e-giunchiglia.bsky.social
Assistant Professor at Imperial College London | EEE Department and I-X.
Neuro-symbolic AI, Safe AI, Generative Models
Previously: Post-doc at TU Wien, DPhil at the University of Oxford.
11 posts
641 followers
260 following
Regular Contributor
comment in response to
post
đź“© Interested? Apply now: [email protected]
đź“Ś Use [PhD Application] in the email subject
@imperial-ix.bsky.social @imperialeee.bsky.social @imperialcollegeldn.bsky.social @nesyconf.org
[3/3]
comment in response to
post
📢 What’s included?
âś… Full scholarship for UK/EU citizens with (pre-)settled status
âś… Industry collaboration: 3-month internship with our partner company
✅ Be part of a world-class research environment 🌍
[2/3]
comment in response to
post
@neuralnoise.com @pascalhitzler.bsky.social @lucderaedt.bsky.social @guyvdb.bsky.social @emilevankrieken.com @sbadredd.bsky.social @ema-ridopoco.bsky.social @nolovedeeplearning.bsky.social @arturgarcez.bsky.social @michaelcochez.bsky.social @tarekbesold.bsky.social @garymarcus.bsky.social
comment in response to
post
Track Editors:
Alessandro Abate, University of Oxford, U.K.
Eleonora Giunchiglia, Imperial College London, U.K.
Bettina Könighofer, Graz University of Technology, Austria
Luca Pasa, University of Padova, Italy
Matteo Zavatteri, University of Padova, Italy
comment in response to
post
We analyzed the behavior of Gumbel softmax in complex stochastic computation graphs. It’s a combination of vanishing gradients and a tendency to fall into poor local minima, underutilizing available categories. We also have some ideas for improvements. proceedings.neurips.cc/paper/2021/h...