2. WHAT ARE NEURAL NETWORKS?
â˘Artificial Neural Network (ANN) :- an information processing paradigm
inspired by the HUMAN nervous system.
â˘Composed of large number of highly interconnected processing elements (neurons).
⢠ANNs, like people, learn by example.
â˘An ANN is configured for a specific application, like pattern recognition or data
classification, through learning.
â˘Learning in biological systems involves synaptic connections between neurons.
3. INTRODUCTION TO NEURAL NETWORKS
⢠An Artificial Neuron Network (ANN), popularly known as Neural Network is a
computational model based on the structure and functions of biological neural
networks.
⢠It is like an artificial human nervous system for receiving, processing, and
transmitting information in terms of Computer Science.
Basically, there are 3 different layers in a neural network :-
⢠Input Layer (All the inputs are fed in the model through this layer)
⢠Hidden Layers (There can be more than one hidden layers which are used
for processing the inputs received from the input layers)
⢠Output Layer (The data after processing is made available at the output
layer)
4. Why use neural networks ?
⢠Knowledge acquisition under noise and
uncertainty.
⢠Flexible knowledge representation.
⢠Efficient knowledge processing.
⢠Fault Tolerance .
⢠They have learning capability.
5. HOW DOES HUMAN BRAIN LEARNS
ďŽ Brain ,made up of large no. of neurons.
ďŽ Each neuron connects to thousands of neurons, communicates
by electrochemical signals.
ďŽ Signals coming are received via SYNAPSES, located at the
end of DENDRITES.
ďŽ A neuron sum up the inputs, and if threshold value is reached
then it generates a voltage and o/p signal, along the AXON.
8. THE ARTIFICIAL NEURON:-
⢠Electronically modeled biological neuron.
⢠Has many inputs and one output.
⢠Has 2 modes -training mode & using mode.
⢠Training mode - neuron is trained to fire (or
not), for particular input patterns.
⢠Using mode - when a taught input pattern is
detected at input, its associated output becomes
current output .
⢠If input pattern does not belong in taught list,
firing rule is used.
9. Working of a
Biological Neuron
As shown in the above diagram, a
typical neuron consists of the following
four parts with the help of which we
can explain its working â
Dendrites â They are tree-like
branches, responsible for receiving the
information from other neurons it is
connected to. In other sense, we can
say that they are like the ears of
neuron.
Soma â It is the cell body of the
neuron and is responsible for
processing of information, they have
received from dendrites.
Axon â It is just like a cable through
which neurons send the information.
Synapses â It is the connection
between the axon and other neuron
dendrites.
10. Model of Artificial
Neural Network
For the above general model
of artificial neural network,
the net input can be
calculated as follows â
yin=x1.w1+x2.w2+x3.w3âŚxm.
wmyin=x1.w1+x2.w2+x3.w3âŚ
xm.wm
i.e., Net
input yin=âmixi.wiyin=âimxi.w
i
The output can be calculated
by applying the activation
function over the net input.
Y=F(yin)Y=F(yin)
Output = function (net input
calculated)
11. Artificial Neural Network - Building
Blocks
⢠Processing of ANN depends upon the
following three building blocks â
⢠Network Topology
⢠Adjustments of Weights or Learning
⢠Activation Functions
12. Network Topology
Feedforward Network:
It is a non-recurrent network having processing
units/nodes in layers and all the nodes in a layer are
connected with the nodes of the previous layers. The
connection has different weights upon them. There is
no feedback loop means the signal can only flow in
one direction, from input to output. It may be
divided into the following two types.
13. Single layer feedforward
network
The concept is of feedforward
ANN having only one
weighted layer. In other
words, we can say the input
layer is fully connected to the
output layer.
14. Multilayer
feedforward network
The concept is of feedforward
ANN having more than one
weighted layer. As this
network has one or more
layers between the input and
the output layer, it is called
hidden layers.
15. LEARNING METHOD FOR IN ANN
⢠Learning is an application of artificial intelligence (AI) that
provides systems the ability to automatically learn and
improve from experience without being explicitly
programmed.
