All outcomes
Skills

Derive the Linear Algebra Behind Machine Learning

8 weeks · 0 milestones

Produce hand-derived solutions to 20 exercises spanning matrix operations (multiplication, inversion, transposition), eigendecomposition, singular value decomposition, and PCA derivation — all derivations must be symbolic or hand-worked (no NumPy for the derivation steps, only for verification afterwards). The work must show the derivation reasoning, not just the result. Proof: the solutions reviewed by a maths lecturer or ML researcher who presents 2–3 unseen problems during the review session — you must work through them live and explain your reasoning at each step, not just produce an answer.

Milestone map

Milestone map

3 milestones

Master Vectors, Matrices, and Linear Transformations

10–16 weeks

Study the foundations of linear algebra for machine learning: vector spaces, matrix operations, linear transformations, eigenvectors and eigenvalues, and matrix decompositions (LU, QR, SVD). Complete at least twenty exercises from MIT OCW 18.06 or equivalent, working through the derivations — not just applying formulas. Implement SVD from scratch using the power iteration method.

Proof required

Submit: a typed solution set for at least twenty problems from MIT OCW 18.06 problem sets (or equivalent) with all steps shown; a public GitHub repository (or Colab notebook) containing your SVD implementation using power iteration with a test comparing your output to NumPy's SVD; and a 200-word explanation of why SVD is used in dimensionality reduction. A mathematician, CS lecturer, or ML researcher must confirm the solutions and implementation are correct.

What gets checked

  • At least twenty problem set solutions with all derivation steps shown — not just final answers
  • SVD implementation produces output matching NumPy's SVD within numerical tolerance on the same input
  • A mathematician, CS lecturer, or ML researcher has confirmed the solutions and implementation are correct

Common mistakes

  • Using NumPy for the SVD computation — the proof requires implementing power iteration, not calling numpy.linalg.svd
  • Problem set solutions with only final answers and no derivation steps — the proof requires showing the work

Resources

Foundationstart here

Depthgo deeper

What a verifier looks for

  • Are at least twenty problem solutions shown with all derivation steps — not just final answers?
  • Does the SVD implementation produce output matching NumPy's SVD within numerical tolerance?
  • Ask: 'why does PCA use SVD rather than eigendecomposition directly on the data matrix?' — tests deeper understanding

Apply Linear Algebra to ML Algorithm Derivations

8–12 weeks (after milestone 1)

Derive the closed-form solution to linear regression using the normal equations (showing the matrix derivation step by step). Derive the gradient of the cross-entropy loss for logistic regression using matrix calculus. Implement PCA from scratch using SVD and verify it against scikit-learn's PCA on a real dataset.

Proof required

Submit: a typed derivation of the linear regression normal equations (matrix calculus steps, not just the final formula); a typed derivation of the logistic regression cross-entropy gradient; and a public GitHub repository (or Colab) containing your PCA implementation with a comparison to scikit-learn's PCA showing the explained variance ratios match. A mathematician or ML researcher must confirm the derivations are correct.

What gets checked

  • Normal equations derivation shows all matrix calculus steps — not just the final (XᵀX)⁻¹Xᵀy formula
  • PCA implementation produces explained variance ratios matching scikit-learn's PCA within numerical tolerance
  • A mathematician or ML researcher has confirmed the derivations are correct

Common mistakes

  • Normal equations derivation that starts from the formula without showing the matrix calculus derivation
  • PCA implementation that uses scikit-learn for the core computation — must use SVD directly

Resources

Foundationstart here

Depthgo deeper

What a verifier looks for

  • Does the normal equations derivation show all matrix calculus steps — not just the formula?
  • Does the PCA implementation match scikit-learn's explained variance ratios?
  • Ask: 'what happens to the normal equations when XᵀX is not invertible?' — tests understanding of rank deficiency

Present Linear Algebra for ML to an Expert Reviewer

2–4 weeks (after milestone 2)

Present your derivations and implementations to a mathematician or ML researcher in a live technical review. The reviewer will pose at least two questions about the mathematical properties of the algorithms you implemented — questions you must answer using the linear algebra concepts, not just code recall.

Proof required

Submit: a recording or transcript of a live review with a mathematician or ML researcher; your derivation documents and implementation repository as the basis for the review; and documentation of at least two questions posed during the review and your responses.

What gets checked

  • Review was live — not an async written exchange
  • At least two mathematical questions were posed about the algorithms' properties — not just the implementations
  • Your responses used linear algebra concepts specifically — not just code-level descriptions

Common mistakes

  • Live review that becomes a code walkthrough without mathematical questions
  • Responses that describe what the code does rather than using linear algebra concepts to explain the algorithm

Resources

Foundationstart here

Depthgo deeper

What a verifier looks for

  • Was the review live — not async?
  • Were at least two mathematical questions about algorithm properties posed?
  • Did the responses use linear algebra concepts — not just code-level descriptions?

We use analytics to improve Powstik. No ads, ever.