UCL ELLIS

Speaker	Alex Graves
Affiliation	Google Deepmind
Date	Friday, 25 April 2014
Time	13:00-14:00
Location	Zoom
Link	Malet Place Engineering Building 1.02
Event series	Jump Trading/ELLIS CSML Seminar Series
Abstract	Generating sequential data is the closest computers get to dreaming. Digital dreams are likely to play a crucial role in the future of AI, by helping agents to simulate, predict and interpret their surroundings. This talk shows how Long Short-term Memory recurrent neural networks can be used to generate complex sequences with large-scale structure, simply by predicting one step at a time. The method is demonstrated for character-level language modelling (where the data are discrete) and speech and handwriting generation (where the data are real-valued). A novel extension allows the network to condition its predictions on an auxiliary input sequence, making it possible to speak or write specific texts.
Biography