University of Cambridge > Talks.cam > Inference Group > Dynamical Networks for Agent Systems

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Dynamical Networks for Agent Systems

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.

Other lists

Baroness Lawrence of Clarendon Alison Richard Building (ARB), 7 West Road, 1st floor, Room 138, CB3 9DT U202 Meeting room, Department of Chemistry, Cambridge

Other talks

The Neurophenomenology of Surrender: Agency, Renewal, and Social Engagement in Speaking in Tongues Welcome Reception and Poster Session A Novel Diffusion Model based Approach for Sleep Music Generation Spectral theory for Dirac operators with singular potentials Title to be confirmed Carrollian momenta from anti de Sitter
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity