Questions for Review

    1. What is an activation function? Explain when you might use the hyperbolic tangent activation function over the sigmoid activation function.

    2. How can you determine if an activation function is compatible with the backpropagation training method?

    3. Consider a neural network with one output neuron and three input neurons. The weights between the three input neurons and the one output neuron are 0.1, 0.2, and 0.3. The threshold is 0.5. What would be the output value for an input of 0.4, 0.5, and 0.6?

    4. Explain the role of the learning rate in backpropagation.

    5. Explain the role of the momentum in backpropagation.