JohnMark Taylor's Avatar

JohnMark Taylor

@johnmarktaylor.bsky.social

Cognitive computational neuroscientist at Columbia. Creator of TorchLens: https://github.com/johnmarktaylor91/torchlens

480 Followers  |  1,020 Following  |  9 Posts  |  Joined: 21.11.2024  |  1.3224

Latest posts by johnmarktaylor.bsky.social on Bluesky

Post image

now on Twitter an AI dog automatically pops up and spouts regime propaganda slop at you when you express heretical opinions

18.04.2025 01:31 β€” πŸ‘ 3    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

Harvard has set an example for other higher-ed institutions - rejecting an unlawful and ham-handed attempt to stifle academic freedom, while taking steps to make sure students can benefit from an environment of intellectual inquiry, rigorous debate and mutual respect. Let’s hope others follow suit.

15.04.2025 03:52 β€” πŸ‘ 89746    πŸ” 18264    πŸ’¬ 1575    πŸ“Œ 747

Excellent primer. Can be hard to pack in software engineering training amidst everything else in grad school but a little bit goes a long way

15.04.2025 13:50 β€” πŸ‘ 8    πŸ” 2    πŸ’¬ 0    πŸ“Œ 0
Video thumbnail

gotta believe the top salsa dancers would score through the roof on spatial intelligence / shape rotation tests

27.03.2025 16:05 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

Just found out NIH has officially canceled our grant, a longitudinal study of Alzheimer's disease in Black Americans. I cannot even put into words how angry I am. The truth is they are canceling it because it has Black in the title. That's it, there is no other reason to do this.

21.03.2025 20:12 β€” πŸ‘ 1839    πŸ” 790    πŸ’¬ 50    πŸ“Œ 42

I searched for β€œclave rhythm” and this came up

28.01.2025 01:16 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

Geometry of Musical Rhythm is a lovely book

28.01.2025 01:11 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0
Preview
When do measured representational distances reflect the neural representational geometry? The representational geometry of a brain region can be characterized by the distances among neural activity patterns for a set of experimental conditions. Researchers routinely estimate representation...

Recording modalities like fMRI aggregate the responses of many thousands of neurons, but how does this affect representational geometry? Meticulous essential breakdown from @veronicabossio.bsky.social

biorxiv.org/cgi/content/...

05.01.2025 01:37 β€” πŸ‘ 4    πŸ” 1    πŸ’¬ 0    πŸ“Œ 0

Thank you! Hope it helps you out and welcome any feedback you’ve got

27.12.2024 17:25 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

Great suggestion, that’s the biggest item on the to-do list and actually shouldn’t be too difficult with the existing infrastructureβ€”just want to make the interface user-friendly and flexible so there are some design choices to figure out

27.12.2024 03:57 β€” πŸ‘ 3    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Post image

Deep neural networks are complex, but looking inside them ought to be simple. Check out TorchLens, a package that can visualize any PyTorch network and extract all activations and metadata in just one line of code:

github.com/johnmarktayl...

www.nature.com/articles/s41...

27.12.2024 03:14 β€” πŸ‘ 55    πŸ” 15    πŸ’¬ 2    πŸ“Œ 0

@johnmarktaylor is following 20 prominent accounts