Links:
🧠 My neuro-RHEL abstract:
openreview.net/attachment?i...
📄 Original RHEL paper: openreview.net/forum?id=w1i...
🎮 Interactive demo by Guillaume Pourcel to understand RHEL: guillaumepourcel.github.io/rhel-interac...

📆 And if you want to hear more (or rather all) about RHEL Guillaume Pourcel will present the full framework in San Diego 🇺🇸 on Friday 5:
- Oral at 4:10 pm PST
- Poster from 4:30 pm PST
Maxence Ernoult presents in Copenhagen 🇩🇰 at #EurIPS2025:
- Oral on Friday 5 at 9 am
- Poster on Thursday 4

🤓 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!

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

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...

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