This homework is derived from your lab Expressiveness and an introduction to neural networks we completed in class.
Homework exercise: Consider the following two-adjacent-bumps function. One bump is be \(4\) units in height, the other \(10\).
Draw a basic neural network, including its weights and biases, that represents this function.
Homework exercise: Suppose that \(f(x) = e^{x-1}\) as below. Find a one-hidden-layer neural network approximation of \(f\). Use the \(\text{ReLU}(x)\) activation function and at least three neurons in the hidden layer. Submit both: the graph of your approximation and a diagram of the neural network you used including its weights and biases.
