A signal with weight behind it

What can one weighted signal separate?

Make your own investigation

Compare a single threshold with a two-hidden-unit network on all four XOR inputs.

One unit thresholds a weighted sum. The two-unit network computes OR and NAND, then ANDs their outputs.

Case cards

Cut these cards apart. Use the original example first, then let a partner supply a changed case. Keep sealed/final cards with the teacher until the learner commits a rule.

Case 1

Input A: 0

Input B: 0

Expected XOR: 0

My prediction and reason:

Case 2

Input A: 0

Input B: 1

Expected XOR: 1

My prediction and reason:

Case 3

Input A: 1

Input B: 0

Expected XOR: 1

My prediction and reason:

Case 4

Input A: 1

Input B: 1

Expected XOR: 0

My prediction and reason:

What this cannot establish

The hand-designed XOR network demonstrates representation capacity, not a training result.