b) Describe the Function Approximation in MLP. Also, explain Generalization of MLP.
Function approximation in Multilayer Perceptrons (MLPs) involves training the network to approximate a target function, which maps input data to output data. MLPs consist of an input layer, one or more hidden layers, and an output layer. Each neuron in the network performs a weighted sum of its inputs, applies an activation function, and passes the result to the neurons in the next layer.
During training, the weights of the connections between neurons are __________ __________ _________ ____ ___ __________ ____.
_____ ___ _________ ______ ___ _________ _________ __________.
____ _____ ________ ____ _____.
_____ ___ _________ ______ ______ _____ ______ _________ ________.
_______ ___ _________ ________ _______ _________ _____ ___ ____ _______.
______ ______ _____ _________ ___ _______ ______ ______.
________ __________ _________ ____ ________.
_____ _________ ___ ______ ____ _________ __________.
____ ________ _______ _______ ____ ____ _________.
__________ ________ _______ _________ ___ ___ _______ ______ __________.
__________ _______ _____ _________ _____ _________ _______ _________ _________ ____ _______ ____.
________ _______ ______ _______ __________ ____ ______.
____ ____ ______ ______ _____.
______ ___ ________ ___ _____.
___ _______ ____ ______ _________.
________ _____ __________ ________ ___ _____ _________ _____ ________ ______ ___ _________.
___ ___ _________ _________ ______ _____ _____ _____ ____ _____.
_____ ___ ___ _____ ____ _________ ________ __________ _________ _________.
_________ ___ ______ ___ ________ ______ ______ ___.
___ _______ __________ ________ ___ ______.
_____ ___ ________ ________ ______ ____ _____.
___ ____ _______ _________ _____.
_______ ______ ____ ___ _______ _________ _________ ___ ______.
___ ____ ____ _________ ______ ________ ________ ___ ________ _____.
__________ __________ __________ _______ ____ ______ __________ __________ __________ ___ ________ ___.
___ ___ ____ _______ _________ ________ __________ ___.
__________ ______ ___ ___ _____ ________.
_________ __________ _______ _______ _____ ________ _____ _______ ________.
__________ ______ ____.
Get Full Answer on WhatsApp
b) Apply the “very” hedge on the fuzzy sets defined in Q. 1(b) to get the new modified fuzzy sets. Show the modified fuzzy sets through numeration.
Consider a dataset of six points given in the following table, each of which has two features and
Assuming the values of the parameters c and m as 2 and the initial cluster centers
and
apply FCm algorithm to find the new cluster center after one iteration.
| 3 | 11 | |
| 3 | 10 |
| 8 | 12 | |
| 10 | 6 | |
| 13 | 6 | |
| 13 | 5 |
b) Consider a subset of natural numbers from 1 to 30, as the universe of discourse, U. Define the fuzzy sets “small” and “medium” by enumeration.
a) Define Error Correction Learning with examples.
Which of the following statements are true or false? Give a short proof or a counter example in support of your answers.
a) There is chance of occurrence of the premature convergence in Roulett-wheel selection shceme used in GA.
b) Gradient based optimization methods are used when the objective function is not smooth and one needs efficient local optimization.
c) The cut of a fuzzy set A in U is defined as A
d) A single perception with preprocessing is neither an auto associative network nor a multiple layer neural network.
e) If W then perception is non-linear separable.
b) Write the types of Neural Memory Models. Also, give one example of each.
a) Construct the α − cut at α = 4.0 for the fuzzy sets defined in Q. 1(b)