mx+C
Threshold
Set value based upon which the final output of
the network may be calculated
Used in activation function
The activation function using threshold can be
defined as
1ifnet
f ( net ) =
- 1ifnet
Learning rate
Denoted by .
Used to control the amount of weight
adjustment at each step of training
Learning rate ranging from 0 to 1
determines the rate of learning in each
time step
Other terminologies
Momentum factor:
used for convergence when momentum factor
is added to weight updation process.
Vigilance parameter:
Denoted by
Used to control the degree of similarity
required for patterns to be assigned to the
same cluster
Neural Network Learning rules
c learning constant
Hebbian Learning Rule
FEED FORWARD UNSUPERVISED LEARNING
y Bias update
b(new)=b(old) + y
Activate input
xi=si
Stop