Dr Marc Lanctot, a research scientist with Google DeepMind, will visit the University to discuss AlphaGo, the computer programme developed by Google DeepMind to play the board game Go.
Go is a complex board game that requires intuition, creative and strategic thinking and has long been considered a difficult challenge in the field of artificial intelligence (AI) due to the inherent complexity arising from its large branching factor.
However, recently AlphaGo became the first computer programme to beat a human professional at the game.
Dr Lanctot’s talk will look at the new approach used by AlphaGo which combines deep learning from expert play and self play reinforcement learning of a `value network’ to evaluate positions.
He will also discuss the recent landmark match where AlphaGo beat the South Korean professional Go player Lee Sedol in four out of five games. The match has been compared with the historic chess match between Deep Blue and Garry Kasparov in 1997.
`AlphaGo: Mastering the game of Go with deep neural networks and tree search’ will take place on Tuesday, 19 April at 1pm in the Leggate Theatre in the Victoria Gallery & Museum. No booking is required.
You can find a schedule of upcoming seminars from the Department of Computer Science here: http://intranet.csc.liv.ac.uk/research/seminars/