The official home of the Python Programming Language
TLDR; The PSF has made the decision to put our community and our shared diversity, equity, and inclusion values ahead of seeking $1.5M in new revenue. Please read and share. pyfound.blogspot.com/2025/10/NSF-...
π§΅
27.10.2025 14:47 β π 6424 π 2770 π¬ 128 π 457
New #NeuroAI preprint on #ContinualLearning!
Continual learning methods struggle in mostly unsupervised environments with sparse labels (e.g. parents telling their child the object is an 'apple').
We propose that in the cortex, predictive coding of high-level top-down modulations solves this! (1/6)
10.06.2025 13:17 β π 22 π 6 π¬ 1 π 1
Check out our new paper!
Vision models often struggle with learning both transformation-invariant and -equivariant representations at the same time.
@hafezghm.bsky.social shows that self-supervised prediction with proper inductive biases achieves both simultaneously. (1/4)
#MLSky #NeuroAI
14.05.2025 12:57 β π 45 π 13 π¬ 2 π 0
"Our results demonstrate that the better a model understands the data, the more effectively it can compress it, suggesting a deep connection between understanding and compression." - such a cool implication
03.05.2025 15:02 β π 20 π 4 π¬ 3 π 0
complete blog post is now live! more tips, and reframed into 2-step process: (1) get accepted by page 1, (2) avoid rejection with the rest. download both PDFs too.
maxwellforbes.com/posts/how-to...
11.04.2025 21:35 β π 19 π 4 π¬ 1 π 1
Thereβs no such thing as A.I βart.β Itβs a soulless amalgamation of plagiarised data. That is the antithesis of art.
29.03.2025 12:48 β π 9015 π 1555 π¬ 35 π 2
I'm interested in doing a PhD in your group. Sent you an email, looking forward to your reply :)
29.03.2025 21:04 β π 0 π 0 π¬ 0 π 0
#NeuroJobs
14.03.2025 23:56 β π 0 π 0 π¬ 0 π 0
The Ultra-Scale Playbook - a Hugging Face Space by nanotron
The ultimate guide to training LLM on large GPU Clusters
After 6+ months in the making and over a year of GPU compute, we're excited to release the "Ultra-Scale Playbook": hf.co/spaces/nanot...
A book to learn all about 5D parallelism, ZeRO, CUDA kernels, how/why overlap compute & coms with theory, motivation, interactive plots and 4000+ experiments!
19.02.2025 18:10 β π 181 π 52 π¬ 2 π 5
Assistant Professor of Neuroscience at
the University of WΓΌrzburg, interested in #neuroscience #learning #decisionmaking #mentalhealth
Deputy Exec Director @python.org π€ π Opinions and tiny dog my own. she/her
PhD student at @mackelab.bsky.social
Prof. of Computational Cognitive Science at TU Darmstadt & PI of the Human and Machine Cognition lab at the University of TΓΌbingen | hmc-lab.com
MSc Student in NeuroAI @ McGill & Mila
w/ Blake Richards & Shahab Bakhtiari
PostDoc at University of Oxford.
Networks, neuroscience, control theory, curiosity, science of science
π³οΈβππ³οΈββ§οΈJ Peter Skirkanich Professor, University of Pennsylvania
Assoc. Prof. Learning Sciences, Harvard GSE. Study learning in early childhood using computational modeling & empirical studies. Speaking for self only. She/her
Cognitive scientist, philosopher, and psychologist at Berkeley, author of The Scientist in the Crib, The Philosophical Baby and The Gardener and the Carpenter and grandmother of six.
Reward-Free Model-based Maximalist. High-dimensional Empowerment. Self-Preserving Autonomous Agents. Theories of intelligence grounded in compositional control.
How do we learn to achieve our goals? π§ Computational Cognitive Neuroscience PhD student UC Berkeley πΏ
Research Scientist at Google DeepMind and Professor of Computer Science and Engineering at the University of Michigan. Interested in Reinforcement Learning and Artificial Intelligence.
Psychology, education science, cognitive neuroscience, statistical methods. Prof @uni_tue. Made in Japan. Learning German.
Assistant professor at NUS. Scaling cooperative intelligence & infrastructure for an increasingly automated future. PhD @ MIT ProbComp / CoCoSci. Pronouns: η₯/δΌ
Neurogeneticist interested in the relations between genes, brains, and minds. Author of INNATE (2018) and FREE AGENTS (2023)
See(k)ing the surreal
Causal World Models for Curious Robots @ University of TΓΌbingen/Max Planck Institute for Intelligent Systems π©πͺ
#reinforcementlearning #robotics #causality #meditation #vegan
Building autotelic agents from socio-cultural interactions
https://ccolas.github.io/
Philosophy of learning, evolution, & development, but make it metaphysics.
Itβs not a point of view, itβs a point of *do*. Cognition is like digestion. Plant I > AI. Phil of Mind = Phil of Biology.
https://philosophy.stanford.edu/people/mariel-goddu
comp neuro prof @ Princeton
brains, machine learning, & postmodern angst
pillowlab.princeton.edu
Professor, Computer Science, University of British Columbia. CIFAR AI Chair, Vector Institute. Senior Advisor, DeepMind. ML, AI, deep RL, deep learning, AI-Generating Algorithms (AI-GAs), open-endedness.
