Hugo_Ninou

I am a PhD student in Pr. Cayco-Gajic's lab at Ens-PSL working at the intersection of neuroscience and machine learning.

[Hugo_Ninou @NinouHugo]

Huge thanks to my amazing supervisors Jonathan Kadmon and Alex Cayco-Gajic !

Read the full story : https://t.co/Uhf8FJG59T

[Hugo_Ninou @NinouHugo]

🚨New spotlight paper at Neurips 2025🚨

We show that in sign-diverse networks, inherent non-gradient “curl” terms arise, and can, depending on network architecture, destabilize gradient-descent solutions or paradoxically accelerate learning.
🧵⬇️

https://t.co/Uhf8FJG59T

[Hugo_Ninou @NinouHugo]

9/10
Our work challenges the dominant view that learning must strictly follow a gradient. The diversity of plasticity rules in biology might not be a bug, but a feature—an evolutionary strategy leveraging non-gradient dynamics for more efficient and robust learning. 🌀

[Hugo_Ninou @NinouHugo]

9/9 A huge thank you to my co-first author Sharon Israely and Ori Rajchert, Lee Elmaleh, Ran Harel, @FirasMawase , @kadmonj , and @PrutYifat for their invaluable contributions and support throughout this journey. 🙏

[Hugo_Ninou @NinouHugo]

🚨 Paper Alert! 🚨 1/n Thrilled to share our latest research, now published in Nature Communications! 🎉 This study dives deep into how the cerebellum shapes cortical preparatory activity during motor adaptation.
https://t.co/MT04ycnGU5
#Neuroscience #motorcontrol #cerebellum

[Hugo_Ninou @NinouHugo]

8/n
1️⃣ Our study provides insights into how cerebellar signals constrain cortical preparatory activity, promoting generalization and adaptation.
2️⃣ We show that without cerebellar signals, cortical mechanisms are harnessed to restore adaptation, albeit with reduced efficiency.