SpeakerStew: Scaling to Many Languages with a Triaged Multilingual Text-Dependent and Text-Independent Speaker Verification System I’ll share system design and research I’ve been working on recently as part of the Speaker, Voice & Language team at Google NYC. It has […]
Data-driven approaches to self-driving Self-driving technology promises to improve safety on roads, reduce costs of transportation, and, last but not least, save us a lot of time behind the wheel. Even though first real-world deployments exist, the technology is still […]
Everything is Connected (especially Planning) Autonomous vehicle (AV) software stacks often form a feed-forward pipeline of components: perception to prediction and then planning. Such architectures help to “divide and conquer” the difficult problem of autonomous driving, where each component can […]
Hindsight Off-policy Options – Disentangling Abstractions in the Option Framework Deep reinforcement learning has seen numerous successes in recent years (e.g. Go, Chess, Atari, StarCraft), but still faces challenges in domains with limited data access. We will discuss the perspective […]
The Learner’s Bug Spotter, or how to spot bugs in source code. Learning to program is fun and rewarding, but it also can be frustrating when we are stuck on a hard to find bug. Automated tests can tell if […]
Gait laboratory in your pocket: Measuring disease progression from single-camera videos. Recent achievements in machine learning are subverting foundations of many research disciplines. In this presentation, I will show how these developments affect collection, modeling and prediction of human movement, […]
Rethinking Attention with Performers – Towards New Transformers’ Revolution. Transformers took the field of machine learning by storm, marking the eclipse of LSTM architectures in Natural Language Processing and becoming the golden standard for dealing with generic sequential data. Despite […]
Towards multi-agent emergent communication as a building block of human-centric AI. The ability to cooperate through language is a defining feature of humans. As the perceptual, motory and planning capabilities of deep artificial networks increase, researchers are studying whether they […]
Reformer: The Efficient Transformer Transformer models have been used in a variety of fields and yield great results on many NLP tasks. But between the BERT, GPT-3, and many other variants, they can be inefficient and it can be hard […]
Language Models Are Few-shot learners In my talk, I’ll try to familiarize listeners with what a GPT-3 is, what it can and can’t do, and what, as a research community, we can learn from it. I’ll start by analyzing research […]
