Contributed by Pulkit Khandelwal.
Let us say that we are given two types of activation functions: linear and a hard threshold function as stated below:
- Hard Threshold:
Which of the following can be exactly represented by a neural network with one hidden layer? You can use linear and/or threshold activation functions. Justify your answer with a brief explanation.
- polynomials of degree 2
- polynomials of degree 1
- hinge loss
- piecewise constant functions