Seeing Is Believing: Brain-Inspired Modular Training for Mechanistic Interpretability
We introduce Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable. Inspired by brains, BIMT embeds neurons in a geometric space and augments the loss function with a cost proportional to the length of each neuron connection. This is inspired by t...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Published: |
Multidisciplinary Digital Publishing Institute
2024
|
| Online Access: | https://hdl.handle.net/1721.1/153423 |