Exercises

These exercises review the chapter as a whole. They mix small computations with the interpretation mistakes that often make ML losses and metrics confusing.

MATH-C11-C-001Exercise: Certain event

In bits, a fair coin has entropy 1.

How many bits of entropy does a certain event have?

Compute it first, then check your number.

MATH-C11-C-002Exercise: Joint entropy

If H(X) = 4 and H(Y | X) = 2, what is H(X, Y)?

Compute it first, then check your number.

MATH-C11-C-003Exercise: Negative log

In base 2, what is -log2(0.125)?

Compute it first, then check your number.

MATH-C11-C-004Exercise: Perplexity from bits

If average loss is 4 bits, what is perplexity?

Compute it first, then check your number.

MATH-C11-C-005Exercise: Mutual information

If H(Y) = 7 and H(Y | X) = 3, what is I(X;Y)?

Compute it first, then check your number.

MATH-C11-C-006Exercise: Cross-entropy target

For a one-hot target, cross-entropy reads the probability assigned to which class?

Answer it first, then check.

MATH-C11-C-007Exercise: KL symmetry

Is KL divergence generally symmetric?

Answer it first, then check.

MATH-C11-C-008Exercise: Perplexity comparison

Should perplexity values from different tokenizers be compared casually?

Answer it first, then check.

MATH-C11-C-009Exercise: Mutual information and cause

Does mutual information by itself prove causation?

Answer it first, then check.

MATH-C11-C-010Exercise: Next-token prediction

Can next-token prediction be read as classification over a vocabulary?

Answer it first, then check.

MATH-C11-C-011Exercise: Entropy and correctness

Enter 1 if a low-entropy prediction can still be wrong.

Compute it first, then check your number.

MATH-C11-C-012Exercise: Accuracy versus cross-entropy

Enter 1 if two correct predictions can have the same accuracy but different cross-entropy losses.

Compute it first, then check your number.

MATH-C11-C-013Exercise: KL reference view

Enter 1 if D_KL(p || q) measures mismatch from p's weighting view.

Compute it first, then check your number.

MATH-C11-C-014Exercise: Perplexity setup

Enter 1 if perplexity comparisons require compatible evaluation data and tokenization.

Compute it first, then check your number.

MATH-C11-C-015Exercise: Compression limit

Enter 1 if good compression or prediction is not by itself a full test of truthfulness, safety, or usefulness.

Compute it first, then check your number.

Next

Use the hints only after you have tried the exercises.