University of Cambridge > Talks.cam > Churchill CompSci Talks > Neuroevolution & NEAT

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

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

ℹī¸ Information

Neuroevolution & NEAT

Download to your calendar using vCal

If you have a question about this talk, please contact Matthew Ireland .

Neural Networks are very useful for machine learning. But how do we generate them? There are many many different ways to do this, but one that is increasingly being talking about is neuroevolution. In neuroevolution, we combine the ideas of neural networks with evolutionary algorithms. This talk discusses the idea of neuroevolution, as well as going into depth on one such neuroevolutionary method, NEAT . NEAT stands for NeuroEvolution of Augmenting Topologies, and it lets us evolve different structures of neural networks, not just the weights of the network.

This talk is part of the Churchill CompSci Talks series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Human Enhancement Cambridge Consultants Ltd, Science Park, Milton Road, Cambridge CB4 0DW Biophysical Techniques Lecture Series 2020

Other talks

Paediatric Medicine and Rheumatology Machine Learning for Spectral Geometry and Vice Versa Group Work Optimal metric and approximation of free boundary minimal surfaces Christmas Social Evening & Annual General Meeting Title to be confirmed
 

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