Cengiz Pehlevan
@cpehlevan.bsky.social
theory of neural networks for natural and artificial intelligence
https://pehlevan.seas.harvard.edu/
https://pehlevan.seas.harvard.edu/
Pinned
Cengiz Pehlevan
@cpehlevan.bsky.social
· Nov 21
We collected lecture notes and blog posts by group members about recent topics in deep learning theory here. Hope it is useful!
pehlevan.seas.harvard.edu/resources-0
pehlevan.seas.harvard.edu/resources-0
Reposted by Cengiz Pehlevan
I’m deeply thankful to my supervisor, Mark Brandon (@markbrandonlab.bsky.social) for his patience, guidance, and constant support throughout this project, and to our collaborators in the Cengiz Pehlevan (@cpehlevan.bsky.social) lab at Harvard for their thoughtful and generous contributions.
January 16, 2026 at 6:48 PM
I’m deeply thankful to my supervisor, Mark Brandon (@markbrandonlab.bsky.social) for his patience, guidance, and constant support throughout this project, and to our collaborators in the Cengiz Pehlevan (@cpehlevan.bsky.social) lab at Harvard for their thoughtful and generous contributions.
Reposted by Cengiz Pehlevan
All theory is wrong until verified by data. Greatly indebted to @mhyaghoubi.bsky.social, @markbrandonlab.bsky.social, @douglasresearch.bsky.social for finding the hippocampus encoding reward prediction! Grateful to my advisor @cpehlevan.bsky.social, @kempnerinstitute.bsky.social.
#RL #hippocampus
#RL #hippocampus
January 19, 2026 at 9:32 AM
All theory is wrong until verified by data. Greatly indebted to @mhyaghoubi.bsky.social, @markbrandonlab.bsky.social, @douglasresearch.bsky.social for finding the hippocampus encoding reward prediction! Grateful to my advisor @cpehlevan.bsky.social, @kempnerinstitute.bsky.social.
#RL #hippocampus
#RL #hippocampus
Delighted to have contributed to this work. Huge kudos to everyone involved.
I’m very happy to share the latest from my lab published in @Nature
Hippocampal neurons that initially encode reward shift their tuning over the course of days to precede or predict reward.
Full text here:
rdcu.be/eY5nh
Hippocampal neurons that initially encode reward shift their tuning over the course of days to precede or predict reward.
Full text here:
rdcu.be/eY5nh
January 15, 2026 at 12:20 AM
Delighted to have contributed to this work. Huge kudos to everyone involved.
Reposted by Cengiz Pehlevan
I’m very happy to share the latest from my lab published in @Nature
Hippocampal neurons that initially encode reward shift their tuning over the course of days to precede or predict reward.
Full text here:
rdcu.be/eY5nh
Hippocampal neurons that initially encode reward shift their tuning over the course of days to precede or predict reward.
Full text here:
rdcu.be/eY5nh
January 14, 2026 at 9:32 PM
I’m very happy to share the latest from my lab published in @Nature
Hippocampal neurons that initially encode reward shift their tuning over the course of days to precede or predict reward.
Full text here:
rdcu.be/eY5nh
Hippocampal neurons that initially encode reward shift their tuning over the course of days to precede or predict reward.
Full text here:
rdcu.be/eY5nh
Reposted by Cengiz Pehlevan
Very excited about this new work from the omnipotent Owen, with me and Ashok Litwin-Kumar! Can we reconcile low- and high-dimensional activity in neural circuits by recognizing that these circuits ~multitask~?
(Plausibly, yes 😊)
(Plausibly, yes 😊)
1/X Excited to present this preprint on multi-tasking, with
@david-g-clark.bsky.social and Ashok Litwin-Kumar! Timely too, as “low-D manifold” has been trending again. (If you read thru the end, we escape Flatland and return to the glorious high-D world we deserve.) www.biorxiv.org/content/10.6...
@david-g-clark.bsky.social and Ashok Litwin-Kumar! Timely too, as “low-D manifold” has been trending again. (If you read thru the end, we escape Flatland and return to the glorious high-D world we deserve.) www.biorxiv.org/content/10.6...
A theory of multi-task computation and task selection
Neural activity during the performance of a stereotyped behavioral task is often described as low-dimensional, occupying only a limited region in the space of all firing-rate patterns. This region has...
www.biorxiv.org
December 15, 2025 at 8:17 PM
Very excited about this new work from the omnipotent Owen, with me and Ashok Litwin-Kumar! Can we reconcile low- and high-dimensional activity in neural circuits by recognizing that these circuits ~multitask~?