⢠Learning in ANN can be classified into three categories namely
supervised learning, unsupervised learning, and
reinforcement learning.
17. Supervised Learning
â˘As the name suggests, this type
of learning is done under the
supervision of a teacher.
â˘This learning process is
dependent.
â˘During the training of ANN under
supervised learning, the input
vector is presented to the
network, which will give an
output vector.
â˘This output vector is compared
with the desired output vector. An
error signal is generated, if there
is a difference between the actual
output and the desired output
vector.
â˘On the basis of this error signal,
the weights are adjusted until the
actual output is matched with the
desired output.
18. PERCEPTRON
â˘Developed by Frank Rosenblatt by
using McCulloch and Pitts model,
perceptron is the basic operational
unit of artificial neural networks. It
employs supervised learning rule and
is able to classify the data into two
classes.
â˘Operational characteristics of the
perceptron: It consists of a single
neuron with an arbitrary number of
inputs along with adjustable weights,
but the output of the neuron is 1 or
0 depending upon the threshold. It
also consists of a bias whose weight is
always 1. Following figure gives a
schematic representation of the
perceptron
19. PERCEPTRON
⢠Perceptron thus has the following three basic elements â
Links â It would have a set of connection links, which carries a weight including a bias
always having weight 1.
Adder â It adds the input after they are multiplied with their respective weights.
Activation function â It limits the output of neuron. The most basic activation function
is a Heaviside step function that has two possible outputs. This function returns 1,
if the input is positive, and 0 for any negative input.
Training Algorithm
Training Algorithm for Single Output Unit
Step 1 â Initialize the following to start the training â Weights Bias Learning rate For
easy calculation and simplicity, weights and bias must be set equal to 0 and the
learning rate must be set equal to 1.
⢠Step 2 â Continue step 3-8 when the stopping condition is not true. Step 3 â
Continue step 4-6 for every training vector x.
Step 4 â Activate each input unit as follows â
⢠Step 5 â Now obtain the net input with the following relation âÎą
Here âbâ is bias and ânâ is the total number of input neurons
⢠Step 6 â Apply the following activation function to obtain the final output
⢠Step 7 â Adjust the weight and bias as follows
⢠Case 1 â if y â t then, wi(new) = wi(old) + Îątxi b(new) = b(old) + Îąt
â˘
Case 2 â if y = t then, wi(new) = wi(old) b(new) = b(old)
21. Adaptive Linear Neuron(ADALINE)
⢠Adaline which stands for Adaptive Linear Neuron, is a network
having a single linear unit. It was developed by Widrow and
Hoff in 1960. Some important points about Adaline are as
follows:
⢠It uses bipolar activation function.
⢠It uses delta rule for training to minimize the Mean-Squared
Error (MSE) between the actual output and the desired/target
output.
⢠The weights and the bias are adjustable
⢠The basic structure of Adaline is similar to perceptron having
an extra feedback loop with the help of which the actual
output is compared with the desired/target output. After
comparison on the basis of training algorithm, the weights
and bias will be update
22. Multiple Adaptive Linear
Neuron(Madaline)
â˘The architecture of Madaline consists
of ânâ neurons of the input layer, âmâ
neurons of the Adaline layer, and 1
neuron of the Madaline layer. The
Adaline layer can be considered as the
hidden layer as it is between the input
layer and the output layer, i.e. the
Madaline layer.
â˘Madaline which stands for Multiple
Adaptive Linear Neuron, is a network
which consists of many Adalines in
parallel. It will have a single output
unit. Some important points about
Madaline are as follows â
â˘It is just like a multilayer perceptron,
where Adaline will act as a hidden unit
between the input and the Madaline
layer.
â˘The weights and the bias between the
input and Adaline layers, as in we see
in the Adaline architecture, are
adjustable.
The Adaline and Madaline layers have
fixed weights and bias of 1.
Training can be done with the help of
Delta rule.
