Six questions covering the whole short course. Each has one correct answer.
Your turn
What does a single neuron compute from its inputs?
Your turn
Why must a neural network use a nonlinear activation function?
Your turn
In the layer equation a = sigma(Wx + b), what does one row of W hold?
Your turn
Why can a single neuron not learn the XOR function?
Your turn
When is binary cross-entropy loss for one example close to zero?
Your turn
In the update w <- w - eta times the slope of the loss, what does that slope tell you?
Sign in to take the chapter quiz and check your understanding.