Top 3 Takeaways from Deep Learning Summit SF 2022

2022 was a big year for Artificial Intelligence. RE•WORK held over 10 events around the world which brought together some of the best and brightest minds in the AI/ML industry. One of the flagship RE•WORK events is Deep Learning Summit, San Francisco. Here's a look at the top 3 presentations from 2022's edition:

1. Danny Lang: Learning from Multi-Agent, Emergent Behaviors in a Simulated Environment

A revolution in reinforcement learning is happening, one that helps companies harness the more diverse, complex, virtual simulations available to accelerate the pace of innovation. Join this session to learn about particular environments already created that have yielded surprising advances in AI agents, and to better understand how emergent behaviors and open-endedness in multi-agent systems can lead to the most optimal designs and real-world practices.

2. Maithra Raghu: Do Transformers See Like Convolutional Neural Networks?

Deep learning capabilities have arguably entered a new stage since around 2020. These new capabilities also rely on new design principles, with self-supervision, large-scale pretraining, and transfer learning all playing central roles. Perhaps most strikingly, this new stage of deep learning makes critical use of Transformers. Initially developed for machine translation tasks, then rapidly adopted across different NLP tasks, Transformers have recently shown superior performance to Convolutional Neural Networks (CNNs) on a variety of computer vision tasks.

As CNNs have been the de-facto model for visual data for almost a decade, this gives rise to a fundamental question: how are Transformers solving visual tasks, and what can we learn about their successful application? In this talk, I present results providing answers to these questions. I overview key differences in image representations in Transformers and CNNs and reveal how these arise from the differing functions of self-attention vs convolutions. I highlight connections between pretraining and learned representations, and explore ramifications for transfer learning and the role of scale in performance.

3. Daniel Wu: XRL - Explainable Reinforcement Learning in a Nutshell

Thanks to the encouraging advancement in machine learning technology, AI has become more ubiquitous in our daily lives. From task automation, decision-making, cost optimization, human augmentation, and medical diagnosis to autonomous driving and robotics, AI is realizing its promise to greatly enhance efficient decision-making. Given our increasing dependency on AI and systems, it is paramount to ensure AI development adheres to the principles of responsible AI.

Explainability is one such foundational principle of responsible AI. In the reinforcement learning setting where intelligent agents learn by themselves with little human intervention, explainability is even more important in establishing trust and confidence with the users. This talk aims to provide an overview of XRL and a brief survey of XRL techniques.

Interested in joining us for Deep Learning Summit SF 2023? The eighth annual edition is taking place on February 15-16, 2023, at Hotel Kabuki, in San Francisco, CA. This 2-in-1 summit includes access to Deep Learning Summit and Enterprise AI Summit.

Interested in learning more about what to expect at Deep Learning Summit SF 2023?  Download the Event Brochure Here

Looking to join us for groundbreaking sessions, countless networking opportunities, and sessions by some of the Top Senior Executive Leaders in AI? Register for Your Pass Here