08 · Recursion with Matrices and Vectors

Part IV demo of Tensors for Machine Learning. One simple pattern:

Use the current state to create the next state, then repeat.

The same pattern appears in Fibonacci numbers, in power iteration, and in a real monthly airline-passenger forecast. The last of those combines recursion with the pseudoinverse from section 07 — fit a model that predicts each month from the previous 12, then apply it to its own output.

This is exactly the structure of a recurrent neural network: a hidden state, updated by the same weights at every step.

Study here, then run the real thing: notebook 08 on Colab · the handbook · workshop home

Built from the workshop’s own material by Ravi Kalia and Sebastian Laverde Chunza, CC BY 4.0.

6 topics1 tag

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.

08 · Recursion with Matrices and Vectors

Your path through this unit

Initial review

Mistake: a small one-step error stays small

Fibonacci as a matrix state

Power iteration

This is a recurrent neural network

Forecasting real airline traffic

State, update rule, recursion