Fixture build. Each tier has one scaffold exercise for chapter 1. The JSON shape is documented in the platform README.md and insrc/data/exercises/c01.json.
c01
1. Rules That Turn Inputs Into Outputs
What does a program promise you?
E1
Apply the idea to a fresh example.
8 exercises
E2
Prove, derive or compute something not stated in the text.
3 exercises
E3
Work on a question the field does not fully settle.
1 exercise
c02
2. Learning a Rule From Examples
What must a table of examples carry for prediction to be possible?
E1
Apply the idea to a fresh example.
8 exercises
E2
Prove, derive or compute something not stated in the text.
3 exercises
E3
Work on a question the field does not fully settle.
1 exercise
c03
3. How to Know a Claim Is True
What does "for all" commit you to?
E1
Apply the idea to a fresh example.
8 exercises
E2
Prove, derive or compute something not stated in the text.
3 exercises
E3
Work on a question the field does not fully settle.
1 exercise
c04
4. Experiments That Do Not Lie
How much does one run tell you?
E1
Apply the idea to a fresh example.
8 exercises
E2
Prove, derive or compute something not stated in the text.
3 exercises
E3
Work on a question the field does not fully settle.
1 exercise
c05
5. How Long Does It Take?
How do we measure the work a program does?
E1
Apply the idea to a fresh example.
8 exercises
E2
Prove, derive or compute something not stated in the text.
3 exercises
E3
Work on a question the field does not fully settle.
1 exercise
c06
6. The Real Machine
How is a decimal number stored in 32 bits?
E1
Apply the idea to a fresh example.
8 exercises
E2
Prove, derive or compute something not stated in the text.
3 exercises
E3
Work on a question the field does not fully settle.
1 exercise
c07
7. Lists of Numbers That Do Things
What makes a list of numbers a vector?
E1
Apply the idea to a fresh example.
8 exercises
E2
Prove, derive or compute something not stated in the text.
3 exercises
E3
Work on a question the field does not fully settle.
1 exercise
c08
8. Projection and the Best Fit
How do you measure the angle between two lists?
E1
Apply the idea to a fresh example.
8 exercises
E2
Prove, derive or compute something not stated in the text.
3 exercises
E3
Work on a question the field does not fully settle.
1 exercise
c09
9. Directions That Stay Put
Which directions does a matrix leave alone?
E1
Apply the idea to a fresh example.
8 exercises
E2
Prove, derive or compute something not stated in the text.
3 exercises
E3
Work on a question the field does not fully settle.
1 exercise
c10
10. Change, Slopes and Approximation
What does it mean to get arbitrarily close?
E1
Apply the idea to a fresh example.
8 exercises
E2
Prove, derive or compute something not stated in the text.
3 exercises
E3
Work on a question the field does not fully settle.
1 exercise
c11
11. Probability as Reasoning
What rules must a degree of belief obey?
E1
Apply the idea to a fresh example.
8 exercises
E2
Prove, derive or compute something not stated in the text.
3 exercises
E3
Work on a question the field does not fully settle.
1 exercise
c12
12. Averages, Spread and Surprises
How do you attach a number to an outcome?
E1
Apply the idea to a fresh example.
8 exercises
E2
Prove, derive or compute something not stated in the text.
3 exercises
E3
Work on a question the field does not fully settle.
1 exercise
c13
13. Estimating From Data
What makes one guess better than another?
E1
Apply the idea to a fresh example.
8 exercises
E2
Prove, derive or compute something not stated in the text.
3 exercises
E3
Work on a question the field does not fully settle.
1 exercise
c14
14. Lines, Curves and Boundaries
What does the best straight line mean?
E1
Apply the idea to a fresh example.
8 exercises
E2
Prove, derive or compute something not stated in the text.
3 exercises
E3
Work on a question the field does not fully settle.
1 exercise
c15
15. Judging a Model Honestly
How optimistic is a model about itself?
E1
Apply the idea to a fresh example.
8 exercises
E2
Prove, derive or compute something not stated in the text.
3 exercises
E3
Work on a question the field does not fully settle.
1 exercise
c16
16. Information and Compression
How much information is in one symbol?
E1
Apply the idea to a fresh example.
8 exercises
E2
Prove, derive or compute something not stated in the text.
3 exercises
E3
Work on a question the field does not fully settle.
1 exercise
c17
17. Going Downhill on Purpose
How does a gradient point to a better answer?
E1
Apply the idea to a fresh example.
8 exercises
E2
Prove, derive or compute something not stated in the text.
3 exercises
E3
Work on a question the field does not fully settle.
1 exercise
c18
18. Getting Gradients From a Computer
When do you use symbols, numbers or a program?
E1
Apply the idea to a fresh example.
8 exercises
E2
Prove, derive or compute something not stated in the text.
3 exercises
E3
Work on a question the field does not fully settle.
1 exercise
c19
19. Neural Networks: Simple Parts, Stacked
How does one unit draw a line?
E1
Apply the idea to a fresh example.
8 exercises
E2
Prove, derive or compute something not stated in the text.
3 exercises
E3
Work on a question the field does not fully settle.
1 exercise
c20
20. Training Deep Networks Without Breaking Them
Where does the gradient go?
E1
Apply the idea to a fresh example.
8 exercises
E2
Prove, derive or compute something not stated in the text.
3 exercises
E3
Work on a question the field does not fully settle.
1 exercise
c21
21. Attention, Images and Sequences
Why does looking at neighbours help?
E1
Apply the idea to a fresh example.
8 exercises
E2
Prove, derive or compute something not stated in the text.
3 exercises
E3
Work on a question the field does not fully settle.
1 exercise
c22
22. Making Pictures Out of Noise
What does it mean to learn a distribution?
E1
Apply the idea to a fresh example.
8 exercises
E2
Prove, derive or compute something not stated in the text.
3 exercises
E3
Work on a question the field does not fully settle.
1 exercise
c23
23. Learning by Acting
What is different about learning from reward?
E1
Apply the idea to a fresh example.
8 exercises
E2
Prove, derive or compute something not stated in the text.
3 exercises
E3
Work on a question the field does not fully settle.
1 exercise
c24
24. Scale, Language Models and What They Learned
How does a model learn to predict the next token?
E1
Apply the idea to a fresh example.
8 exercises
E2
Prove, derive or compute something not stated in the text.
3 exercises
E3
Work on a question the field does not fully settle.
1 exercise