Biology and neural networks
So many similarities
- Information is contained in the connections
- Network learns to perform specific functions
- Network generalizes to new inputs
But NN are woefully inadequate compared with biology
- Need implausible learning rules
- Hard to train large networks
- Network construction is a heuristic art
One obvious difference: Spike representation
- Recent models (Hopfield, Maass, others) explore spikes
- More about this next week