11.4b Graphical deep-net labs

Source: Lab ideas from Computational Physics (Landau, Páez, Bordeianu), §11.3. Original drills. Continues 11.4.

Explorer

Pure Python.

Formula refresh

Warm up: pick the matching equation among lookalikes (same walk as the theory lesson).

Labs

Activity: $(-1)(1)+(1)(1)$

Print the vertical-detector weighted sum with 10 decimals.

No input.

Write-ups

0/2 solved

11.4b.W1

Using “hierarch”, “layer”, and “feature”, explain:

Why does a deep net for line orientation use several hidden layers instead of one giant layer of pixel weights?

Minimum 3 words. Your answer must include: “hierarch”, “layer”, “feature”.

0 words/ 3 min

Meet the writing requirements, then you can open the model answer.

Next: 11.5 Machine learning software.