(Plausibly, yes 😊)
(Plausibly, yes 😊)
Reposted by Cengiz Pehlevan
Congratulations to #KempnerInstitute community members @msalbergo.bsky.social and @mweber.bsky.social — recipients of @schmidtsciences.bsky.social AI2050 Fellowships! 🎉
Discover their innovative research shaping the future of AI 👉 bit.ly/47Do4R3
#AI
Discover their innovative research shaping the future of AI 👉 bit.ly/47Do4R3
#AI
Schmidt Sciences Awards Early Career Fellowships to Michael Albergo, Melanie Weber - Kempner Institute
Two Kempner Institute community members have received AI2050 Fellowships from Schmidt Sciences, a nonprofit organization aimed at accelerating scientific knowledge and breakthroughs. The AI2050 Progra...
bit.ly
November 6, 2025 at 8:10 PM
Congratulations to #KempnerInstitute community members @msalbergo.bsky.social and @mweber.bsky.social — recipients of @schmidtsciences.bsky.social AI2050 Fellowships! 🎉
Discover their innovative research shaping the future of AI 👉 bit.ly/47Do4R3
#AI
Discover their innovative research shaping the future of AI 👉 bit.ly/47Do4R3
#AI
Reposted by Cengiz Pehlevan
First paper from the lab!
We propose a model that separates estimation of odor concentration and presence and map it on olfactory bulb circuits
Led by @chenjiang01.bsky.social and @mattyizhenghe.bsky.social joint work with @jzv.bsky.social and with @neurovenki.bsky.social @cpehlevan.bsky.social
We propose a model that separates estimation of odor concentration and presence and map it on olfactory bulb circuits
Led by @chenjiang01.bsky.social and @mattyizhenghe.bsky.social joint work with @jzv.bsky.social and with @neurovenki.bsky.social @cpehlevan.bsky.social
Simultaneous detection and estimation in olfactory sensing https://www.biorxiv.org/content/10.1101/2025.11.01.686013v1
November 4, 2025 at 3:40 PM
First paper from the lab!
We propose a model that separates estimation of odor concentration and presence and map it on olfactory bulb circuits
Led by @chenjiang01.bsky.social and @mattyizhenghe.bsky.social joint work with @jzv.bsky.social and with @neurovenki.bsky.social @cpehlevan.bsky.social
We propose a model that separates estimation of odor concentration and presence and map it on olfactory bulb circuits
Led by @chenjiang01.bsky.social and @mattyizhenghe.bsky.social joint work with @jzv.bsky.social and with @neurovenki.bsky.social @cpehlevan.bsky.social
Reposted by Cengiz Pehlevan
Now in PRX: Theory linking connectivity structure to collective activity in nonlinear RNNs!
For neuro fans: conn. structure can be invisible in single neurons but shape pop. activity
For low-rank RNN fans: a theory of rank=O(N)
For physics fans: fluctuations around DMFT saddle⇒dimension of activity
For neuro fans: conn. structure can be invisible in single neurons but shape pop. activity
For low-rank RNN fans: a theory of rank=O(N)
For physics fans: fluctuations around DMFT saddle⇒dimension of activity
Connectivity Structure and Dynamics of Nonlinear Recurrent Neural Networks
The structure of brain connectivity predicts collective neural activity, with a small number of connectivity features determining activity dimensionality, linking circuit architecture to network-level...
journals.aps.org
November 3, 2025 at 9:47 PM
Now in PRX: Theory linking connectivity structure to collective activity in nonlinear RNNs!
For neuro fans: conn. structure can be invisible in single neurons but shape pop. activity
For low-rank RNN fans: a theory of rank=O(N)
For physics fans: fluctuations around DMFT saddle⇒dimension of activity
For neuro fans: conn. structure can be invisible in single neurons but shape pop. activity
For low-rank RNN fans: a theory of rank=O(N)
For physics fans: fluctuations around DMFT saddle⇒dimension of activity
Reposted by Cengiz Pehlevan
Reposted by Cengiz Pehlevan
Applying to do a postdoc or PhD in theoretical ML or neuroscience this year? Consider joining my group (starting next Fall) at UT Austin!
POD Postdoc: oden.utexas.edu/programs-and... CSEM PhD: oden.utexas.edu/academics/pr...
POD Postdoc: oden.utexas.edu/programs-and... CSEM PhD: oden.utexas.edu/academics/pr...
October 23, 2025 at 9:36 PM
Applying to do a postdoc or PhD in theoretical ML or neuroscience this year? Consider joining my group (starting next Fall) at UT Austin!
