Here I answer (some of) the questions at the end of the first chapter of Deep Learning for Coders with fastai and PyTorch.

1. What was the name of the first device that was based on the principle of the artificial neuron?
   • The name of this device was the Mark I Perceptron. It was primarily developed by Mark Rosenblatt (when he expanded upon work done by Warren McCulloch and Walter Pitts). In “The Design of an Intelligent Automaton”, Rosenblatt wrote about this work: “We are now about to witness the birth of such a machine - a machine capable of perceiving, recognizing and identifying its surroundings without any human training or control”. It was able to successfully recognize simple shapes.
2. Based on the book of the same name, what are some of the requirements for parallel distributed processing (PDP)?
   • A set of processing units
   • A state of activation
   • An output function for each unit
   • A pattern of connectivity among units
   • A propogation rule for propogating patterns of activities through the network of connectivities
   • An activation rule for combining the inputs impinging on a unit with the current state of that unit to produce an output for the unit
   • A learning rule whereby patterns of connectivity are modified by experience
   • An environment within which the system must operate Neural networks handle each of these requirements.
3. What were two theoretical misunderstandings that held back the field of neural networks? -
4. What is a GPU? -
5. Why is it hard to use a traditional computer program to recognize images in a photo? -
6. What did Samuel mean by “weight assignment? -
7. What term do we normally use in deep learning for what Samuel called “weights”? -
8. Why is it hard to understand why a deep learning model makes a particular prediction? -
9. What is the name of the theorem that shows that a neural network can solve any mathematical problem to any level of accuracy? -
10. What do you need in order to train a model? -
11. How could a feedback loop impact the rollout of a predictive policing model? -
12. What is the difference between classification and regression? -
13. What is a validation set? What is a test set? Why do we need them? -
14. Can we always use a random sample for a validation set? Why or why not? -
15. What is overfitting? Provide an example. -
16. What is a metric? How does it differ from loss? -
17. How can pretrained models help? -
18. What is the “head” of a model? -
19. What kinds of features do the early layers of a CNN find? How about the later layers? -
20. What is an architecture? -
21. What is segmentation? -
22. What are hyperparameters? -