Question

I have built a simple neural network for an image recognition problem. Now, I want to test if I have assigned the weights &
biases for the hidden layer correctly. To perform this action, I am giving an identity matrix as input. Below is my identity
matrix:
A= [1,0,0
0,1,0
0, 0, 1]​

Answer 1

Answer:

np,eye(3)

Explanation:

correct answer

Answer 2

Concept

Neural network is a learning algorithm that uses function networks to translate a data input into a desired output.

Given

The statement for a simple neural network is given

Find

We need to test the assigned weights.

Solution

• If number of input layer nurons = 3
• number of hidden layer nuron should be 3
• It should be at max a 2 layer neutal network
• Weights + bias linear combination will be obtained when we pass identity matrix
• You can confirm dimensions of weights and bias correctly
• Individual weights and bias cannot be confirmed using this

Hence the solutions of the test is been described.

#SPJ2