POD Postdoc: oden.utexas.edu/programs-and... CSEM PhD: oden.utexas.edu/academics/pr...
POD Postdoc: oden.utexas.edu/programs-and... CSEM PhD: oden.utexas.edu/academics/pr...
Reposted by Cengiz Pehlevan
William Qian, Cengiz Pehlevan: Discovering alternative solutions beyond the simplicity bias in recurrent neural networks https://arxiv.org/abs/2509.21504 https://arxiv.org/pdf/2509.21504 https://arxiv.org/html/2509.21504
September 29, 2025 at 6:50 AM
William Qian, Cengiz Pehlevan: Discovering alternative solutions beyond the simplicity bias in recurrent neural networks https://arxiv.org/abs/2509.21504 https://arxiv.org/pdf/2509.21504 https://arxiv.org/html/2509.21504
Reposted by Cengiz Pehlevan
⏳ Less than 1 day left until the Brain & Mind Workshop submission deadline!
🔍 Submit to our Finding or Tutorials track on OpenReview.
Findings track submission: openreview.net/group?id=Neu...
Tutorial track submission: openreview.net/group?id=Neu...
More info: data-brain-mind.github.io
🔍 Submit to our Finding or Tutorials track on OpenReview.
Findings track submission: openreview.net/group?id=Neu...
Tutorial track submission: openreview.net/group?id=Neu...
More info: data-brain-mind.github.io
NeurIPS 2025 Workshop DBM Findings
Welcome to the OpenReview homepage for NeurIPS 2025 Workshop DBM Findings
openreview.net
September 7, 2025 at 4:30 PM
⏳ Less than 1 day left until the Brain & Mind Workshop submission deadline!
🔍 Submit to our Finding or Tutorials track on OpenReview.
Findings track submission: openreview.net/group?id=Neu...
Tutorial track submission: openreview.net/group?id=Neu...
More info: data-brain-mind.github.io
🔍 Submit to our Finding or Tutorials track on OpenReview.
Findings track submission: openreview.net/group?id=Neu...
Tutorial track submission: openreview.net/group?id=Neu...
More info: data-brain-mind.github.io
Reposted by Cengiz Pehlevan
Since I'm back on BlueSky - with @frostedblakess.bsky.social and @cpehlevan.bsky.social we wrote a brief perspective on how ideas about summary statistics from the statistical physics of learning could potentially help inform neural data analysis... (1/2)
Frontiers | Summary statistics of learning link changing neural representations to behavior
How can we make sense of large-scale recordings of neural activity across learning? Theories of neural network learning with their origins in statistical phy...
www.frontiersin.org
September 4, 2025 at 6:30 PM
Since I'm back on BlueSky - with @frostedblakess.bsky.social and @cpehlevan.bsky.social we wrote a brief perspective on how ideas about summary statistics from the statistical physics of learning could potentially help inform neural data analysis... (1/2)
Reposted by Cengiz Pehlevan
Excited to share new computational work, led by @jzv.bsky.social, driven by Juan Carlos Fernandez del Castillo + contribution from Farhad Pashakanloo. We recover 3 core motifs in the olfactory system of evolutionarily distant animals using a biophysically-grounded model + efficient coding ideas!
Convergent motifs of early olfactory processing are recapitulated by layer-wise efficient coding
The architecture of early olfactory processing is a striking example of convergent evolution. Typically, a panel of broadly tuned receptors is selectively expressed in sensory neurons (each neuron exp...
www.biorxiv.org
September 4, 2025 at 4:51 PM
Excited to share new computational work, led by @jzv.bsky.social, driven by Juan Carlos Fernandez del Castillo + contribution from Farhad Pashakanloo. We recover 3 core motifs in the olfactory system of evolutionarily distant animals using a biophysically-grounded model + efficient coding ideas!
Reposted by Cengiz Pehlevan
Great to have this video about my @darpa.mil Artificial Intelligence Quantified (AIQ) program out! Very exciting program with absolutely fantastic teams. Stay tuned for some jaw dropping announcements!
www.youtube.com/watch?v=KVRF...
www.youtube.com/watch?v=KVRF...
AIQ: Artificial Intelligence Quantified
YouTube video by DARPAtv
www.youtube.com
September 2, 2025 at 9:50 PM
Great to have this video about my @darpa.mil Artificial Intelligence Quantified (AIQ) program out! Very exciting program with absolutely fantastic teams. Stay tuned for some jaw dropping announcements!
www.youtube.com/watch?v=KVRF...
www.youtube.com/watch?v=KVRF...
