Advancing best-in-class massive fashions, compute-optimal RL brokers, and extra clear, moral, and truthful AI techniques
The thirty-sixth Worldwide Convention on Neural Data Processing Methods (NeurIPS 2022) is going down from 28 November – 9 December 2022, as a hybrid occasion, primarily based in New Orleans, USA.
NeurIPS is the world’s largest convention in synthetic intelligence (AI) and machine studying (ML), and we’re proud to assist the occasion as Diamond sponsors, serving to foster the alternate of analysis advances within the AI and ML group.
Groups from throughout DeepMind are presenting 47 papers, together with 35 exterior collaborations in digital panels and poster classes. Right here’s a short introduction to among the analysis we’re presenting:
Greatest-in-class massive fashions
Giant fashions (LMs) – generative AI techniques skilled on big quantities of knowledge – have resulted in unbelievable performances in areas together with language, textual content, audio, and picture era. A part of their success is right down to their sheer scale.
Nonetheless, in Chinchilla, we have now created a 70 billion parameter language model that outperforms many larger models, together with Gopher. We up to date the scaling legal guidelines of enormous fashions, displaying how beforehand skilled fashions had been too massive for the quantity of coaching carried out. This work already formed different fashions that comply with these up to date guidelines, creating leaner, higher fashions, and has received an Outstanding Main Track Paper award on the convention.
Constructing upon Chinchilla and our multimodal fashions NFNets and Perceiver, we additionally current Flamingo, a family of few-shot learning visual language models. Dealing with photographs, movies and textual information, Flamingo represents a bridge between vision-only and language-only fashions. A single Flamingo mannequin units a brand new cutting-edge in few-shot studying on a variety of open-ended multimodal duties.
And but, scale and structure aren’t the one elements which can be vital for the ability of transformer-based fashions. Information properties additionally play a big function, which we talk about in a presentation on data properties that promote in-context learning in transformer models.
Optimising reinforcement studying
Reinforcement studying (RL) has proven nice promise as an method to creating generalised AI techniques that may handle a variety of advanced duties. It has led to breakthroughs in lots of domains from Go to arithmetic, and we’re all the time on the lookout for methods to make RL brokers smarter and leaner.
We introduce a brand new method that enhances the decision-making talents of RL brokers in a compute-efficient manner by drastically expanding the scale of information available for their retrieval.
We’ll additionally showcase a conceptually easy but basic method for curiosity-driven exploration in visually advanced environments – an RL agent known as BYOL-Explore. It achieves superhuman efficiency whereas being strong to noise and being a lot easier than prior work.
From compressing information to operating simulations for predicting the climate, algorithms are a elementary a part of fashionable computing. And so, incremental enhancements can have an infinite influence when working at scale, serving to save vitality, time, and cash.
We share a radically new and extremely scalable technique for the automatic configuration of computer networks, primarily based on neural algorithmic reasoning, displaying that our extremely versatile method is as much as 490 instances quicker than the present cutting-edge, whereas satisfying the vast majority of the enter constraints.
Throughout the identical session, we additionally current a rigorous exploration of the beforehand theoretical notion of “algorithmic alignment”, highlighting the nuanced relationship between graph neural networks and dynamic programming, and the way greatest to mix them for optimising out-of-distribution efficiency.
On the coronary heart of DeepMind’s mission is our dedication to behave as accountable pioneers within the discipline of AI. We’re dedicated to growing AI techniques which can be clear, moral, and truthful.
Explaining and understanding the behaviour of advanced AI techniques is a vital a part of creating truthful, clear, and correct techniques. We provide a set of desiderata that capture those ambitions, and describe a practical way to meet them, which entails coaching an AI system to construct a causal mannequin of itself, enabling it to clarify its personal behaviour in a significant manner.
To behave safely and ethically on the planet, AI brokers should be capable to purpose about hurt and keep away from dangerous actions. We’ll introduce collaborative work on a novel statistical measure known as counterfactual harm, and reveal the way it overcomes issues with normal approaches to keep away from pursuing dangerous insurance policies.
Lastly, we’re presenting our new paper which proposes ways to diagnose and mitigate failures in model fairness caused by distribution shifts, displaying how vital these points are for the deployment of secure ML applied sciences in healthcare settings.
See the total vary of our work at NeurIPS 2022 here.