Question

For training a binary classification model with three independent variables, you choose to use neural networks. You apply one hidden layer with four
neurons. What are the number of parameters to be estimated? (Consider the bias term as a parameter)

Answer 1

Answer:

If you have a lot of training sets or examples, you can use many hidden units.

Usually  2 hidden units works best with less amount of data. The optimal number of hidden units can be smaller than the number of inputs.

There is no rule like multiply the number of inputs with N.

Usually people use one hidden layer for simple tasks, but nowadays research in deep neural network architectures show that many hidden layers can be fruitful for difficult object, handwritten character, and face recognition problems.You need to use Cross-validation to test the accuracy on the test set.