@satpreetsingh.bsky.social
Postdoc @harvard.edu @kempnerinstitute.bsky.social Homepage: http://satpreetsingh.github.io Twitter: https://x.com/tweetsatpreet
Excited to share a new project spanning cognitive science and AI where we develop a novel deep reinforcement learning model---Multitask Preplay---that explains how people generalize to new tasks that were previously accessible but unpursued.
12.07.2025 16:19 — 👍 42 🔁 9 💬 2 📌 1
For the past 3 years, I've taught a course on Machine Learning for Climate Change to undergrads. At times, people have asked if the course lectures could be made available online. While I can't offer that, I have decided to start making "5 Minute Papers on AI for the Planet" videos. Hope its useful!
20.06.2025 01:55 — 👍 126 🔁 41 💬 4 📌 2
Might be a bit outside your time-range, but these reviews are key refs:
arxiv.org/abs/2210.05050
www.nowpublishers.com/article/Deta...
CC: @swarat.bsky.social @yisongyue.bsky.social
If you're at #RLDM2025, check out our contributed talk at Session 3 (Fri 6/13, 12:10pm), presented by my brilliant co-first-author on this project @sjohnsonyu.bsky.social!
Wasn't able to make it in person, but would love to hear your thoughts
@kempnerinstitute.bsky.social @harvardmed.bsky.social
Check out our new work on making robots process touch more like brains!
Surprisingly, ConvRNNs best matched mouse cortex—passing the NeuroAI Turing Test. We also developed tactile-specific SSL augmentations and an Encoder-Attender-Decoder framework unifying ConvRNNs, SSMs & Transformers.
It was an honor to speak at the
@kempnerinstitute.bsky.social
on how some of our recent works can be interpreted as an application of rational analysis to language model behaviors — seeing both their successes and failures through the lens of adaptation to the properties of their training data.
After using electrical stimulation to activate their muscles, patients improved movement in their paralyzed limbs even when the system was turned off. The team leading the clinical trial believes new nerve connections may have begun to grow. https://cbsn.ws/43ocCrA
11.05.2025 23:33 — 👍 257 🔁 51 💬 5 📌 8
Big day for the Rajan lab at @harvardmed.bsky.social Friday Seminar Series 🌟
@satpreetsingh.bsky.social & Siyan Zhou gave outstanding talks on collective behaviors in artificial fish schools & disordered attractors in mice. I’m so proud of their work! 🤖🧠
Aran Nayebi (@anayebi.bsky.social): Why NeuroAI Needs NeuroAgents
www.youtube.com/watch?v=s3kl...
Emily Mackevicius: Multi-agent foraging across real-world environments
www.youtube.com/watch?v=8ces...
Kevin Miller (@kevinjmiller.bsky.social): Discovering Interpretable Cognitive Models from Behavior Data
www.youtube.com/watch?v=61_Y...
Kristopher Jensen (@kristorpjensen.bsky.social): Recurrent network models of planning in prefrontal cortex
www.youtube.com/watch?v=baY8...
Margarida Sousa: Dopamine neurons encode a multidimensional probabilistic map of future reward
www.youtube.com/watch?v=HXU8...
Thanks to my co-organizers Organizers:
@chingfang.bsky.social l and @gzmozd.bsky.social!
Thanks to our wonderful speakers Speakers: Margarida Sousa, @kristorpjensen.bsky.social, @kevinjmiller.bsky.social, Emily Mackevicius, @anayebi.bsky.social, @bingbrunton.bsky.social,
@talmo.bsky.social, and Shreya Saxena
Our workshop was very well attended, we hope to hold it again next year!!
📽️Recordings from our
@cosynemeeting.bsky.social
#COSYNE2025 workshop on “Agent-Based Models in Neuroscience: Complex Planning, Embodiment, and Beyond" are now online: neuro-agent-models.github.io
🧠🤖
ML/stats folks!
This might be a stupid question but my brain isn’t working. In control theory, is there a way to directly infer a system’s objective function by just observing its behavior (as opposed to doing model comparison hypothesis tests)?
