Monthly Archives: March 2018

English version followsLorsque nous avons tabli notre sige Londres en 2010, nous voulions faire de DeepMind le nec plus ultra de la recherche de pointe dans le domaine de lintelligence artificielle. Nous voulions galement aider la communaut de lintelligence artificielle se dvelopper. Nous avons ainsi publi des articles dans les confrences et journaux les plus slectifs (plus de 180 ce jour!) et partag nos connaissances dans ce domaine; nous avons incit nos experts enseigner dans les universits locales, et uvr avec les coles et les ONG former la prochaine gnration de scientifiques. Nous avons eu non seulement la chance de contribuer au succs scientifique du Royaume-Uni, mais avons aussi grandement bnfici de louverture et de la diversit de cette ville ainsi que de son influence culturelle. Lintelligence artificielle doit tre dveloppe en accordant la plus grande attention aux diffrents besoins de la socit et pour autant quune ville puisse runir elle seule ces conditions une capitale multiculturelle comme Londres, ma ville natale, est cet gard lendroit idal. Je suis, donc, trs heureux dannoncer notre dcision douvrir notre premier laboratoire en Europe continentale, dans une autre grande capitale culturelle et scientifique: Paris.Read More

How did you learn to navigate the neighborhood of your childhood, to go to a friends house, to your school or to the grocery store? Probably without a map and simply by remembering the visual appearance of streets and turns along the way. As you gradually explored your neighborhood, you grew more confident, mastered your whereabouts and learned new and increasingly complex paths. You may have gotten briefly lost, but found your way again thanks to landmarks, or perhaps even by looking to the sun for an impromptu compass.Navigation is an important cognitive task that enables humans and animals to traverse, without maps, over long distances in a complex world. Such long-range navigation can simultaneously support self-localisation (I am here) and a representation of the goal (I am going there).In Learning to Navigate in Cities Without a Map,we present an interactive navigation environment that uses first-person perspective photographs from Google Street View,approved for use by the StreetLearn project and academic research, and gamify that environment to train an AI. As standard with Street View images, faces and license plates have been blurred and are unrecognisable. We build a neural network-based artificial agent that learns to navigate multiple cities using visual information (pixels from a Street View image).Read More

Through a humans eyes, the world is much more than just the images reflected in our corneas. For example, when we look at a building and admire the intricacies of its design, we can appreciate the craftsmanship it requires. This ability to interpret objects through the tools that created them gives us a richer understanding of the world and is an important aspect of our intelligence.We would like our systems to create similarly rich representations of the world. For example, when observing an image of a painting we would like them to understand the brush strokes used to create it and not just the pixels that represent it on a screen.In this work, we equipped artificial agents with the same tools that we use to generate images and demonstrate that they can reason about how digits, characters and portraits are constructed. Crucially, they learn to do this by themselves and without the need for human-labelled datasets. This contrasts with recent research which has so far relied on learning from human demonstrations, which can be a time-intensive process.Read More

Deep neural networks are composed of many individual neurons, which combine in complex and counterintuitive ways to solve a wide range of challenging tasks. This complexity grants neural networks their power but also earns them their reputation as confusing and opaque black boxes.Understanding how deep neural networks function is critical for explaining their decisions and enabling us to build more powerful systems. For instance, imagine the difficulty of trying to build a clock without understanding how individual gears fit together. One approach to understanding neural networks, both in neuroscience and deep learning, is to investigate the role of individual neurons, especially those which are easily interpretable.Our investigation intothe importance of single directions for generalisation, soonto appear at the Sixth International Conference on Learning Representations (ICLR), uses an approach inspired by decades of experimental neuroscience exploring the impact of damage to determine: how important are small groups of neurons in deep neural networks? Are more easily interpretable neurons also more important to the networks computation?Read More

I like to take things slow. Take it slowly and get it right first time, one participant said, but was quickly countered by someone else around the table: But Im impatient, I want to see the benefits now. This exchange neatly captures many of the conversations I heard at DeepMind Healths recent Collaborative Listening Summit. It also represents, in laymans terms, the debate that tech thinkers and policy-makers are having right now about the future of artificial intelligence.The Collaborative Listening Summit brought together members of the public, patient representatives and stakeholder, and was facilitated by Ipsos MORI. The objective of the Summit: to explore how principles, co-created in earlier events with the public, patients and stakeholders, should govern DeepMind Healths operating practices and engagement with the NHS. These principles ranged from the technical for example, how evidence should inform DeepMinds practice to the societal for example, operating in the best interests of society.The challenge of how technology companies and the NHS should interact has had many of us, including myself, cautious about the risk of big technology firms leveraging their finance and power over an NHS that is under seemingly endless pressure.Read More