ML meets Neuroscience #NeuroAI, Full Professor at the Institute of Cognitive Science (@UniOsnabrueck), prev. @DondersInst, @Cambridge_Uni #neuroconnectionism
Now out in Nature Machine Intelligence @NatMachIntell “Adopting a human developmental visual diet yields robust and shape-based AI vision”:
https://t.co/vJDuIJgi7C. A wonderful case where brain inspiration improved AI solutions.
With @martisamuser, Radek Cichy and @TimKietzmann.
Packed room for the second talk of the MIND (machine intelligence, neuroscience discovery) lecture series in Osnabrück.
Excited to hear from @dirkuwulff !
Now out in Nature Neuroscience: "Fixation duration on natural scenes is explained by memory encoding not processing demand".
https://t.co/6cBVNRLgsm
Our eyes don't linger because recognition is hard; they linger to remember. Let me take you on a quick tour. 🧵
Our NeuroAI study made it onto the cover of Nature Machine Intelligence (@NatMachIntell) ❤️.
In it, we demonstrate that a developmentally-inspired visual diet can drastically improve the robustness of ANN-based vision systems.
open access, open code, open weights, open science
Excited about our new preprint: “The illusory simplicity of the feedforward pass: evidence for the dynamical nature of stimulus encoding along the primate ventral stream”
https://t.co/IbtXBTQb5t
Work with Sushrut Thorat, Anna Mitola, Paolo Papale, Peter König & Tim Kietzmann
ANNs work off of spatial activation patterns, sent from one layer to the next. But how about the brain?
In a heroic effort, @AnthesDaniel characterised information transfer across the primate ventral stream. He found a different picture: information is encoded spatiotemporally.
The core finding: even the earliest phase of vision is highly dynamic and nothing like a stage-like sequence of information transfer.
Recurrent decoders can harness this information, and strongly outperform spatial decoders.
This has important implications for NeuroAI and BCI.
ANNs work off of spatial activation patterns, sent from one layer to the next. But how about the brain?
In a heroic effort, @AnthesDaniel characterised information transfer across the primate ventral stream. He found a different picture: information is encoded spatiotemporally.
Excited about our new preprint: “The illusory simplicity of the feedforward pass: evidence for the dynamical nature of stimulus encoding along the primate ventral stream”
https://t.co/IbtXBTQb5t
Work with Sushrut Thorat, Anna Mitola, Paolo Papale, Peter König & Tim Kietzmann
It is an incredibly fun event, so I encourage you and your team to join us.
This year, it is financed by the MIND (Machine Intelligence, Neuroscientific Discovery) initiative in Osnabrück.
If you have any questions, feel free to reach out to me.
https://t.co/Scr49A5XDw
Happy to announce the third iteration of NEAT (Neuro-AI-Talks), which will take place in Osnabrück September 14th-15th 2026.
NEAT is a (deliberately small scale) NeuroAI workshop that brings together researchers from neuroscience and AI.
https://t.co/Scr49A5XDw
More info👇
NEAT has one central design rule: only research groups whose PI can attend in person can join.
NEAT is small (80 attendees max) to encourage an open and relaxed exchange.
NEAT takes place every other year, in particular whenever CCN takes place outside of the EU.
2/3
Here at [famous scientist’s name].ai, we’re developing tools to accelerate science. Unlike academia, which has stifled the production of high quality scientific work by demanding it be correct, here at [fsn].ai, we know that you can just do (wrong) things.
📢 PhD position in Developmental Language Modelling (plz RT🙏)
What can human language acquisition teach us about training language models? Join us as a PhD!
4 yrs, fully funded, MPI-NL; april 3
https://t.co/BCCap6MzPh
@MengmiZhang We followed a similar idea last summer. We found contrast development, rather than colour or acuity, to be the deciding factor.
Our journal paper includes a large variety of tests, including texture-bias, adversarial attacks, image degradations, abstract shape recognition, etc.
What a milestone 🤯. The institute of cognitive science in Osnabrück, the first of its kind in Germany, is now home to more than 1,000 cognitive science students across our programs. Wild.