//
sign in
Profile
by @danabra.mov
Profile
by @dansshadow.bsky.social
Profile
by @jimpick.com
AviHandle
by @danabra.mov
AviHandle
by @dansshadow.bsky.social
AviHandle
by @katherine.computer
EventsList
by @katherine.computer
ProfileHeader
by @dansshadow.bsky.social
ProfileHeader
by @danabra.mov
ProfileMedia
by @danabra.mov
ProfilePlays
by @danabra.mov
ProfilePosts
by @danabra.mov
ProfilePosts
by @dansshadow.bsky.social
ProfileReplies
by @danabra.mov
Record
by @atsui.org
Skircle
by @danabra.mov
StreamPlacePlaylist
by @katherine.computer
+ new component
Profile
Loading...









Loading...
If of interest, please reach out! Questions very welcome. See recent work: sites.google.com/site/robmokb... /8 /fin
We need this at conference venues. #philosophy #philtwit #philsky
NEW PAPER. Why do larger networks train better? "Because they contain more candidate *sub*networks that can learn the task" → lottery tickets This popular explanation uses an appealing but misleading metaphor🧵 We propose an intuitive alternative grounded in theory: escape dimensions
Other ideas brewing that we would welcome people to work on include: - AI trust - e.g., how do people perceive AI errors? - human-like multimodal learning - transcranial ultrasound stimulation (e.g., hippocampus, inferior temporal cortex) /6
We aim to 1) understand concept learning and representation in the brain, and 2) build brain-inspired models for efficient and safe AI. /4
My group is interested in how the brain and ANNs build and represents concepts, from encoding (early learning, hippocampus) to consolidated semantic knowledge (e.g. ant/lat/inf temp lobe), with a focus on visual and semantic (incl. word) concepts. /3
1d
2d
NOTE: our institute's internal deadline is very early (31/07/2026), so please contact me ASAP if interested (official deadline 28/08/2026). If your interests align with anything below, please contact me ASAP for incl any Qs! Email: rob[dot]mok[at]nict.go.jp. /2
2d
Projects currently include: - building hippocampus/cortex-inspired models - using/modifying DNNs (vision/language, vision-language models) for comp and neural insights - 3T/7T fMRI, MEG model-human comparisons, behavioral error alignment - modeling ageing and neurodegeneration using DNNs /5
1d
CiNet is based within the University of Osaka, within a beautiful campus, great neuroimaging resources (few restrictions on 3T, 7T, MEG) and computing resources (CPU/GPU clusters). cinet.jp/english/ /7
1d
1d
Interested in a Postdoc on how brains/ANNs learn and represent visual/semantic concepts in Osaka, Japan? Check out the JSPS Postdoctoral Fellowships (up to 2 yr). I'd be happy to host postdocs to come work in my lab at CiNet, Osaka! Info🧵👇 Please repost! #neuroskyence #psychscisky #mlsky 🧠💻 /1
1d
1d
1d
1d
Rob Mok
Rob Mok
Kristina Šekrst
Rob Mok
Rob Mok
Rob Mok
Official Website of Japan Society for the Promotion of Science (JSPS)
www.jsps.go.jp
About the Program (Standard)|Postdoctoral Fellowships for Research in Japan|Postdoctoral Fellowships for Research in Japan
Rob Mok
Rob Mok
Flavio Martinelli
Rob Mok