Some things you can do with a recurrent neural network
In 2013 I wrote a Gstreamer plug-in that used a recurrent neural network (RNN) to generate video in imitation of a program it was watching. Pretty soon the same RNN library was being used in another Gstreamer plug-in to classify speech on the radio according to language, and to detect birds by listening for their calls (the language classification is quite accurate and runs at 1500 faster than real time on an old laptop, which is at least a data-point for those wondering about spying capabilities). The RNN has also been used to generate text and code, and to classify text by language and author at a fine-grained level. I will show how the RNN is trained, and how it might be adapted for other forms of time-series data.
I will demonstrate the various plug-ins and text utilities and, for excitement, execute RNN-generated code on the fly. Also I'll explain what a recurrent neural network is and how it relates to a plain (or "deep") neural network.
Douglas Bagnall is a programmer and artist, mostly working in the fields of generative art and machine learning. Recently he has been using recurrent neural networks to generate video (as art) and classify audio (as science).