Q&A

1. How would you define the term "deep learning"?
2. What is the difference between traditional machine learning algorithms and algorithms used in deep learning?
3. List and briefly describe five types of neural networks.
4. Can you figure out how to calculate the number of trainable parameters in a network given the number of neurons per layer? For example, a neural network with the architecture [10, 8, 8, 2] has in total 178 trainable parameters (160 weights and 18 biases).
5. Name four different activation functions and briefly explain them.
6. In your own words, describe loss in neural networks.
7. Explain why modeling imagine classification models with regular artificial neural networks isn't a good idea.