Proud to share our 150-page "proto-book" with @mmbronstein@joanbruna@TacoCohen on geometric DL! Through the lens of symmetries and invariances, we attempt to distill "all you need to build the architectures that are all you need".
https://t.co/CBN0IG8BXR
More info below! 🧵
Proud to be part of sensational teams!
We just released a new take on different ways to achieve #XAI using concept-based explanations!
There is also a public library to get you off the ground at lightning speed! ⚡️
🎧In our latest #IntergratedCancerMedicine podcast Helena, Zohreh and Nikola of the @Cambridge_CL Cancer AI group talk about integrative and interpretable AI tools for bench to bedside research in cancer medicine, funded by @TheMarkFdn@CRUKresearch
▶️https://t.co/26OZV2habO
Hoy es el Día Internacional de la Mujer y la Niña en la Ciencia
Today it's International Day of Women and Girls in Science
#11F
Todos los días, pero hoy más nunca... #NoMoreMatildas
Every day, but today more than ever... #NoMoreMatildas
Research Associate @helenaandrest is the 5th speaker in our Healthcare Research Showcase next Friday, 29 Jan. She focuses on developing #AI techniques to integrate multi-modal cancer data to achieve better diagnoses and treatment for cancer patients. https://t.co/ZGW3ZDW4Ht
😲 Acabamos de descubrir los ‘Big Four’, los cuatro grandes factores de la conducta violenta, tal como nos explica el Dr. Antonio Andrés Pueyo @UniBarcelona @PrevenSi @FacPsicoUB
🔴👉https://t.co/j89BhvoOMh #CazadorDeViolencia
Very pleased to share my first @NakedScientists episode as full-time producer - 'Rosalind Franklin: the hidden story of DNA' featuring Rosalind's sister Jenifer Glynn on Rosalind's time as a student at my very own @Newnham_College#Franklin100
https://t.co/jtiQsHsjLV
The Unreasonable Effectiveness of Mathematics in the Natural Sciences is an essay about mathematical concepts and their applicability written by Nobel Prize winning physicist Eugene Wigner.
It's a great read: https://t.co/7Vivp1iQaH
A great paper for your summer reading list 📚
What is the relation b/w de-anonymization of authors through arXiv e-prints and their acceptance at a double-blind conference?
Not a hot take: For ICLR, we find positive correlation between releasing preprints on arXiv and acceptance rates of papers by well-known authors
1/n
"You know, people think mathematics is complicated. Mathematics is the simple bit. It's the stuff we can understand. It's cats that are complicated". RIP John Conway