Thomas Miconi
@thomasmiconi.bsky.social
Reposted by Thomas Miconi
it's sad that the UK doesn't have Mormons, because they would be incredible at Taskmaster
September 9, 2025 at 5:45 AM
it's sad that the UK doesn't have Mormons, because they would be incredible at Taskmaster
What are good examples of meta-training *plastic* neural networks (either optimizing plasticity rules or network structure) to address neurosci questions?
Stuff like @tpvogels.bsky.social & @bconfavreux.bsky.social’s rule search, Tyulmankov Neuron 2021, our stuff on transitive inference etc.
Stuff like @tpvogels.bsky.social & @bconfavreux.bsky.social’s rule search, Tyulmankov Neuron 2021, our stuff on transitive inference etc.
June 17, 2025 at 5:43 PM
What are good examples of meta-training *plastic* neural networks (either optimizing plasticity rules or network structure) to address neurosci questions?
Stuff like @tpvogels.bsky.social & @bconfavreux.bsky.social’s rule search, Tyulmankov Neuron 2021, our stuff on transitive inference etc.
Stuff like @tpvogels.bsky.social & @bconfavreux.bsky.social’s rule search, Tyulmankov Neuron 2021, our stuff on transitive inference etc.
Google Meet is down
A million meetings cancelled
The people exult
A million meetings cancelled
The people exult
June 12, 2025 at 7:09 PM
Google Meet is down
A million meetings cancelled
The people exult
A million meetings cancelled
The people exult
tl;dr: DeepMind automates the Graduate Student Descent algorithm!
Announcing AlphaEvolve, our new LLM coding agent that has
- made new scientific discoveries
- discovered algorithms that are now deployed at Google (in Gemini, Transformers, TPU hardware design & data centers)
Blog: deepmind.google/discover/blo...
White paper:
storage.googleapis.com/deepmind-med...
- made new scientific discoveries
- discovered algorithms that are now deployed at Google (in Gemini, Transformers, TPU hardware design & data centers)
Blog: deepmind.google/discover/blo...
White paper:
storage.googleapis.com/deepmind-med...
AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms
New AI agent evolves algorithms for math and practical applications in computing by combining the creativity of large language models with automated evaluators
deepmind.google
May 15, 2025 at 5:02 PM
tl;dr: DeepMind automates the Graduate Student Descent algorithm!
Really struck at how @tyrellturing.bsky.social model of hippocampus (yesterday at Cosyne) is almost symmetric to the very similar Whittington/Fiete lab models.
Latter is based on grid cells, former has no grid cells at all!
Latter is based on grid cells, former has no grid cells at all!
March 30, 2025 at 7:16 PM
Really struck at how @tyrellturing.bsky.social model of hippocampus (yesterday at Cosyne) is almost symmetric to the very similar Whittington/Fiete lab models.
Latter is based on grid cells, former has no grid cells at all!
Latter is based on grid cells, former has no grid cells at all!
Max Bennett’s keynote was, predictably, spectacular 🤯
I’m off to Montréal for Cosyne 2025. Say hi if you see me!
March 28, 2025 at 12:16 AM
Max Bennett’s keynote was, predictably, spectacular 🤯
I’m off to Montréal for Cosyne 2025. Say hi if you see me!
March 26, 2025 at 2:45 PM
I’m off to Montréal for Cosyne 2025. Say hi if you see me!
Now out in @NatureNeuro!
Animals can do Transitive Inference (TI): quickly learn, and reconfigure, global order from partial info (learn A>B, B>C,C>D, immediately know A>D).
But currently no neural model explains the observed features of TI.
So we asked the machine to find one for us -and it did!
Animals can do Transitive Inference (TI): quickly learn, and reconfigure, global order from partial info (learn A>B, B>C,C>D, immediately know A>D).
But currently no neural model explains the observed features of TI.
So we asked the machine to find one for us -and it did!
Fully neural mechanisms for structured generalization and rapid learning identified using a meta-learning (“learning-to-learn”) approach to model relational learning (e.g. if A > B and B > C, then A > C) 🧪🧠
www.nature.com/articles/s41...
www.nature.com/articles/s41...
Neural mechanisms of relational learning and fast knowledge reassembly in plastic neural networks - Nature Neuroscience
Using a metalearning approach to model relational learning, Miconi and Kay show neural mechanisms for structured generalization and rapid learning.
www.nature.com
January 17, 2025 at 5:36 PM
Now out in @NatureNeuro!
Animals can do Transitive Inference (TI): quickly learn, and reconfigure, global order from partial info (learn A>B, B>C,C>D, immediately know A>D).
But currently no neural model explains the observed features of TI.
So we asked the machine to find one for us -and it did!
Animals can do Transitive Inference (TI): quickly learn, and reconfigure, global order from partial info (learn A>B, B>C,C>D, immediately know A>D).
But currently no neural model explains the observed features of TI.
So we asked the machine to find one for us -and it did!
It was bound to happen eventually!
December 14, 2024 at 6:56 PM
It was bound to happen eventually!
I’m at NeurIPS! Say hi if you want to talk about meta-learning, computational neuroscience, plastic neural networks, or any combination of the above.
December 11, 2024 at 6:37 PM
I’m at NeurIPS! Say hi if you want to talk about meta-learning, computational neuroscience, plastic neural networks, or any combination of the above.
Reposted by Thomas Miconi
There’s a special place in hell for departments that require letters of recommendation for all job applicants rather than just those who make some initial cut.
September 30, 2023 at 12:11 AM
There’s a special place in hell for departments that require letters of recommendation for all job applicants rather than just those who make some initial cut.