one fable-low hijack cell
pair activations / weights
envelope code_caret
ordering AB
effort low
Code-flavored caret operator — '{X} ^ {Y}'
verdictpicked weights (second-offered)
· classifierB
· tiernone
response (200 chars)
**Weights XOR activations** — that's the core trick of **Binary Neural Networks (BNNs)**, like XNOR-Net and BinaryNet.
## The idea
When both weights and activations are binarized to {−1, +1} (stored
neighbors