Posts in category: Deepmind

We apply a generative segmental model of task structure, guided by narration, to action segmentation in video. We focus on unsupervised and weakly-supervised settings where no action labels are known during training. Despite its simplicity, our model performs competitively with previous work on a dataset of naturalistic instructional videos.Read More

Specification gaming is a behaviour that satisfies the literal specification of an objective without achieving the intended outcome. We have all had experiences with specification gaming, even if not by this name. Readers may have heard the myth of King Midas and the golden touch, in which the king asks that anything he touches be turned to gold – but soon finds that even food and drink turn to metal in his hands. In the real world, when rewarded for doing well on a homework assignment, a student might copy another student to get the right answers, rather than learning the material – and thus exploit a loophole in the task specification.Read More

Under a microscope, a pane of window glass doesnt look like a collection of orderly molecules, as a crystal would, but rather a jumble with no discernable structure. Glass is made by starting with a glowing mixture of high-temperature melted sand and minerals. Once cooled, its viscosity (a measure of the friction in the fluid) increases a trillion-fold, and it becomes a solid, resisting tension from stretching or pulling. Yet the molecules in the glass remain in a seemingly disordered state, much like the original molten liquid almost as though the disordered liquid state had been flash-frozen in place. The glass transition, then, first appears to be a dramatic arrest in the movement of the glass molecules. Whether this process corresponds to a structural phase transition (as in water freezing, or the superconducting transition) is a major open question in the field. Understanding the nature of the dynamics of glass is fundamental to understanding how the atomic-scale properties define the visible features of many solid materials.Read More

The Atari57 suite of games is a long-standing benchmark to gauge agent performance across a wide range of tasks. Weve developed Agent57, the first deep reinforcement learning agent to obtain a score that is above the human baseline on all 57 Atari 2600 games. Agent57 combines an algorithm for efficient exploration with a meta-controller that adapts the exploration and long vs. short-term behaviour of the agent.Read More

Our goal is to use visual grounding to improve unsupervised word mapping between languages. The key idea is to establish a common visual representation between two languages by learning embeddings from unpaired instructional videos narrated in the native language.Read More

This blog introduces a new long-range memory model, the Compressive Transformer, alongside a new benchmark for book-level language modelling, PG19. We provide the conceptual tools needed to understand this new research in the context of recent developments in memory models and language modelling.Read More

A recent development in computer science may provide a deep, parsimonious explanation for several previously unexplained features of reward learning in the brain.Read More

Our Nature paper describes AlphaFold, a system that generates3D models of proteins that are far more accurate than any that have come before.Read More

This paper looks at philosophical questions that arise in the context of AI alignment. It defends three propositions. First, normative and technical aspects of the AI alignment problem are interrelated, creating space for productive engagement between people working in both domains. Second, it is important to be clear about the goal of alignment. There are significant differences between AI that aligns with instructions, intentions, revealed preferences, ideal preferences, interests and values. A principle-based approach to AI alignment, which combines these elements in a systematic way, has considerable advantages in this context. Third, the central challenge for theorists is not to identify ‘true’ moral principles for AI; rather, it is to identify fair principles for alignment, that receive reflective endorsement despite widespread variation in people’s moral beliefs. The final part of the paper explores three ways in which fair principles for AI alignment could potentially be identified.Read More

Screening mammography aims to identify breast cancer before symptoms appear, enabling earlier therapy for more treatable disease. Despite the existence of screening programs worldwide, interpretation of these images suffers from suboptimal rates of false positives and false negatives. Here we present an AI system capable of surpassing a single expert reader in breast cancer prediction performance.Read More