Between 30 April and 03 May, hundreds of researchers and engineers will gather in Vancouver, Canada, for the Sixth International Conference on Learning RepresentationsHere you can read details of all DeepMinds accepted papers and find out where you can see the accompanying poster sessions and talks. Maximum a posteriori policy optimisationAuthors: Abbas Abdolmaleki, Jost Tobias Springenberg, Nicolas Heess, Yuval Tassa, Remi MunosWe introduce a new algorithm for reinforcement learning called Maximum a posteriori Policy Optimisation (MPO) based on coordinate ascent on a relative entropy objective. We show that several existing methods can directly be related to our derivation. We develop two off-policy algorithms and demonstrate that they are competitive with the state-of-the-art in deep reinforcement learning.Read More
Making Alexa more friction-free
This morning, I am delivering a keynote talk at the World Wide Web Conference in Lyon, France, with the title, Conversational AI for Interacting with the Digital and Physical World.Read More
Alexa scientists present two new techniques that improve wake word performance
The Amazon Echo is a hands-free smart home speaker you control with your voice. The first important step in enabling a delightful customer experience with an Echo or other Alexa-enabled device is wake word detection, so accurate detection of “Alexa” or substitute wake words is critical. It is challenging to build a wake word system with low error rates when there are limited computation resources on the device and it’s in the presence of background noise such as speech or music.Read More
Our first COO Lila Ibrahim takes DeepMind to the next level
One of the greatest pleasures of coming to work every day at DeepMind is the chance to collaborate with brilliant researchers and engineers from so many different fields and perspectives – with machine learning experts alongside neuroscientists, physicists, mathematicians, roboticists, ethicists and more.This level of interdisciplinary collaboration is both challenging and unusual, and it requires a unique type of organisation. We built DeepMind to combine the rigour and long-term thinking of the worlds best scientific institutions, along with the focus, pace and energy common to the best tech startups. I believe this is essential if were to fulfil the scientific and social promise of AI, and Im proud of all thatweve achieved so far. But theres still a very long way to go!So Im really pleased to welcome Lila Ibrahim to DeepMind as our first ever Chief Operating Officer, partnering with me to design, build and manage our next phase of growth. Having started out as a microprocessor designer and assembler programmer at Intel, Lila went on to lead the companys emerging markets product group, as well as working with Intel CEO Craig Barrett and then the legendary investor John Doerr at Kleiner Perkins as Chief of Staff.Read More
Alexa scientists address challenges of end-pointing
Just as Alexa can wake up without the need to press a button, she also automatically detects when a user finishes her query and expects a response. This task is often called “end-of-utterance detection,” “end-of-query detection,” “end-of-turn detection,” or simply “end-pointing.”Read More