Professional Documents
Culture Documents
3/13/2019 1
Objective
2
History
3
Definition
5
Biological
Neural Networks
Each of the yellow blobs in the picture above are neuronal cell bodies
(soma), and the lines are the input and output channels (dendrites and
axons) which connect them.
6
Biological
Neural Networks
presynaptic
Synapse
neuron
Synapse Dendrites
Axon
Axon
Soma Soma
Dendrites
Synapse
postsynaptic
7 neuron
Biological
Neural Networks
9
Biological
Neural Networks
Hence a neuron fires only if the total signal received at the cell
body exceeds a certain level. The neuron either fires or it doesn't,
there aren't different grades of firing.
10
Artificial Neuron/models of neuron
Input Synaptic
Output Signals
Signals Weights
x1
wk1
Summing
function
x2 uk
wk2
k (.) yk
Activation
wkp
k Function
xp
Threshold, -1
11
Artificial Neuron
12
Artificial Neuron
p
u wi xi w T x
i 1
y (u )
15
Artificial Neuron
Example 1:
The figure shows a neuron with
activation function u given
by
0.8
u
1 exp 11.2u
Find the total synaptic input and the output activation of the
neuron for an input with x1 = 0.8, x2 = 2.0 and x3 = -0.5.
17
Artificial Neuron
Example 1: Solution
T
2.5 0.8
u wT x 1.2 2 1 1.9
or
1.0 0.5
T
2.5 0.8
1.2 2
u w 'T x ' 1.9
1.0 0.5
1 1
0.8
y u 1.9 0.8
18 1 exp 11.2* 1.9
Typical ANN
Activation Functions
(u) purelin(u) u
20
ANN Activation
Functions
1 exp(bu ) 2
(u ) a a 1
1 exp( bu ) 1 exp( bu )
Sigmoid is the most pervasive and biologically plausible activation
function. a denotes the gain or amplitude of the transfer function,
b denotes the slope of transfer function. Note that the sigmoid
21 function is differentiable.
Example
What activation function is this?
Two-Layer Feedforward
Networks:
23
ANN
Architectures
Recurrent networks
without hidden neurons:
• Recurrent network
consists of a single layer of
neurons with each neuron
feeding its output signal
back to the input layer.
25
Three-Layer
FeedForward Network
Consider a three layer neural network:
wji
vkj
xi = (x1 x2 … xI)T
28
FeedForward
ANN Analysis
The synaptic input vector u = (u1, u2, … , uJ)T to the
hidden layer
u = [w1, w2, … wJ]Tx
= Wx
where the weight matrix W between input and hidden-
layer is given by
W = {wji}J*I = [w1 w2 … wJ]T
30
FeedForward
ANN Analysis
z = g(s)
Where
31
ANN
Example 2:
A three-layer neural network contains 3 input-layer nodes, 3
hidden-layer neurons and 2 output-layer neurons. When u is the
net synaptic input the activation function of the hidden-layer is
given by
1 exp 0.5u1
f u1
1 exp 0.5u1
Example 2: Solution
x =(1.0 0.0 -0.2)T, 0.2 - 1.0 0.5 1.0
u1 Wx 1.0 - 0.2 0.2 0.0
-0.3 - 0.4 1.0 0.2
u2 ?
35 output g u 2 ?
ANN Learning
Training (or learning) of Neural Networks:
Supervised Learning:
Unsupervised Learning:
• Adaptiveness:
Neural network learn from exemplars as they arise in the
external world.
40
Characteristics
of ANN
• Generalization:
Networks have the ability to learn the rules and mimic the
behavior of a large ensemble of inputs from an adequate set of
exemplars.
• Fault-tolerance:
Since information processing involves a large no. of neurons and
connections, loss of a few connections does not necessarily
affect the overall performance.
• Ease of construction:
To implement a neural-based system for solving complex
problems, it requires only a short development time.
41
ANN
Limitations
• Operational Problems:
Majority of neural networks are simulated on sequential
machines. As size of the problem increases, size of the
computational time required to solve the problems will
increase significantly.
• Intractable Systems:
Outcomes computed from neural networks are extremely
difficult to be explained. Networks operate as black boxes
whose rules of operation are completely hidden.
42
ANN
Applications
• Pattern recognition:
Automatic recognition of handwritten characters; The large
variations in sizes, orientations, and styles of different
handwriting make this an extremely difficult problem.
• Speech recognition:
Learning to read English text; A set of written letters, together
with the correct pronunciation are required for training a neural-
base system. After training, the system can read new words
without or with few errors.
43
ANN
Applications
• Financial:
Real estate appraisal, loan advisor, mortgage screening,
corporate financial analysis, currency price prediction.
44
ANN
Applications
45
ANN
Applications
Predicting the age of abalone from physical measurements.
The age of abalone is determined by cutting the shell through the cone, staining it, and
counting the number of rings through a microscope -- a boring and time-consuming
task. Other measurements, which are easier to obtain, are used to predict the age.
Further information, such as weather patterns and location (hence food availability) may
be required to solve the problem.
Number of Attributes/Features: 15
47
ANN
Applications
Breast Cancer Prediction
This breast cancer databases was obtained from the University of
Wisconsin Hospitals, Madison, USA.