At @cosynemeeting.bsky.social ? Don't miss the workshop "It's All Connected" or how graph neural networks help us understand the structure-function relationship in the brain🧠
Thanks to the organizers @neurokim.bsky.social @briandepasquale.bsky.social Sam Lewallen 🌟
sites.google.com/bu.edu/gnnwo...
COSYNE 2025 Rajan lab posters. Friday, March 28 - Poster Session 2: 2-043: Emergent small-group foraging under variable group size, food scarcity, and sensory capabilities by Zhouyang (Hanson) Lu, Satpreet H Singh, Sonja Johnson-Yu, Aaron Walsman, Kanaka Rajan 2-058: 'Modeling rapid neuromodulation in the cortex-basal ganglia-thalamus loop' by Julia Costacurta and Yu Duan (co-first), John Assad, Kanaka Rajan and Scott Linderman (co-senior) 2-060: 'Measuring and Controlling Solution Degeneracy across Task-Trained RNNs' by Ann Huang, Satpreet Singh, Kanaka Rajan Saturday, March 29 - Poster Session 3: 3-020: 'ForageWorld: RL agents in complex foraging arenas develop internal maps for navigation and planning' by Ryan Badman, Riley Simmons-Edler, Joshua Lunger, John Vastola, William Qian, Kanaka Rajan 3-109: 'Inhibition-stabilized disordered dynamics in mouse cortex during navigational decision-making' by Siyan Zhou, Ryan Badman, Charlotte Arlt, Kanaka Rajan, Christopher Harvey
Big showing from the Rajan Lab at @cosynemeeting.bsky.social!
We have posters on everything from multi-agent social foraging to neuromodulated neural networks. Catch us in Poster Sessions 2 & 3 🧠🤖
#Cosyne2025 #NeuroAI #CompSci #neuroskyence
Attending #COSYNE2025? Check out our workshop on Agent-based models in Neuroscience on Monday March 31st!
Updated schedule here: neuro-agent-models.github.io
If you are attending the #cosyne2025 Workshops, please come join our Navigation under Uncertainty workshop! An exciting topic and a great line-up of speakers - what's more to ask for?
Details below, and at sites.google.com/view/cosyne2...
Countdown to #COSYNE2025!
Leading up to @cosynemeeting.bsky.social GNN workshop w @neurokim.bsky.social and Sam, allow us to introduce our fabulous speakers, starting with @wesleyqian.bsky.social! Wesley is part of osmo.ai foundling team, using GNNs to digitize smell!
Organizers: @chingfang.bsky.social, @satpreetsingh.bsky.social and @gzmozd.bsky.social
18.02.2025 18:11 — 👍 2 🔁 0 💬 0 📌 0Speakers: Margarida Sousa, @kristorpjensen.bsky.social n.bsky.social, @anayebi.bsky.social bi.bsky.social, @kevinjmiller.bsky.social r.bsky.social, Emily Mackevicius, @satpreetsingh.bsky.social, @bingbrunton.bsky.social ton.bsky.social, @olveczky.bsky.social bsky.social, and Shreya Saxena
18.02.2025 18:11 — 👍 2 🔁 0 💬 1 📌 0🚀 From abstract agent models of behavior to "digital twins" of model organisms, we’ll explore:
* Simulating naturalistic animal behavior using artificial agents
* Embodiment & the role of the body in neural computation
* Using agents to uncover neural mechanisms & inspire experiments
📣 Excited to announce our workshop "Agent-Based Models in Neuroscience: Complex Planning, Embodiment, and Beyond" at the upcoming @cosynemeeting.bsky.social #CoSyNe2025! 🧠🤖 🪱🪰🐟🐝🐭💪
Schedule: neuro-agent-models.github.io
🗓️ Join us in Mont-Tremblant, Canada, on March 31!
Digital illustration of a school of red fish with simple geometric features on a purple background. Some fish are connected by curved dashed and solid lines, suggesting interactions or relationships between them.
Enjoyed sharing our work on electric fish with @dryohanjohn.bsky.social⚡🐟 Their electric "conversations" help us build models to discover neural mechanisms of social cognition. Work led by Sonja Johnson-Yu & @satpreetsingh.bsky.social with Nate Sawtell
kempnerinstitute.harvard.edu/news/what-el...
