12 · Wrap-Up and Take-Homes
The close of Tensors for Machine Learning. This section has two jobs: connect the ideas from all thirteen sections, and hand you the extensions.
One idea connects sections 07, 09 and 10: when a problem has no exact answer and no true inverse, you do not give up. You find the best stable approximation instead.
You watch it happen three times — the pseudoinverse on two columns that are copies of each other in section 07, Tucker on the taxi tensor in section 10, and Richardson-Lucy on a blurred photograph in deep dive 13.
The five take-homes are Appendices A to E, all in notebook 12: PCA, attention, CP, Cholesky and audio denoising. The four deep dives opened live — 13 (convolution and deconvolution, with Appendix F), 14 (CP), 17 (attention) and 20 (AlphaTensor) — each go well past the route the room worked.
Study here, then run the real thing: notebook 12 on Colab · deck 13, convolution and deconvolution · the handbook
Built from the workshop’s own material by Ravi Kalia and Sebastian Laverde Chunza, CC BY 4.0.
Your path through this unit
Step 1 of 3
Initial review
Take a first look at each topic and tick Got it once you have the general idea.