DeepMindThere's still time to apply to @Khipu_AI, an AI teaching conference designed to help strengthen the AI community across Latin America. There's a fantastic line up of speakers and scholarships are available. Apply before June 28
We introduce a framework for continual learning based on Bayesian inference
over the function space rather than the parameters of a deep neural network.
This method, referred to as functional regularisation for continual learning,
DeepMindNeural networks suffer from catastrophic forgetting when tasks are encountered sequentially. We overcome this by Bayesian inference in function space, using inducing point sparse GP methods and by optimising over rehearsal data points: arxiv.org/abs/1901.11356pic.twitter.com/lMvXZxPG7r
Meta-learning methods leverage past experience to learn data-driven inductive
biases from related problems, increasing learning efficiency on new tasks. This
ability renders them particularly suitable for sequential decision making with
DeepMindCongratulations to @natashajaques and @DeepMindAI colleagues, whose paper 'Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning' received an Honourable Mention @icmlconf 2019!
DeepMindHow do you get an agent to build complex structures out of blocks? Come see our answer on Wednesday at #ICML2019 from 11:40am-12pm in Hall B & during posters! We use 3 key ingredients: structured policies, object-centric actions, & model-based planning.
DeepMind#ICML2019 - the Thirty-sixth International Conference on Machine Learning - begins today! Come say hello at our stand any time this week.
We’re kicking off w/ a tutorial on Safe Machine Learning @ 9:15am in Room 104, with @csilviavr and @janleike
In optimization the duality gap between the primal and the dual problems is a
measure of the suboptimality of any primal-dual point. In classical mechanics
the equations of motion of a system can be derived from the Hamiltonian
function, which is a...
Research to keep AI reliable is no more a side-project in AI design than keeping a bridge standing is a side-project in bridge design.
DeepMindDeepMind’s @pushmeet spoke to @80000Hours about the importance of building robust and safe AI systems.
Listen to the full podcast to find out why a career in machine learning makes a difference
Mastering the strategy, tactical understanding, and team play involved in multiplayer video games represents a critical challenge for AI research. In our latest paper now published in the journal Science, we present new developments in reinforcement...
Artificially intelligent agents are getting better and better at two-player games, but most real-world endeavors require teamwork. Jaderberg et al. designed a computer program that excels at playing the video game Quake III Arena in Capture the Flag...
With a view to bridging the gap between deep learning and symbolic AI, we
present a novel end-to-end neural network architecture that learns to form
propositional representations with an explicitly relational structure from raw
pixel data. In order...
DeepMindMicroNet Challenge @NeurIPSConf 2019: the networks we build are dictated by the hardware we have, and the hardware that gets built is informed by the networks we have. Help break the wheel—build networks that influence the design of future hardware!
Large scale deep learning excels when labeled images are abundant, yet
data-efficient learning remains a longstanding challenge. While biological
vision is thought to leverage vast amounts of unlabeled data to solve
classification problems with...