a_proca Profile Banner
Alexandra Proca Profile
Alexandra Proca

@a_proca

Followers
178
Following
543
Statuses
57

PhD student @imperialcollege. theoretical neuroscience, machine learning. 🦋https://t.co/LWcL9aT9wa

London, England
Joined April 2020
Don't wanna be here? Send us removal request.
@a_proca
Alexandra Proca
19 days
RT @DanAkarca: We are hosting & organising the UK Neural Computation Conference 2025 @imperialcollege! 🚀 Fantastic set of speakers, see a…
0
28
0
@a_proca
Alexandra Proca
2 months
RT @japhba: Had a lot of fun thinking about the neural basis of cognitive flexibility with Alex, Kai, and Ali! Excited to see what other wo…
0
1
0
@a_proca
Alexandra Proca
2 months
RT @akaijsa: This was an amazingly fun collaboration that began at the AC Summer School @GatsbyUCL, and I can't wait to see where it takes…
0
1
0
@a_proca
Alexandra Proca
2 months
@RaymondRChua Thanks! Very happy to chat, see you in Vancouver :)
0
0
1
@a_proca
Alexandra Proca
2 months
To conclude, we show that task abstractions can be learned in simple models, and how they result from learning dynamics in multi-task settings. These abstractions allow for behavioral flexibility and rapid adaptation.
1
0
5
@a_proca
Alexandra Proca
4 months
RT @achterbrain: @TonyZador @NatureComms @loopyluppi What if you are a student interested in NeuroAI and are looking for resources to learn…
0
3
0
@a_proca
Alexandra Proca
4 months
RT @achterbrain: Last year @TonyZador et al called to train a new generation of AI researchers, equally at home in engineering/computer sci…
0
44
0
@a_proca
Alexandra Proca
4 months
RT @NatureComms: New developing area of #NeuroAI at the intersection of #neuroscience and #artificialintelligence has many open challenges.…
0
27
0
@a_proca
Alexandra Proca
10 months
RT @stefesseM: 📣 Join us in Analytical Connectionism our summer school on the foundations of higher-level cognition. Join experts from neur…
0
20
0
@a_proca
Alexandra Proca
11 months
RT @ssmonsays: Many tasks are compositional. Their constituent parts can be recombined in exponentially many ways. How could neural network…
0
21
0