Timezone: »

Real-time interactive sequence generation with Recurrent Neural Network ensembles
Memo Akten

Tue Dec 06 09:00 AM -- 12:30 PM (PST) @ Area 5 + 6 + 7 + 8

The demonstration allows users to gesturally 'conduct' the generation of text. We propose a method of real-time continuous control and ‘steering’ of sequence generation using an ensemble of RNNs, dynamically altering the mixture weights of the models. We demonstrate the method using character based LSTM networks and a gestural interface allowing users to ‘conduct’ the generation of text.

Author Information

Memo Akten (Goldsmiths, University of London)

Artist working with computation as a medium, exploring collisions between nature, science, technology, culture, ethics, ritual, tradition and religion. Doing PhD at Goldsmiths UoL in artificial intelligence and expressive human-machine interaction - particularly realtime image and sound synthesis and expressive manipulation using deep learning.

More from the Same Authors