mlg.eng.cam.ac.uk
Zoubin Ghahramani
http://mlg.eng.cam.ac.uk/zoubin
Professor of Information Engineering. And Founding Executive Board Member. Gatsby Computational Neuroscience Unit. Machine Learning Group @ Cambridge. Former Students and Postdocs. Matthew W. Hoffman. Research Areas and Papers by Topic. Publications see the Machine Learning Group Publications Webpage. 2013 Machine Learning Summer School Lectures, Tuebingen on probabilistic modelling and Bayesian inference (videos and slides). 2012 Machine Learning Summer School Lectures, La Palma: Bayesian Modelling.
magenta.tensorflow.org
Tuning Recurrent Neural Networks with Reinforcement Learning
https://magenta.tensorflow.org/2016/11/09/tuning-recurrent-networks-with-reinforcement-learning
Tuning Recurrent Neural Networks with Reinforcement Learning. Nov 9, 2016. We are excited to announce our new RL Tuner algorithm. A method for enchancing the performance of an LSTM trained on data using Reinforcement Learning (RL). We create an RL reward function that teaches the model to follow certain rules, while still allowing it to retain information learned from data. We use. When I joined Magenta. Is conceptually similar to a. Music is an interesting test-bed for sequence generation, in that music...