๐๐ฒ๐ฎ๐ฟ๐ป๐ถ๐ป๐ด ๐ฑ๐๐ป๐ฎ๐บ๐ถ๐ฐ๐ฎ๐น ๐๐๐๐๐ฒ๐บ๐ ๐ถ๐ ๐ต๐ฎ๐ฟ๐ฑ
But lots of progress being made; this one looks very interesting.
arxiv.org/abs/2604.24662
Great paper! Large scale 2p + behav. reveals that time codes in M2 and PPC can shift between coherent and ind. modes. Plus, their shared pop. dyn. are stratified: time info in a high-D subspace, and behav info in a low-D subspace. @riichirohira.bsky.social www.nature.com/articles/s41...
A pyramidal cell in the mouse medial frontal cortex #FluorescenceFriday
h/t Jiajun Li on the confocal ๐ฌ๐ง ๐งช
Spencer LaVere Smith
PessoaBrain
Pleased to share that this work is now published in TMLR!
openreview.net/forum?id=RuW...
When do machine learning systems fail to generalize, and what mechanisms could improve their generalization? Here, we draw inspiration from cognitive science to argue that one weakness of...
Why does AI sometimes fail to generalize, and what might help? In a new paper (arxiv.org/abs/2509.16189), we highlight the latent learning gap โ which unifies findings from language modeling to agent navigation โ and suggest that episodic memory complements parametric learning to bridge it. Thread:
When do machine learning systems fail to generalize, and what mechanisms could improve their generalization? Here, we draw inspiration from cognitive science to argue that one weakness of machine lear...
