Alice Dauphin's Avatar

Alice Dauphin

@monomisphere

PhD student, TU Graz

70
Followers
245
Following
7
Posts
14.09.2024
Joined
Posts Following

Latest posts by Alice Dauphin @monomisphere

Post image

Iranians are experiencing a collective trauma. Thousands have been killed/injured in recent events, the economy is crippled & the threat of a wider conflict is real. This is especially difficult for those living in Iran, as many have lost (or fear losing) loved ones. www.nature.com/articles/d41...

03.02.2026 14:11 ๐Ÿ‘ 70 ๐Ÿ” 32 ๐Ÿ’ฌ 1 ๐Ÿ“Œ 7

Hats off to the great Anne "I don't do fancy" Treisman!

01.02.2026 21:55 ๐Ÿ‘ 89 ๐Ÿ” 14 ๐Ÿ’ฌ 1 ๐Ÿ“Œ 2

Links:
๐Ÿง  My neuro-RHEL abstract:
openreview.net/attachment?i...
๐Ÿ“„ Original RHEL paper: openreview.net/forum?id=w1i...
๐ŸŽฎ Interactive demo by Guillaume Pourcel to understand RHEL: guillaumepourcel.github.io/rhel-interac...

03.12.2025 00:08 ๐Ÿ‘ 0 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0

๐Ÿ“† And if you want to hear more (or rather all) about RHEL Guillaume Pourcel will present the full framework in San Diego ๐Ÿ‡บ๐Ÿ‡ธ on Friday 5:
- Oral at 4:10 pm PST
- Poster from 4:30 pm PST
Maxence Ernoult presents in Copenhagen ๐Ÿ‡ฉ๐Ÿ‡ฐ at #EurIPS2025:
- Oral on Friday 5 at 9 am
- Poster on Thursday 4

02.12.2025 23:39 ๐Ÿ‘ 0 ๐Ÿ” 0 ๐Ÿ’ฌ 1 ๐Ÿ“Œ 0

๐Ÿค“ If you're interested in our latest results, comparison with existing approaches or just curious about new theories for learning in the brain, stop by!

02.12.2025 23:39 ๐Ÿ‘ 0 ๐Ÿ” 0 ๐Ÿ’ฌ 1 ๐Ÿ“Œ 0

๐Ÿ” The key result: Our learning rule is a form of contrastive Hebbian learning and recovers the exact gradients through time!

02.12.2025 23:39 ๐Ÿ‘ 0 ๐Ÿ” 0 ๐Ÿ’ฌ 1 ๐Ÿ“Œ 0

Amazingly there is a new alternative to BPTT in town: RHEL==Recurrent Hamiltonian Echo Learning (Pourcel & Ernoult, 2025)! We took inspiration from Hopfield energy models to design a novel Hamiltonian NN. In our model, neurons are now second-order oscillating ODEs that can be trained using RHEL...

02.12.2025 23:38 ๐Ÿ‘ 0 ๐Ÿ” 0 ๐Ÿ’ฌ 1 ๐Ÿ“Œ 0

๐Ÿ“ข Presenting our work at #NeurIPS2025 ๐Ÿ‡บ๐Ÿ‡ธ today (6-9 pm) @wimlworkshop.bsky.social!

๐Ÿง  The question: How can the brain learn temporal dependencies without an artificial backward pass? BPTT is notoriously harder than BP and is still uncharted territory (Lillicrap & @adamsantoro.bsky.social , 2019).

02.12.2025 23:37 ๐Ÿ‘ 3 ๐Ÿ” 0 ๐Ÿ’ฌ 1 ๐Ÿ“Œ 0
Post image

๐—ช๐—ต๐—ฒ๐—ฟ๐—ฒ ๐—ฑ๐—ผ ๐—ฟ๐—ฒ๐˜„๐—ฎ๐—ฟ๐—ฑ๐˜€ (๐˜ƒ๐—ฎ๐—น๐˜‚๐—ฒ) ๐—ฐ๐—ผ๐—บ๐—ฒ ๐—ณ๐—ฟ๐—ผ๐—บ?
Implications for reinforcement learning.
Very interesting paper.
doi.org/10.1016/j.ti...
#neuroskyence

03.09.2025 16:27 ๐Ÿ‘ 111 ๐Ÿ” 24 ๐Ÿ’ฌ 7 ๐Ÿ“Œ 0
Preview
What a Swedish Series (Real Humans) Teaches Us About AI Safety A cool series that brings AI safety concepts to life...

If you are curious about AI safety/alignment or just look for a good series picturing a future with AI at scale, check my post: open.substack.com/pub/aisig/p/...

03.09.2025 08:01 ๐Ÿ‘ 4 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
Post image

Et je viens de voir passer de strip de @unpied.bsky.social qui rรฉsume pas mal ce qu'on peut penser de cette histoire.

19.06.2025 07:17 ๐Ÿ‘ 230 ๐Ÿ” 73 ๐Ÿ’ฌ 5 ๐Ÿ“Œ 1
Preview
The Replicards โ€“ Replicards

With @eliamascolo.bsky.social we developed an interactive class on biological evolution (focusing on mutations ๐Ÿ‘พ) for science #teacher through a card game ๐ŸŽฒ We crash-tested it with #HighSchool students from Milan and made it available online for broader use: replicards.netlify.app #SciCom #EvoBio

25.02.2025 11:36 ๐Ÿ‘ 18 ๐Ÿ” 6 ๐Ÿ’ฌ 3 ๐Ÿ“Œ 2