Kohitij Kar
@kohitij.bsky.social
Assistant Professor, Canada Research Chair in Visual Neuroscience, @yorkuniversity, Visiting Scientist @MIT, Previously: Postdoc(@MIT), PhD (@RutgersU)
I agree. But I doubt how much one’s intuition (perception) about how their brain functions to support their intelligence or how it evolved translates into scientific facts about those same questions.
May 8, 2025 at 6:05 PM
I agree. But I doubt how much one’s intuition (perception) about how their brain functions to support their intelligence or how it evolved translates into scientific facts about those same questions.
In many conversations, I felt that people often have certain preconceived (largely unvalidated) notion of how intelligence should emerge. And because certain developments in AI dont fit that template—instead of re-evaluating their initial position— they are blindly critical of current AI!
May 8, 2025 at 5:56 PM
In many conversations, I felt that people often have certain preconceived (largely unvalidated) notion of how intelligence should emerge. And because certain developments in AI dont fit that template—instead of re-evaluating their initial position— they are blindly critical of current AI!
Most concepts and ideas have levels and nuances — and taking the most extreme stance seems to be in fashion now.
May 8, 2025 at 2:53 PM
Most concepts and ideas have levels and nuances — and taking the most extreme stance seems to be in fashion now.
Yeah, if current AI systems (vision, audio, language, multimodal) are not “intelligent”, I don’t know what is! There are many intelligent (biological) species that don’t run human like processing but can solve tasks, reason, and most importantly survive.
May 8, 2025 at 2:53 PM
Yeah, if current AI systems (vision, audio, language, multimodal) are not “intelligent”, I don’t know what is! There are many intelligent (biological) species that don’t run human like processing but can solve tasks, reason, and most importantly survive.
Extremely sad news! Very sorry to hear this and a great loss for vision science
December 31, 2024 at 6:54 PM
Extremely sad news! Very sorry to hear this and a great loss for vision science
(3/3) Many ANN models of untrained IT show similar changes at the level of ANN-IT (which is typically not at the very end of the ANN hierarchy) with additional category training (implemented via varied learning approaches) that also generalize to category orthogonal representational shifts.
December 30, 2024 at 5:58 PM
(3/3) Many ANN models of untrained IT show similar changes at the level of ANN-IT (which is typically not at the very end of the ANN hierarchy) with additional category training (implemented via varied learning approaches) that also generalize to category orthogonal representational shifts.
(2/3) Untrained animals can see objects but can’t attach labels—so we don’t expect ventral stream to reformat with learning. But does it change at all, or everything happens downstream? Trained vs. untrained monkeys show minor but robust IT changes -- not a complete reformat, but meaningful tweaks.
December 30, 2024 at 5:58 PM
(2/3) Untrained animals can see objects but can’t attach labels—so we don’t expect ventral stream to reformat with learning. But does it change at all, or everything happens downstream? Trained vs. untrained monkeys show minor but robust IT changes -- not a complete reformat, but meaningful tweaks.