DeepMind papers at ICLR 2018
Between 30 April and 03 May, hundreds of researchers will gather in Vancouver, Canada, for the Sixth International Conference on Learning Representations. Here you will find details of all DeepMind’s accepted papers.
作者：DeepMind 来源：DeepMind
发布时间：2018-04-26 20:17:00
Taking DeepMind to the next level: welcoming Lila Ibrahim as our first Chief Operating Officer
We are pleased to welcome Lila Ibrahim to DeepMind as our first ever Chief Operating Officer. Lila will help design, build and manage our next phase of growth.
作者：DeepMind 来源：DeepMind
发布时间：2018-04-11 21:00:00
Blockchain is not only crappy technology but a bad vision for the future
Blockchain is not only crappy technology but a bad vision for the future. Its failure to achieve adoption to date is because systems built…
作者：Kai Stinchcombe 来源：medium
发布时间：2018-04-10 00:33:54
How Does Spotify Know You So Well?
A software engineer explains the science behind personalized music recommendations
作者：Sophia Ciocca 来源：medium
发布时间：2018-04-06 01:44:52
Intuitively Understanding Variational Autoencoders
And why they’re so useful in creating your own generative text, art and even music
作者：Irhum Shafkat 来源：medium
发布时间：2018-04-05 22:44:46
Learning to navigate in cities without a map
Navigating through unstructured environments is a basic capability of intelligent creatures, and thus is of fundamental interest in the study and development of artificial intelligence. Building upon recent research that applies deep reinforcement learning to maze navigation problems, we present an end-to-end deep reinforcement learning approach that can be applied on a city scale. We present an interactive navigation environment that uses Google Street View for its photographic content and worldwide coverage, and demonstrate that our learning method allows agents to learn to navigate multiple cities and to traverse to target destinations that may be kilometres away.
作者：DeepMind 来源：DeepMind
发布时间：2018-03-29 23:00:00
Retour à Paris / A return to Paris
We're delighted to announce the opening of our first research lab in continental Europe, DeepMind Paris, which will be led by Remi Munos - one of DeepMind’s principal research scientists and author of 150 research papers. The blog is available in French and English.
作者：DeepMind 来源：DeepMind
发布时间：2018-03-29 14:00:00
Learning to write programs that generate images
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.
作者：DeepMind 来源：DeepMind
发布时间：2018-03-27 23:00:00
Understanding deep learning through neuron deletion
Deep neural networks are composed of many individual neurons, which combine in complex and counterintuitive ways to solve challenging tasks, ranging from machine translation to Go. 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.
作者：DeepMind 来源：DeepMind
发布时间：2018-03-22 00:00:00
Stop, look and listen to the people you want to help
Harry Evans, researcher at The King's Fund, writes on his experience attending the Collaborative Listening Summit - run by DeepMind Health and Ipsos MORI on Wednesday 31st January 2018.
作者：DeepMind 来源：DeepMind
发布时间：2018-03-06 20:00:00
Learning by playing
Our new paper proposes a new learning paradigm called ‘Scheduled Auxiliary Control (SAC-X)’ which seeks to overcome the issue of exploration in control tasks. SAC-X is based on the idea that to learn complex tasks from scratch, an agent has to learn to explore and master a set of basic skills first. Just as a baby must develop coordination and balance before she crawls or walks—providing an agent with internal (auxiliary) goals corresponding to simple skills increases the chance it can understand and perform more complicated tasks.
作者：DeepMind 来源：DeepMind
发布时间：2018-02-28 20:00:00
Researching patient deterioration with the US Department of Veterans Affairs
We’re excited to announce a medical research partnership with the US Department of Veterans Affairs (VA), one of the world’s leading healthcare organisations responsible for providing high-quality care to veterans and their families across the United States.
作者：DeepMind 来源：DeepMind
发布时间：2018-02-23 01:00:00
Importance Weighted Actor-Learner Architectures: Scalable Distributed DeepRL in DMLab-30
Our latest paper introduces IMPALA (Importance-Weighted Actor-Learner), a new and efficient distributed architecture capable of solving many tasks at the same time. We also introduce DMLab-30, a new set of visually-unified environments designed to test IMPALA and other architectures.
作者：DeepMind 来源：DeepMind
发布时间：2018-02-05 22:52:00
Learning explanatory rules from noisy data
Our new paper, recently published in JAIR, demonstrates it is possible for systems to combine intuitive perceptual with conceptual interpretable reasoning. The system we describe, ∂ILP, is robust to noise, data-efficient, and produces interpretable rules.
作者：DeepMind 来源：DeepMind
发布时间：2018-01-29 22:00:00
Open-sourcing Psychlab
Understanding an agent’s specific cognitive skill set may prove useful for improving its overall performance, but the complexity of a tasks in AI research can often make it difficult to tease apart individual skills. We believe it is possible to draw on experimental methods from fields like cognitive psychology to better understand the behaviours of artificial agents. That is why we developed Psychlab, a platform built on top of DeepMind Lab, which allows us to directly apply methods from these fields to study behaviours of artificial agents in a controlled environment. We are also open-sourcing this platform for others to use.
作者：DeepMind 来源：DeepMind
发布时间：2018-01-26 21:00:00
