Question

A no bias autoencoder consists of 100 input neurons, 50 hidden neurons. If the network weights are represented using single precision floating point numbers then what will be size of weight matrix?​

Answer 1

Explanation:

For convenience, a weighing matrix of order n and weight w is often denoted by W(n,w). A W(n,n) is a Hadamard matrix and a W(n,n-1) is equivalent to a conference matrix.

Answer 2

GIVEN:

Hidden neurons=50

Input neurons=100

To find:

Size of weight matrix

Solution:

Weights are represented using single precession floating point numbers

We know that,  

The size of weight matrix= Hidden neurons(no of rows),input neurons+1(no of coloumns)

So here ,

Size of weight matrix=50 rows,100+1 coloumns

                                        =50 rows,101 coloumns

The weight matrix depends on the input neurons as well as hidden neurons as well .

So  we get,

Rows=50

Coloumns=101