Cognitive computational neuroscientist at Columbia. Creator of TorchLens: https://github.com/johnmarktaylor91/torchlenshttps://bsky.app/profile/johnmarktaylor.bsky.socialhttps://bsky.app/profile/johnmarktaylor.bsky.social/post/3ml2go52njk2tMy favorite vision science success story: based on her theory Anne Treisman boldly posited a weird new kind of conscious experience, where we see features (e.g., colors & shapes) combined the wrong way. Then she just went and created this experience in people's brains. 1/04 May 2026 19:44 +0000at://did:plc:74ay4vkkl3fhqostwus7t7jc/app.bsky.feed.post/3ml2go52njk2thttps://bsky.app/profile/johnmarktaylor.bsky.social/post/3mj372dbyz22z🧵Excited to announce— "Reimagining the binding problem(s) for the 21st century": A VSS Symposium St. Pete Beach @vssmtg.bsky.social May 15th, 10:30am Presenters: Peter Tse, JohnMark Taylor, Seda Karakose-Akbiyik, Ana Chica, Anne Sereno, & Jake Quilty-Dunn https://visionsciences.org/symposia/?sym=6809 Apr 2026 16:10 +0000at://did:plc:74ay4vkkl3fhqostwus7t7jc/app.bsky.feed.post/3mj372dbyz22zhttps://bsky.app/profile/johnmarktaylor.bsky.social/post/3ln2hxwrn222know on Twitter an AI dog automatically pops up and spouts regime propaganda slop at you when you express heretical opinions18 Apr 2025 01:31 +0000at://did:plc:74ay4vkkl3fhqostwus7t7jc/app.bsky.feed.post/3ln2hxwrn222khttps://bsky.app/profile/johnmarktaylor.bsky.social/post/3lmu7t4pysc2dExcellent primer. Can be hard to pack in software engineering training amidst everything else in grad school but a little bit goes a long way [contains quote post or other embedded content]15 Apr 2025 13:50 +0000at://did:plc:74ay4vkkl3fhqostwus7t7jc/app.bsky.feed.post/3lmu7t4pysc2dhttps://bsky.app/profile/johnmarktaylor.bsky.social/post/3lleoixa6hc2jgotta believe the top salsa dancers would score through the roof on spatial intelligence / shape rotation tests27 Mar 2025 16:05 +0000at://did:plc:74ay4vkkl3fhqostwus7t7jc/app.bsky.feed.post/3lleoixa6hc2jhttps://bsky.app/profile/johnmarktaylor.bsky.social/post/3lexib4vxok2hRecording 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 https://biorxiv.org/cgi/content/short/2024.12.30.630743v105 Jan 2025 01:37 +0000at://did:plc:74ay4vkkl3fhqostwus7t7jc/app.bsky.feed.post/3lexib4vxok2hhttps://bsky.app/profile/johnmarktaylor.bsky.social/post/3leazirye6k2kDeep 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: https://github.com/johnmarktaylor91/torchlens https://www.nature.com/articles/s41598-023-40807-027 Dec 2024 03:14 +0000at://did:plc:74ay4vkkl3fhqostwus7t7jc/app.bsky.feed.post/3leazirye6k2k