Dynamical Networks for Agent Systems
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact Phil Cowans.
The basic ideas for a novel class of recurrent neural networks that learn through active interaction with an unknown environment by reading
data and reward information and by emitting actions through its I/O
interface. The network’s connections are fixed and no weights need to be adjusted. A neuron’s activity is determined by one of two possible boolean gates. Starting out with a uniform distribution over the two gates, learning consists in assigning a gate to each neuron as evidence is gathered, thus “programming” the network on-the-fly.
This talk is part of the Inference Group series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|