This chapter was filled with various theoretical concepts to understand so, just like the previous chapter, don't skip the exercises:
- What are the similarities between artificial and biological neurons?
- Does the neuron's topology change the neural network's behavior?
- Why do neurons require a non-linear activation function?
- If the activation function is linear, a multi-layer neural network is the same as a single layer neural network. Why?
- How is an error in input data treated by a neural network?
- Write the mathematical formulation of a generic neuron.
- Write the mathematical formulation of a fully connected layer.
- Why can a multi-layer configuration solve problems with non-linearly separable solutions?
- Draw the graph of the sigmoid, tanh, and ReLu activation functions.
- Is it always required to format training set labels into a one-hot encoded representation...