23. Unsupervised Learning
â˘As the name suggests, this type of
learning is done without the
supervision of a teacher.
â˘This learning process is
independent.
â˘During the training of ANN under
unsupervised learning, the input
vectors of similar type are combined
to form clusters.
â˘When a new input pattern is
applied, then the neural network
gives an output response indicating
the class to which the input pattern
belongs.
â˘There is no feedback from the
environment as to what should be
the desired output and if it is
correct or incorrect.
â˘Hence, in this type of learning, the
network itself must discover the
patterns and features from the
input data, and the relation for the
input data over the output.
24. Reinforcement Learning
â˘As the name suggests, this type
of learning is used to reinforce or
strengthen the network over
some critic information.
â˘This learning process is similar to
supervised learning, however we
might have very less information.
â˘During the training of network
under reinforcement learning, the
network receives some feedback
from the environment. This
makes it somewhat similar to
supervised learning.
â˘However, the feedback obtained
here is evaluative not instructive,
which means there is no teacher
as in supervised learning.
â˘After receiving the feedback, the
network performs adjustments of
the weights to get better critic
information in future.
25. Neural Network Learning Rules
⢠We know that, during ANN learning, to change the input/output behavior,
we need to adjust the weights. Hence, a method is required with the help
of which the weights can be modified. These methods are called Learning
rules, which are simply algorithms or equations.
Following are some learning rules for the neural network â
⢠Hebbian Learning Rule
⢠Perceptron Learning Rule
⢠Delta Learning Rule (Widrow-Hoff Rule)
⢠Competitive Learning Rule (Winner-takes-all)
26. Hebbian Learning Rule
⢠This rule, one of the oldest and simplest, was introduced by Donald Hebb in his
book The Organization of Behavior in 1949. It is a kind of feed-forward,
unsupervised learning.
⢠Basic Concept
⢠This rule is based on a proposal given by Hebb, who wrote â âWhen an axon of cell
A is near enough to excite a cell B and repeatedly or persistently takes part in firing
it, some growth process or metabolic change takes place in one or both cells such
that Aâs efficiency, as one of the cells firing B, is increased.â
⢠From the above postulate, we can conclude that the connections between two
neurons might be strengthened if the neurons fire at the same time and might
weaken if they fire at different times.
⢠Mathematical Formulation
⢠According to Hebbian learning rule, following is the formula to increase the weight
of connection at every time step.
⢠Îwji(t) = Îąxi(t). yj(t)
â˘
⢠Here, Îwji(t) = increment by which the weight of connection increases at time step
t
⢠ι = the positive and constant learning rate
⢠xi(t) = the input value from pre-synaptic neuron at time step t
⢠yi(t) = the output of pre-synaptic neuron at same time step t
27. Perceptron Learning Rule
⢠This rule is an error correcting the supervised learning algorithm of single layer
feedforward networks with linear activation function, introduced by Rosenblatt.
⢠Basic Concept: As being supervised in nature, to calculate the error, there
would be a comparison between the desired/target output and the actual
output. If there is any difference found, then a change must be made to
the weights of connection
⢠Mathematical Formulation: To explain its mathematical formulation,
suppose we have ânâ number of finite input vectors, x(n), along with its
desired/target output vector t(n), where n = 1 to N
â˘
Now the output âyâ can be calculated, as explained earlier on the basis of the net
input, and activation function being applied over that net input can be expressed
as follows
⢠Where θ is threshold
â˘
The updating of weight can be done in the following two cases â
⢠Case I â when t â y, then
28. Model of Artificial Neural Network
⢠Artificial neural networks can be viewed as weighted directed graphs
in which artificial neurons are nodes and directed edges with weights
are connections between neuron outputs and neuron inputs.
⢠The Artificial Neural Network receives input from the external world in
the form of pattern and image in vector form. These inputs are
mathematically designated by the notation x(n) for n number of inputs.
