Professional Documents
Culture Documents
Unit 1
Unit 1
1
2/2/2022
Model Of A Neuron
Wa
X1
Wb Y
X2 f()
Wc
X3
w1
x1
y
Axon
x2 w2 Activation Function:
yin = x1w1 + x2w2 (y-in) = 1 if y-in >=
and (y-in) = 0
Dendrite
-A neuron receives input, determines the strength or the weight of the input, calculates the total
weighted input, and compares the total weighted with a value (threshold)
- If the total weighted input greater than or equal the threshold value, the neuron will produce the output,
and if the total weighted input less than the threshold value, no output will beproduced
2/2/2022
History
• 1943 McCulloch-Pitts neurons
• 1949 Hebb‟s law
• 1958 Perceptron (Rosenblatt)
• 1960 Adaline, better learning rule (Widrow,
Huff)
• 1969 Limitations (Minsky, Papert)
• 1972 Kohonen nets, associative memory
2/2/2022
• 1977 Brain State in a Box (Anderson)
• 1982 Hopfield net, constraint satisfaction
• 1985 ART (Carpenter, Grossfield)
• 1986 Backpropagation (Rumelhart, Hinton,
McClelland)
• 1988 Neocognitron, character recognition
(Fukushima)
2/2/2022
Characterization
• Architecture
– a pattern of connections between neurons
• Single Layer Feedforward
• Multilayer Feedforward
• Recurrent
• Strategy / Learning Algorithm
– a method of determining the connection weights
• Supervised
• Unsupervised
• Reinforcement
• Activation Function
– Function to compute output signal from input signal
2/2/2022
Single Layer Feedforward NN
x1 w11
w12 ym
w21
yn
x2
w22
output layer
Input layer
2/2/2022
Multilayer Neural Network
z1
x1 V11
w11
w12
V1n
w12 y1
x2 z2
y2
zn
xm Vmn
Input layer Output layer
Hidden layer
CCN, GRNN, MADALINE, MLFF with BP, Neocognitron, RBF, R2C3E
2/2/2022
Recurrent NN
Input Outputs
Hidden nodes
2/2/2022
Unsupervised Learning
2/2/2022
Where can neural network systems help…
• when we can't formulate an algorithmic
solution.
• when we can get lots of examples of the
behavior we require.
„learning from experience‟
• when we need to pick out the structure
from existing data.
2/2/2022
Who is interested?...
• Electrical Engineers – signal processing,
control theory
• Computer Engineers – robotics
• Computer Scientists – artificial
intelligence, pattern recognition
• Mathematicians – modelling tool when
explicit relationships are unknown
2/2/2022
Problem Domains
• Storing and recalling patterns
• Classifying patterns
• Mapping inputs onto outputs
• Grouping similar patterns
• Finding solutions to constrained
optimization problems
2/2/2022
Coronary
Disease
Classification
STOP
01 10
Neural
11
Net 11 10 00 00 Input patterns
00 11
Input layer
Output layer
00 01 10 11
Sorted
00 10 11 pa.tterns
00 11 34
2/2/2022
Clustering
00 11
10
11 10
00 11
00
01
35
2/2/2022
ANN Applications
Medical Applications
Information
Searching & retrieval
Chemistry
Education
2/2/2022 Business & Management
Applications of ANNs
• Signal processing
• Pattern recognition, e.g. handwritten
characters or face identification.
• Diagnosis or mapping symptoms to a
medical case.
• Speech recognition
• Human Emotion Detection
• Educational Loan Forecasting
2/2/2022
Abdominal Pain Prediction
Intensity Duration
Male Age Temp WBC Pain Pain
adjustable
1 20 37 10 1 1
weights
2/2/2022
Voice Recognition
2/2/2022
Educational Loan Forecasting System
2/2/2022
Advantages Of NN
NON-LINEARITY
It can model non-linear systems
INPUT-OUTPUT MAPPING
It can derive a relationship between a set of input & output
responses
ADAPTIVITY
The ability to learn allows the network to adapt to changes in
the surrounding environment
EVIDENTIAL RESPONSE
It can provide a confidence level to a given solution
2/2/2022
Advantages Of NN
CONTEXTUAL INFORMATION
Knowledge is presented by the structure of the network.
Every neuron in the network is potentially affected by the
global activity of all other neurons in the network.
Consequently, contextual information is dealt with naturally in
the network.
FAULT TOLERANCE
Distributed nature of the NN gives it fault tolerant capabilities
NEUROBIOLOGY ANALOGY
Models the architecture of the brain
2/2/2022
The machine learning framework
y = f(x)
output prediction Image
function feature
2/2/2022
The machine learning framework
• Apply a prediction function to a feature representation of the
image to get the desired output:
f( ) = “apple”
f( ) = “tomato”
f( ) = “cow”
2/2/2022
Steps
Training Training
Labels
Training
Images
Image Learned
Training
Features model
Testing
Image Learned
Prediction
Features model
2/2/2022
Test Image
Features
• Raw pixels
• Histograms
•…
2/2/2022
Classifiers: Nearest neighbor
Training
Training Test
examples
examples example
from class 2
from class 1
2/2/2022
Classifiers: Linear
f(x) = sgn(w x + b)
2/2/2022
Many classifiers to choose from
• SVM Which is the best one?
• Neural networks
• Naïve Bayes
• Bayesian network
• Logistic regression
• Randomized Forests
• Boosted Decision Trees
• K-nearest neighbor
• RBMs
• Etc.
2/2/2022
Recognition task and supervision
• Images in the training set must be annotated with the “correct
answer” that the model is expected to produce
Contains a motorbike
2/2/2022
Unsupervised “Weakly” supervised Fully supervised
2/2/2022
Why we use Activation functions with Neural
Networks?
It is used to determine the output of neural network like yes or no. It
maps the resulting values in between 0 to 1 or -1 to 1 etc. (depending
upon the function).
The Activation Functions can be basically divided into 2 types-
1. Linear Activation Function
2. Non-linear Activation Functions
2/2/2022
Linear or Identity Activation Function
As you can see the function is a line or linear. Therefore, the output of
the functions will not be confined between any range.
2/2/2022
Cont…
Equation : f(x) = x
Range : (-infinity to infinity)
Note:
It doesn’t help with the complexity or various parameters of usual
data that is fed to the neural networks.
2/2/2022
Other Linear functions
• Binary Step Function
Binary step function is a threshold-based activation function which
means after a certain threshold neuron is activated and below the said
threshold neuron is deactivated.
2/2/2022
Bipolar step function: if the value of Y is above a certain value known
as the threshold, the output is +1and if it's less than the threshold then
the output is -1. It has bipolar outputs (+1 to -1).
2/2/2022
Non-linear Activation Function
2/2/2022
It makes it easy for the model to generalize or adapt with variety of data
and to differentiate between the output.
The main terminologies needed to understand for nonlinear functions
are:
• Derivative or Differential: Change in y-axis w.r.t. change in x-axis.It
is also known as slope.
• Monotonic function: A function which is either entirely non-
increasing or non-decreasing.
The Nonlinear Activation Functions are mainly divided on the basis of
their range or curves.
2/2/2022
Sigmoid or Logistic Activation Function
2/2/2022
Tanh or hyperbolic tangent Activation Function
The range of the tanh function is from (-1 to 1). tanh is also sigmoidal (s
- shaped).
The advantage is that the negative inputs will be mapped strongly
negative and the zero inputs will be mapped near zero in the tanh graph.
2/2/2022