#NeurIPS

Ben Recht

beenwrekt

A few folks asked about the content of press conference at NeurIPS, so here’s a thread... The press conference mostly consisted of readouts from the chairs, the best paper award

Talia Ringer

TaliaRinger

Also while the NeurIPS name thing is totally tangential to this entire fiasco, as someone whose life work is on a system named by some French dude in the 1980s

Thouis (Ray) Jones

thouis

The @lmrl_bio backgrounds for our http://Gather.Town (@Gather) were created by @liz_wood, using @inkarnaterpg. Town layout was by my eldest child.The space was amazing. A thread… The Main Talks and Panels

Rosanne Liu

savvyRL

Favorite #NeurIPS2020 presentations and posters this year PS: heavily biased by what I happened to catch and whom I happened to talk toPPS: still catching up on talks so the

Patrick Mineault

patrickmineault

How do you get the most out of big multi-track online conferences like #NeurIPS? Received a nice question in my DMs from a software engineer interested in learning more about

Andrew Gordon Wilson

andrewgwils

In practice, standard "deep ensembles" of independently trained models provides a relatively compelling Bayesian model average. This point is often overlooked because we are used to viewing Bayesian methods as

Jakob Foerster

j_foerst

The gradient is a locally greedy direction. Where do you get if you follow the eigenvectors of the Hessian instead? Our new paper, “Ridge Rider” (https://papers.nips.cc/paper/2020/file/08425b881bcde94a383cd258cea331be-Paper.pdf), explor

jonstokes.com

jonst0kes

As a way to think about the stakes in the AI debate:A language model like GPT-3, which trains on a corpus of text & produces new text in response to

Amandalynne Paullada

amandalynneP

I'm grateful to @ResistanceAI for the opportunity to present some notes from a work in progress in which I consider the question: how does machine translation shift power? Some thoughts

Nando de Freitas

NandoDF

Another long thread. Bear with me till the end please. These are my views, and not necessarily of those associated with me. Though those associated with me have been incredibly

Kory Mathewson - Montreal 🇨🇦

korymath

I am excited to be presenting some great work with some brilliant collaborators at #NeurIPS 2020.This has been a challenging year and I want to thank the inspiration and support

Lyne P. Tchapmi

lynetcha

In 2016, when Dr. Gebru @timnitGebru noticed there were about 6 black people out of 5500+ at the largest AI Conference, her team rolled up their sleeves and in 2017,

MMitchell

mmitchell_ai

"didn’t meet our bar for publication ... It ignored too much relevant research".He says of our paper, with over 128 cross-discipline citations. And so fires one of the authors. 2020's

Shreya Shankar

sh_reya

Thrilled to see a NeurIPS 2020 paper that eeks out a bit more performance on benchmark image datasets by...removing mislabeled examples from the train set!"Identifying Mislabeled Data using the Area

Simone Scardapane

s_scardapane

Do you really need deeeep networks for *all inputs*?Can't you do better?A small thread to summarize a number of interesting works I have been reading on how to adaptively and

no love deep learning 🛋️ #NeurIPS2020 🛋️

tetraduzione

A deeply interesting tutorial by @fchollet @MelMitchell1 @ChrSzegedy at #NeurIPS2020 "#Abstraction & #Reasoning in #AI systems: Modern Perspectives "or "What are abstraction, generalization and analogic reasoning?"1/

By continuing to use the site, you are consenting to the use of cookies as explained in our Cookie Policy to improve your experience.