⢠Each input is multiplied by its corresponding weights. Weights are the
information used by the neural network to solve a problem. Typically
weight represents the strength of the interconnection between
neurons inside the neural network.
⢠The weighted inputs are all summed up inside computing unit (artificial
neuron). In case the weighted sum is zero, bias is added to make the
output not- zero or to scale up the system response. Bias has the weight
and input always equal to â1â.
29. Model of Artificial Neural Network
⢠The sum corresponds to any numerical value ranging from 0 to infinity.
⢠In order to limit the response to arrive at desired value, the threshold
⢠value is set up. For this, the sum is passed through activation function.
⢠The activation function is set of the transfer function used to get desired
output. There are linear as well as the non-linear activation function.
⢠Some of the commonly used activation function are â binary, sigmoidal
(linear) and tan hyperbolic sigmoidal functions(nonlinear).
⢠Binary â The output has only two values either 0 and 1. For this, the
threshold value is set up. If the net weighted input is greater than 1, an
output is assumed 1 otherwise zero.
⢠Sigmoidal Hyperbolic â This function has âSâ shaped curve. Here tan
hyperbolic function is used to approximate output from net input. The
function is defined as â f (x) = (1/1+ exp(-đx)) where đâ steepness
parameter.
30. Architecture
⢠Input layerâ It contains those
units (artificial neurons) which
receive input from the outside
world on which network will
learn, recognize about or
otherwise process.
⢠Output layerâ It contains
units that respond to the
informationabout how itâs
learned any task.
⢠Hidden layerâ These units
are in between input and
output layers. The job of
hidden layer is to transform
the input into something that
output unit can use in some
way.
⢠Most neural networks are fully
connected that means to say
each hidden neuron is fully
connected to the every neuron
in its previous layer(input) and
to the next layer (output) layer
31. Learning in Biology(Human
⢠Learning = learning by adaptation
⢠The young animal learns that the green fruits are sour, while the
yellowish/reddish ones are sweet. The learning happens by
adapting the fruit picking behaviour.
⢠At the neural level the learning happens by changing of the synaptic
⢠strengths, eliminating some synapses, and building new ones.
⢠The objective of adapting the responses on the basis of the
information received from the environment is to achieve a better
state. E.g., the animal likes to eat many energy rich, juicy fruits that
make its stomach full, and makes it feel happy.
⢠In other words, the objective of learning in biological organisms
is to optimise the amount of available resources, happiness, or
in general to achieve a closer to optimal state
33. Types of Learning in Neural Network
⢠Supervised Learning âIn supervised learning, the training data is input to
the network, and the desired output is known weights are adjusted until
output yields desired value.
⢠Unsupervised Learning â The input data is used to train the network
whose output is known. The network classifies the input data and adjusts
the weight by feature extraction in input data.
⢠Reinforcement Learning â Here the value of the output is unknown, but
the network provides the feedback whether the output is right or wrong.
It is semi-supervised learning.
⢠Offline Learning âThe adjustment of the weight vector and threshold is
done only after all the training set is presented to the network. it is also
called batch learning.
⢠Online LearningâThe adjustment of the weight and threshold is done
after presenting each training sample to the network.
34. Characteristics of ANN
⢠Using ANNs requires an understanding of their characteristics.
⢠Choice of model: This depends on the data representation and the
⢠application. Overly complex models slow learning.
⢠Learning algorithm: Numerous trade-offs exist between learning
algorithms. Almost any algorithm will work well with the correct
hyper parameters for training on a particular data set. However,
selecting and tuning an algorithm for training on unseen data
requires significant experimentation.
⢠Robustness: If the model, cost function and learning algorithm
are selected appropriately, the resulting ANN can become
robust.
35. Uses of ANN
⢠ANN capabilities fall within the following broad categories
⢠Function approximation, or regression analysis, including time series
⢠prediction, fitness approximation and modeling.
⢠Classification, including pattern and sequence recognition, novelty detection and
sequential decision making.
⢠Data processing, including filtering, clustering, blind source separation and compression.
