Emtiyaz Khan<p>The video of my <a href="https://mastodon.social/tags/NeurIPS2022" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NeurIPS2022</span></a> talk on “building sustainable communities” is online now. I talk about two communities I help to build about 20 and 15 yrs respectively. Those are still running! </p><p>I argue for sustainable efforts, no matter how small scale they are, because over time they really deliver. </p><p>Video: <a href="https://slideslive.com/38995247" rel="nofollow noopener noreferrer" target="_blank"><span class="invisible">https://</span><span class="">slideslive.com/38995247</span><span class="invisible"></span></a></p><p>Thanks to Sara Hooker, Rosanne Liu and coorganizer for inviting me.</p>
Recent searches
Search options
#NeurIPS2022
0 posts0 participants0 posts today
Appropriate lunch spot for me at #NeurIPS2022 (although I'm not retired yet). 
Really looking forward to a very full day of talks and posters at the #NeurIPS2022 workshop on Shared Visual Representations in Humans and Machine Intelligence starting shortly 
https://www.svrhm.com/schedule! I’m curious whether at the end of the day there will be consensus about the degree of ‘sharedness’, where there are still gaps, and how/if we could/should address those.
www.svrhm.comSVRHM 2022 - Schedule
8.45 - 9.00 : Opening Remarks
Session 1: Beyond Object Recognition in Humans and Machines
9.00 - 9.10: Michael Cohen (Amherst/MIT) [Invited Oral/Talk] | The bandwidth of perceptual awareness is constrained by specific high-level visual features | virtual
9.10 - 9.20: Matthew Koichi Grimes
Boosting a paper that was presented a couple of days ago at #NeurIPS #NeurIPS2022: Natural gradient enables fast sampling in spiking neural networks. Led by Paul Masset and @jzv #neuroscience https://openreview.net/forum?id=Yopob26XjmL
OpenReviewNatural gradient enables fast sampling in spiking neural networksWe derive a unified framework for spiking neural networks that can sample at behaviorally-relevant timescales through population geometry.
Leaving 
SF for 
New Orleans. Excited to go to #NeurIPS2022 for the first time!
You can catch me Friday at the "All things attention" workshop (https://attention-learning-workshop.github.io/), and Saturday at the "Gaze meets ML" workshop (https://gaze-meets-ml.github.io/gaze_ml_2022/).
Looking forward to seeing you there! 
So many eager people at #NeurIPS2022 seeking to maximise attention for their iteration of AI, while the social effect is a gradient descent towards the transformations of algorithmic violence. We need an anti-fascist approach to artificial intelligence https://bristoluniversitypress.co.uk/resisting-ai
Bristol University PressResisting AIResisting AI - An Anti-fascist Approach to Artificial Intelligence; Artificial Intelligence (AI) is everywhere, yet it causes damage to society in ways that can’t be fixed. Calling for the restructuring of AI, Dan McQuillan sets out an anti-fascist approach that replaces exclusions with caring and outlines new mechanisms that support collective freedom.
#NeurIPS Is doing something really wrong if everyone is tweeting links to the arXiv versions of their papers there. It's supposed to be this super prestigious conference yet no one wants their (ahem) archival version of their work to be associated with it?
Or maybe it's the researchers/research culture who are devaluing the actual contentful work, & the whole point is the performance of being at the conf/tweeting bc no one is going to pay attn to these papers next month anyway?