For more questions, including detailed answers and links to the video timeline, have a look at Radek Osmulski’s .
-
- Lots of math T / F
- Lots of data T / F
- Lots of expensive computers T / F
- A PhD T / F
Name five areas where deep learning is now the best in the world.
- Based on the book of the same name, what are the requirements for parallel distributed processing (PDP)?
- What were the two theoretical misunderstandings that held back the field of neural networks?
- What is a GPU?
- Open a notebook and execute a cell containing: . What happens?
- Complete the Jupyter Notebook online appendix.
- Why is it hard to use a traditional computer program to recognize images in a photo?
- What did Samuel mean by “weight assignment”?
- What term do we normally use in deep learning for what Samuel called “weights”?
- Draw a picture that summarizes Samuel’s view of a machine learning model.
- Why is it hard to understand why a deep learning model makes a particular prediction?
- What is the name of the theorem that shows that a neural network can solve any mathematical problem to any level of accuracy?
- What do you need in order to train a model?
- How could a feedback loop impact the rollout of a predictive policing model?
- Do we always have to use 224×224-pixel images with the cat recognition model?
- What is the difference between classification and regression?
- What is a validation set? What is a test set? Why do we need them?
- Can we always use a random sample for a validation set? Why or why not?
- What is overfitting? Provide an example.
- What is a metric? How does it differ from “loss”?
- How can pretrained models help?
- What is the “head” of a model?
- What kinds of features do the early layers of a CNN find? How about the later layers?
- Are image models only useful for photos?
- What is an “architecture”?
- What is segmentation?
- What is
y_range
used for? When do we need it? - What are “hyperparameters”?
- What’s the best way to avoid failures when using AI in an organization?
Each chapter also has a “Further Research” section that poses questions that aren’t fully answered in the text, or gives more advanced assignments. Answers to these questions aren’t on the book’s website; you’ll need to do your own research!
- Try to think of three areas where feedback loops might impact the use of machine learning. See if you can find documented examples of that happening in practice.