Copilot suggested a path from someone else's repository that is definitely not on my local machine. How did this happen? It's a bit terrifying 🤨

Peyman Milanfar Kalman filtering was one of my favorite topics to teach. Conceptually beautiful and still highly relevant to understanding all time series models, SSMs, adaptive learning rates, continual learning and Gaussian processes.

Recently noticed an interesting but probably loose connection between the attention mechanism and linear regression. Noted it down here: c16mftang.github.io/attention.html Is there any paper that discussed this similarity? Just curious 🧐

The room is packed for John Hopfield ’s opening talk at the #AMHN2023 workshop at #NeurIPS2023. His presentation covers the fascinating historical evolution of Associative Memory. Beginning with insights into the renowned NRP program at MIT, the origin of the term "neuroscience”,

Super elegant model to explain individual variability in learning!

New Unit Paper in Nature Neuroscience showing that a family of models of the brain learn more effectively than artificial neural networks in many tasks faced by animals mrcbndu.ox.ac.uk/publications/i… MRC BNDU, Oxford Nuffield Department of Clinical Neurosciences University of Oxford

Imagine the alternative timeline if Hebbian Learning took over… 🧠

Some parts of Bristol do remind me of my hometown 😀

New Unit Paper in NeurIPS Conference on a possible computational mechanism for sequential memory in the brain mrcbndu.ox.ac.uk/publications/s… MRC BNDU, Oxford Nuffield Department of Clinical Neurosciences University of Oxford

🚨 neoSSL: Our story on how information flow in neocortical layers is perfectly placed for self-supervised learning (SSL) is now on bioRxiv doi.org/10.1101/2024.0… 🧵 (1/6)

Great knows great. Yes, this is *the* David R. Liu. He had developed a neural network model of visual attention, which (unknown to him) was similar to something Hinton was working on. He was only 16 at the time. Did they meet? I don’t know yet.

BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”

The beauty of this prize is that it is about how a physics model can be used to enable scientific discovery far beyond the narrow original intent. Ai is the biggest thing in the world right now, in large part because Hopfield recognized that spin glasses can store memories.

Super excited about this news as it really recognizes how AI is a symphony of physics, neuroscience and computer science, especially when you think about the journey from Hopfield Nets to LLMs and how intrinsically connected they actually are.

Our paper "Memory reactivation generates new, adaptive behaviours that reach beyond direct experience" is now out nature.com/articles/s4159… ! With Annie Rawson, Jill O’Reilly and Helen C Barron at MRC BNDU, Oxford Nuffield Department of Clinical Neurosciences 1/6