Scribd
Upload
6 views

CHP 9

The document summarizes key aspects of biological and artificial neural networks. It describes how the biological neuron is replicated in artificial neurons. It then explains various activation functions like step, threshold, ReLU, sigmoid and hyperbolic tangent. Early implementations including McCulloch-Pitts model, Rosenblatt's Perceptron, multi-layer perceptron and ADALINE network are outlined. The perceptron and ADALINE are introduced as classifiers for binary problems with linear decision boundaries.

Uploaded by

its9918k
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
6 views

CHP 9

The document summarizes key aspects of biological and artificial neural networks. It describes how the biological neuron is replicated in artificial neurons. It then explains various activation functions like step, threshold, ReLU, sigmoid and hyperbolic tangent. Early implementations including McCulloch-Pitts model, Rosenblatt's Perceptron, multi-layer perceptron and ADALINE network are outlined. The perceptron and ADALINE are introduced as classifiers for binary problems with linear decision boundaries.

Uploaded by

its9918k
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 29

Chapter 9

Neural Network
Biological Neural N/W to Artificial Neural N/W
• The nervous system is constituted of a special type of cell, called
neuron or nerve cell, which has special structures allowing it to
receive or send signals to other neurons.

The only difference is that the biological form of neuron is replicated in the
electronic or digital form of neuron.
Structure of Artificial Neuron Network

A threshold activation function (or simply activation function, also called squashing function)
results in an output signal only when an input signal exceeding a specific threshold value comes as
an input.
Activation Function
• Introduce non-linearities in the network.
Linear activation function produce Non-Linear activation function
linear decision. allows us to approximate
arbitrary complex function.
Types of Activation Function

• Step Function:
- Gives 1 as output if the input is either 0 or positive.
- If the input is negative, the step function gives 0 as output.
• Threshold Function:
- Almost like the step function, with the only difference being the fact
that θ is used as a threshold value instead of 0.
• ReLU (Rectified Linear Unit) function:
- Most popularly used activation function in the areas of convolutional
neural networks and deep learning.
- f(x) is zero when x is less than zero and f(x) is equal to x when x is
above or equal to zero.
• Sigmoid function:
- Most commonly used activation function in neural
networks.

- Types: 1. Binary sigmoid function


2. Bipolar sigmoid function
• Binary sigmoid function:
• k = steepness or slope parameter of the sigmoid function.
• By varying the value of k, sigmoid functions with different slopes can be obtained.
It has range of (0, 1).
• Bipolar Sigmoid Function:

The range of values of sigmoid functions can be varied depending on the


application. However, the range of (−1, +1) is most commonly adopted.
• Hyperbolic tangent function:
• Continuous activation function, which is bipolar in nature.
• Widely adopted activation function for a special type of neural
network known as backpropagation network.
• Note:
• Almost all the activation functions we have defined have values
ranging between 0 and 1.
• In some cases, it is desirable to have values ranging from −1 to +1.
• In that case, there will be a need to reframe the activation function.
Early Implementation of ANN
• McCulloch–Pitts model of neuron:

✔ It has only two types of inputs – excitatory and inhibitory.

✔ The excitatory inputs have weights of positive magnitude and the


inhibitory weights have weights of negative magnitude.

✔ The inputs of the McCulloch– Pitts neuron could be either 0 or 1.

✔ It has a threshold function as activation function. So, the output signal


yout is 1 if the input ysum is greater than or equal to a given threshold
value, else 0.
• Simple McCulloch–Pitts neurons can be used to design logical operations.
• For that purpose, the connection weights need to be correctly decided along with the
threshold function (rather the threshold value of the activation function).
• Example:
John carries an umbrella if it is sunny or if it is raining. There are four
given situations. We need to decide when John will carry the umbrella.

Situations:
Situation 1 – It is not raining nor is it sunny.
Situation 2 – It is not raining, but it is sunny.
Situation 3 – It is raining, and it is not sunny.
Situation 4 – Wow, it is so strange! It is raining as well as it is sunny.
• To analyse the situations using the McCulloch–Pitts neural model, we
can consider the input signals as follows:
x1 → Is it raining?
x2 → Is it sunny?

• So, the value of both x1 and x2 can be either 0 or 1. We can use the
value of both weights x1 and x2 as 1 and a threshold value of the
activation function as 1.
• Formally, we can write,

• Looks like a typical logic problem related to ‘OR’ function?


• It is really an implementation of logical OR using the McCulloch–
Pitts neural model.
Rosenblatt’s Perceptron
• Built around the McCulloch–Pitts neural model.
• The linear combiner or the adder node computes the linear
combination of the inputs applied to the synapses with synaptic
weights being w1 , w2 , …, wn.

• The hard limiter checks


whether the resulting sum is
positive or negative.

• If the input of the hard limiter


node is positive, the output is
+1, and if the input is negative,
the output is −1.
• Basically, mathematical form of the hard limiter input is,

• However, Perceptron includes an adjustable value or bias as


an additional weight w0.
• This additional weight w0 is attached to a dummy input x,
which is always assigned a value of 1.
• So, we get modified equation as,
• The output is decided by the expression,
• A basic perceptron works very successfully for data sets which possess
linearly separable patterns.
(However, in practical situation, that is an ideal situation!)

• This was exactly the point driven by Minsky and Papert in their work
(1969).

• They showed that a basic perceptron is not able to learn to compute


even a simple 2-bit XOR. Why is that so? Let us try to understand.
• Multi-layer Perceptron (MLP):

Major Highlights:
- The neural network contains one or more intermediate layers b/w
the i/p and the o/p nodes, which are hidden from both i/p and o/p
nodes.
- Each neuron in the n/w includes a non-linear activation function
that is differentiable.
- The neurons in each layer are connected with some or all the
neurons in the previous layer.
MLP
ADALINE network model (Adaptive Linear Neural
Element )
• An early single-layer ANN developed by Prof. Bernard
Widrow of Stanford University.
• It has only output neuron.
• The output value can be +1 or −1.
• The activation function is such that if the weighted sum is
positive or 0, then the output is 1, else it is −1.

• The supervised learning algorithm adopted by the ADALINE


network is known as Least Mean Square (LMS) or Delta rule.
• A network combining a number of ADALINEs is termed as
MADALINE (many ADALINE).

• MADALINE networks can be used to solve problems related to


nonlinear separability.
Both perceptron and ADALINE are neural network models.

Both of them are classifiers for binary classification.

They have linear decision boundary and use a threshold


activation function.
Will be continued..

You might also like