TOPBOTS Guide to NeurIPS 2020

This year’s Annual Conference on Neural Information Processing (NeurIPS 2020) is held 100% virtually from December 6th to 12th, 2020. 

Historically NeurIPS sells out quickly and can be a challenge to register for. But, this year’s virtual format welcomes everyone with an affordable ticket price of $100.

2020 is our third year of TOPBOTS covering the conference. To make your virtual NeurIPS experience easier, we’ve prepared this guide about the talks, workshops, and tutorials we are most excited about. 

If you’d like to skip around, here is the table of contents:

• Keynote Speakers at NeurIPS 2020
• NeurIPS 2020 Workshops
• Tutorials to Join at NeuriPS 2020
• Top Research Papers from 2020 

Our team has also reviewed the papers accepted to NeurIPS 2020 and shortlisted the most interesting ones across different research areas. Here are the topics we cover:

• Natural Language Processing & Conversational AI
• Computer Vision
• Reinforcement Learning & More
• Tackling COVID-19 with AI & Machine Learning

Keynote speakers at NeurIPS 2020

As usually, keynote presentations are held by recognized experts with diverse backgrounds.

Charles Isbell

Dean of the College of Computing at the Georgia Institute of Technology

You Can’t Escape Hyperparameters and Latent Variables: Machine Learning as a Software Engineering Enterprise

In this talk, Charles will argue for adopting systematic approaches for creating robust artifacts that contribute to larger systems and consequently, impact the real human world. He will also explore scientifically interesting problems that result from moving beyond narrow machine-learning algorithms to complete machine-learning systems.

Jeff Shamma

Director of the Center of Excellence for NEOM Research at KAUST, Saudi Arabia. Principal Investigator of the Robotics, Intelligent Systems & Control Laboratory

Feedback Control Perspectives on Learning

This talk highlights selected feedback control concepts – in particular robustness, passivity, tracking, and stabilization – as they relate to specific questions in evolutionary game theory, no-regret learning, and multi-agent learning.

Shafi Goldwasser

Director of the Simons Institute for the Theory of Computing, a member of multiple National Academies, and winner of the ACM Turing Award.

Robustness, Verification, Privacy: Addressing Machine Learning Adversaries

Shafi will present cryptography inspired models and results to address three challenges that emerge when worst-case adversaries enter the machine learning landscape: (1) verification of machine learning models given limited access to good data, (2) training at scale on private training data, and (3) robustness against adversarial examples controlled by worst case adversaries.

Christopher Bishop

Director of the Microsoft Research Lab in Cambridge

The Real AI Revolution

In this talk, the speaker will highlight the nature of AI revolution that is already unfolding and is set to transform almost every aspect of our lives. Christopher will elaborate on why the coming decade will be a hugely exciting, and critically important, time to engage deeply in machine learning for those who want to have a truly transformational impact in the real world.

Saiph Savage

Co-director of the Civic Innovation Lab at the National Autonomous University of Mexico (UNAM) and director of the HCI Lab at West Virginia University

A Future of Work for the Invisible Workers in A.I.

Saiph proposes a framework that transforms invisible A.I. labor into opportunities for skill growth, hourly wage increase, and facilitates transitioning to new creative jobs that are unlikely to be automated in the future.

Marloes Maathuis

Professor of Statistics at ETH Zurich, Switzerland

Causal Learning

Marloes will discuss approaches for causal learning from observational data, paying particular attention to the combination of causal structure learning and variable selection, with the aim of estimating causal effects. Throughout, examples will be used to illustrate the concepts.

Anthony Zador

Alle Davis Harris Professor of Biology and Chair of Neuroscience at Cold Spring Harbor Laboratory

The Genomic Bottleneck: A Lesson from Biology

Anthony argues that most animal behavior is not the result of clever learning algorithms, but is encoded in the genome. Specifically, animals are born with highly structured brain connectivity, which enables them to learn very rapidly.

NeurIPS 2020 Workshops

This year, NeurIPS has received a record number of 160 submissions for workshops. Out of these, 60 workshops have been accepted. In the selection process, the organizers strived for a good balance between different research areas as well as between application and theory.

We like the diversity of topics covered in this year’s workshops, and certainly, everyone would be able to find workshops that are a particularly good fit for their interests. Here are our favorites:

• The pre-registration experiment: an alternative publication model for machine learning research (invited talk by Yoshua Bengio).
• BabyMind: How Babies Learn and How Machines Can Imitate (opening remarks by Gary Marcus, invited talks by Celeste Kidd and Oliver Brock).
• Machine Learning for Creativity and Design 4.0 (7 invited speakers, including artists and researchers from Google Brain, Adobe, and Facebook)
• Human in the loop dialogue systems (9 invited speakers from CMU, Stanford, Google, Amazon, FAIR).
• Differentiable computer vision, graphics, and physics in machine learning (fantastic set of panelists from NVIDIA, FAIR, Deepmind, Google Brain, etc.)
• ML4H: Machine Learning for Health (keynote by Andrew Ng)
• Women in Machine Learning (inspiring invited speakers, like Fernanda Viégas, Principal Scientist at Google, and Anca Dragan, Assistant Professor in EECS at UC Berkeley)
• Resistance AI Workshop (many interesting speakers, including Timnit Gebru and Rediet Abebe, co-founders of Black in AI)

Tutorials to Join at NeurIPS 2020

The 2020 program includes 17 tutorials given by leading experts from industry and academia. The following tutorials sound like the most exciting for us at TOPBOTS:

• Deep Conversational AI
  Pascale Fung, Zhaojiang Lin and Andrea Madotto (Hong Kong University of Science and Technology)
• Where Neuroscience meets AI (And What’s in Store for the Future)
  Jane Wang, Adam Marblestone, Kevin Miller (DeepMind)
• The Beautiful Intertwining of Causal Inference, Experimental Design and Reinforcement Learning
  Susan Murphy (Harvard University)
• Abstraction & Reasoning in AI systems: Modern Perspectives
  Francois Chollet (Google), Melanie Mitchell (Santa Fe Institute), Christian Szegedy (Google)

Top Research Papers From 2020

To be prepared for NeurIPS, you should be aware of the major research papers published in the last year in popular topics such as computer vision, NLP, and general machine learning approaches, even if they are not being presented at this specific event. 

We’ve shortlisted the top 10 research papers in these areas so you can review them quickly: 

• 2020’s Top AI & Machine Learning Research Papers
• GPT-3 & Beyond: 10 NLP Research Papers You Should Read
• Novel Computer Vision Research Papers From 2020

Enjoy this article? Sign up for more AI research updates.

We’ll let you know when we release more summary articles like this one.