Skip to yearly menu bar Skip to main content


Real-time interactive sequence generation with Recurrent Neural Network ensembles

Memo Akten

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.

Live content is unavailable. Log in and register to view live content