Scribd
Upload
44 views11 pages

Meghana Tribhuwan

This document discusses different types of machine learning algorithms. It provides details on supervised learning, including that it takes place under teacher supervision and involves comparing network outputs to target outputs to adjust weights. It also describes the basic structure and training algorithm for perceptrons and neural networks with single and multiple outputs. Unsupervised learning is defined as not involving teacher supervision and focusing on discovering patterns in the input data without target outputs.

Uploaded by

meghanaghogare
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
44 views11 pages

Meghana Tribhuwan

This document discusses different types of machine learning algorithms. It provides details on supervised learning, including that it takes place under teacher supervision and involves comparing network outputs to target outputs to adjust weights. It also describes the basic structure and training algorithm for perceptrons and neural networks with single and multiple outputs. Unsupervised learning is defined as not involving teacher supervision and focusing on discovering patterns in the input data without target outputs.

Uploaded by

meghanaghogare
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 11

ANN

Meghana Tribhuwan
Supervised learning
• As the name suggests, supervised learning takes place under the
supervision of a teacher.
• This learning process is dependent
•  the input vector is fed to the network, which produces output vector
• This output vector is compared with the desired/target vector
• An error signal is generated if there is a difference between the actual
output and the desired/target output vector
• On the basis of this error signal, the weights would be adjusted until
the actual output is matched with the desired output.
Perceptron

• Links − It would have a set of


connection links, which carries a weight
including a bias always having weight 1.
• Adder − It adds the input after they are
multiplied with their respective
weights.
• Activation function − 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.
• Y= Salary, A=experience, b=const/bais

Y= b + aX
Training Algorithm for Single Output Unit

• Step 1 − Initialize the following to start the training −


• Weights
• Bias
• For easy calculation and simplicity, weights and bias must be set equal
to 0.
• Step 2 − Continue step 3-8 when the stopping condition is not true.
• Step 3 − Continue step 4-6 for every training vector x.
• Step 4 − Activate each input unit as follows − xi=si
• Step 5 − Now obtain the net input with the following relation −

• Here ‘b’ is bias and ‘n’ is the total number of input neurons.


• Step 6 − Apply the following activation function to obtain the final
output.
• Step 7 − Adjust the weight and bias as follows −
• Case 1 − if y ≠ t then,

• Case 2 − if y = t then,


Training Algorithm for Multiple Output Units
Step 1 − Initialize the following to start the training −
•Weights
•Bias
•Learning rate αα
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 − Continue step 3-8 when the stopping condition is not true.
Step 3 − Continue step 4-6 for every training vector x.
Step 4 − Activate each input unit as follows −
xi=si
• Step 5 − Obtain the net input with the following relation

• Here ‘b’ is bias and ‘n’ is the total number of input neurons.


• Step 6 − Apply the following activation function to obtain the final
output for each output unit j = 1 to m −
Step 7 − Adjust the weight and bias for x = 1 to n and j = 1 to m as follows −
Case 1 − if yj ≠ tj then,

Case 2 − if yj = tj then,

• Here ‘y’ is the actual output and ‘t’ is the desired/target output.


• Step 8 − Test for the stopping condition, which will happen when there is no change in weight.
Unsupervised Learning

• As the name suggests, this type of learning is done without the supervision of a
teacher. 
• This learning process is independent.
• During the training of ANN under unsupervised learning, the input vectors of
similar type are combined to form clusters.
• When a new input pattern is applied, then the neural network gives an output
response indicating the class to which input pattern belongs
• no feedback from the environment as desired op is not known
• Hence, in this type of learning the network itself must discover the patterns,
features from the input data and the relation for the input data over the output.

You might also like