⢠Robotics, including directing manipulators and prostheses.
⢠Control, including computer numerical control.
⢠Classification âA neural network can be trained to classify given pattern or data set into
predefined class. It uses feed forward networks.
⢠Predictionâ A neural network can be trained to produce outputs thatare expected from
given input. E.g.:âStock market prediction.
⢠Clustering â The Neural network can be used to identify a specialfeature of the data and
classify them into different categories without any prior knowledge of the data.
36. Neural networks vr conventional
computers
COMPUTERS
⢠Algorithmic approach
⢠They are necessarily
programmed
⢠Work on predefined
set of instructions
⢠Operations are
predictable
ANN
⢠Learning approach
⢠Not programmed for
specific tasks
⢠Used in decision making
⢠Operation is
unpredictable
37. Output Layer
⢠The output layer of the neural network collects and transmits the information
accordingly in way it has been designed to give.
⢠he number of neurons in output layer should be directly related to the type of
work that the neural network was performing.
⢠To determine the number of neurons in the output layer, first consider the
intended use of the neural network.
38. Figure depicting the Activation function for ANN
Summation function = X1Wi1+X2Wi2+âŚ+XnWin
39. How is Brain Different from Computers
BRAIN
⢠Biological Neurons or Nerve C
⢠200 Billion Neurons, 32
trillion interconnections.ells.
⢠Neuron Size: 10-6m.
⢠Energy Consumption: 6-10
Joules operation per second.
⢠Learning Capability
COMPUTERS
⢠Silicon Transistor.
⢠1 Billion bytes RAM, trillion
of bytes on disk.
⢠Single Transistor Size: 10-
9m.
⢠Energy Consumption: 10-16
Joules Operation per second
⢠Programming capability
40. Comparing ANN with BNN
As this concept borrowed from ANN there are lot of similarities though there
are differences too.
⢠Similarities are in the following table
Biological Neural Network
⢠Soma
⢠Dendrites
⢠Synapse
⢠Axon
Artificial Neural Network
⢠Node
⢠Input
⢠Weights or Interconnections
⢠Output
41. Criteria BNN ANN
Processing Massively parallel, slow but
superior than ANN
Massively parallel, fast but
inferior than BNN
Size 1011 neurons and 1015
interconnections
102 to 104 nodes (mainly
depends on the type of
application and network
designer)
Learning They can tolerate ambiguity Very precise, structured and
formatted data is required to
tolerate ambiguity
Fault tolerance Performance degrades with
even partial damage
It is capable of robust
performance, hence has the
potential to be fault tolerant
Storage capacity Stores the information in the
synapse
Stores the information in
continuous memory locations
42. Analogy of ANN with BNN
⢠The dendrites in biological
neural network is analogous
to the weighted inputs
based on their synaptic
interconnection in artificial
neural network.
⢠Cell body is analogous to
the artificial neuron unit in
artificial neural network
which also comprises of
summation and threshold
unit.
⢠Axon carry output that is
analogous to the output
unit in case of artificial
neural network. So, ANN
are modelled using the
working of basic
biological neurons.
43. Applications
⢠Because of their ability to reproduce and model nonlinear processes, ANNs
have found many applications in a wide range of disciplines.
⢠Application areas include system identification and control (vehicle control,
trajectory prediction, process control, natural
⢠resources management), quantum chemistry,[game-playing and decision making
(backgammon, chess, poker), pattern recognition (radar systems, face
identification, signal classification, object recognition and more), sequence
recognition (gesture, speech, handwritten text recognition), medical diagnosis,
finance (e.g. automated trading systems), data mining, visualization, machine
translation, social network filtering and e-mail spam filtering.
⢠ANNs have been used to diagnose cancers, including lung cancer, prostate cancer,
colorectal cancer and to distinguish highly invasive cancer cell lines from less
invasive lines using only cell shape information.
⢠ANNs have been used for building black-box models in geosciences: hydrology
ocean modeling and coastal engineering, and geomorphology, are just few
examples of this kind.