Suppose your input is a 300 by 300 color (RGB) image, and you are not using a convolutional network. If the first hidden layer has 100 neurons, each one fully connected to the input, how many parameters does this hidden layer have (including the bias parameters)?
9,000,001
9,000,100
27,000,001
27,000,100
Hey @debjanihome,
Option (D)
The input is an RGB image. Therefore,
1.Size of the input layer will be 3003003 = 2,70,000.
2.Size of the hidden layer = 100
3. Number of biases in hidden layer = 100
The number of weights between the hidden layer and the input layer will be = Number of Input x Neurons in hidden layer.
2,70,000 x 100 = 2,70,00,000 parameters.
Therefore total parameters will be Weights +Biases
2,70,00,000 + 100 = 2,70,00,100
I hope you got the point! 