Alexandra Proca

PhD student @imperialcollege. theoretical neuroscience, deep learning. 🦋

[Alexandra Proca @a_proca]

How do task dynamics impact learning in networks with internal dynamics?

Excited to share our ICML Oral paper on learning dynamics in linear RNNs!
with @ClementineDomi6 @mpshanahan @PedroMediano

https://t.co/vh7AImrrtn

[UniReps @unireps]

📢Join us for the next UniReps x @ELLISforEurope
speaker series event, happening on July 1st at 4:00 PM CEST with @prlz77, Xavier Suau and Santiago Acevedo! 🚀

[UniReps @unireps]

📢Join us for the next UniReps x @ELLISforEurope speaker series event, happening on 17 June at 4:00 PM CEST with @adityagrover_ and @black_samorez!🚀

[Alexandra Proca @a_proca]

In summary, we expand the study of superposition to recurrent architectures, enabling us to study how temporal information acts as a capacity constraint and affects feature geometry. Our work highlights how superposition affects dynamics and is shaped by time.

[Alexandra Proca @a_proca]

Excited to share our ICLR Oral paper, co-lead with Pratyaksh Sharma, and with @lucas_prie @PedroMediano!

We study how feature geometry is shaped by memory demands in RNNs, introducing the concept of temporal superposition.

https://t.co/5g0zCZvSEe

[Alexandra Proca @a_proca]

We induce spatial superposition by using 5D input (A-E) and temporal superposition by increasing k. As memory demand (k) increases, the RNN drops features in favor of representing others for a longer duration. This representational tradeoff leads to a strategy that is all-or-none

[Jamie Simon @learning_mech]

1/ Deep learning is going to have a scientific theory. We can see the pieces starting to come together, and it's looking a lot like physics!

We're releasing a paper pulling together these emerging threads and giving them a name: learning mechanics.

🔨 https://t.co/92nSIHameW 🔧

[UniReps @unireps]

📢Join us for the next UniReps x @ELLISforEurope speaker series happening on 29th April at 4:00 PM CET with @neurosacramento and Paul Friedrich!👾

[UniReps @unireps]

📢The next UniReps x @ELLISforEurope speaker series event is happening on 26 February at 4:00 PM CET with @orvieto_antonio and @SaraKangaslahti . Don’t miss it!🚀

[Andrew Saxe @SaxeLab]

Excited to share new work @icmlconf by Loek van Rossem exploring the development of computational algorithms in recurrent neural networks.

Hear it live tomorrow, Oral 1D, Tues 14 Jul West Exhibition Hall C: https://t.co/zsnSlJ0rrc

Paper: https://t.co/aZs7VZuFNg

(1/11)

[Alexandra Proca @a_proca]

@orvieto_antonio Thanks so much!!