Question

A na 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

given

autoencoder consists of 100 input neurons, 50 hidden neurons. If the network

so, weight 100*50

----5000

Answer 2

Size of weight matrix = 50, 101

Explanation:

Given: 100 input neurons and 50 hidden neurons.

Find: Size of weight matrix

Solution:

Size of weight matrix are represented using single precision floating point numbers.

Size of weight matrix = rows, columns.

The number of rows will be the number of hidden neurons.

The number of columns will be the number of input neurons + 1.

Here number of rows = 50

number of columns = 100+1 = 101

Hence size of weight matrix = 50 rows, 101 columns.