Reposted by Cengiz Pehlevan
I am extremely grateful to be awarded the National University of Singapore (NUS) Development Grant, and to be a Young NUS Fellow! Look forward to collaborating with the Yong Loo Lin School of Medicine on exciting projects. This is my first grant and hopefully many more to come! #NUS #NeuroAI
August 27, 2025 at 2:31 PM
Reposted by Cengiz Pehlevan
Our new Simons Collaboration on the Physics of Learning and Neural Computation will develop powerful tools from #physics, #math, computer science and theoretical #neuroscience to understand how large neural networks learn, compute, scale, reason and imagine: www.simonsfoundation.org/2025/08/18/s...
Simons Foundation Launches Collaboration on the Physics of Learning and Neural Computation
Simons Foundation Launches Collaboration on the Physics of Learning and Neural Computation on Simons Foundation
www.simonsfoundation.org
August 19, 2025 at 2:43 PM
Our new Simons Collaboration on the Physics of Learning and Neural Computation will develop powerful tools from #physics, #math, computer science and theoretical #neuroscience to understand how large neural networks learn, compute, scale, reason and imagine: www.simonsfoundation.org/2025/08/18/s...
Reposted by Cengiz Pehlevan
If you work on artificial or natural intelligence and are finishing your PhD, consider applying for a Kempner research fellowship at Harvard:
kempnerinstitute.harvard.edu/kempner-inst...
kempnerinstitute.harvard.edu/kempner-inst...
Kempner Research Fellowship - Kempner Institute
The Kempner brings leading, early-stage postdoctoral scientists to Harvard to work on projects that advance the fundamental understanding of intelligence.
kempnerinstitute.harvard.edu
August 18, 2025 at 5:27 PM
If you work on artificial or natural intelligence and are finishing your PhD, consider applying for a Kempner research fellowship at Harvard:
kempnerinstitute.harvard.edu/kempner-inst...
kempnerinstitute.harvard.edu/kempner-inst...
Reposted by Cengiz Pehlevan
Congratulations to #KempnerInstitute associate faculty member @cpehlevan.bsky.social for joining the new
@simonsfoundation.org Simons Collaboration on the Physics of Learning and Neural Computation!
www.simonsfoundation.org/2025/08/18/s...
#AI #neuroscience #NeuroAI #physics #ANNs
@simonsfoundation.org Simons Collaboration on the Physics of Learning and Neural Computation!
www.simonsfoundation.org/2025/08/18/s...
#AI #neuroscience #NeuroAI #physics #ANNs
Simons Foundation Launches Collaboration on the Physics of Learning and Neural Computation
Simons Foundation Launches Collaboration on the Physics of Learning and Neural Computation on Simons Foundation
www.simonsfoundation.org
August 18, 2025 at 6:57 PM
Congratulations to #KempnerInstitute associate faculty member @cpehlevan.bsky.social for joining the new
@simonsfoundation.org Simons Collaboration on the Physics of Learning and Neural Computation!
www.simonsfoundation.org/2025/08/18/s...
#AI #neuroscience #NeuroAI #physics #ANNs
@simonsfoundation.org Simons Collaboration on the Physics of Learning and Neural Computation!
www.simonsfoundation.org/2025/08/18/s...
#AI #neuroscience #NeuroAI #physics #ANNs
Reposted by Cengiz Pehlevan
Very excited to lead this new @simonsfoundation.org collaboration on the physics of learning and neural computation to develop powerful tools from physics, math, CS, stats, neuro and more to elucidate the scientific principles underlying AI. See our website for more: www.physicsoflearning.org
August 18, 2025 at 5:48 PM
Very excited to lead this new @simonsfoundation.org collaboration on the physics of learning and neural computation to develop powerful tools from physics, math, CS, stats, neuro and more to elucidate the scientific principles underlying AI. See our website for more: www.physicsoflearning.org
Reposted by Cengiz Pehlevan
🚨 Excited to announce our #NeurIPS2025 Workshop: Data on the Brain & Mind
📣 Call for: Findings (4- or 8-page) + Tutorials tracks
🎙️ Speakers include @dyamins.bsky.social @lauragwilliams.bsky.social @cpehlevan.bsky.social
🌐 Learn more: data-brain-mind.github.io
📣 Call for: Findings (4- or 8-page) + Tutorials tracks
🎙️ Speakers include @dyamins.bsky.social @lauragwilliams.bsky.social @cpehlevan.bsky.social
🌐 Learn more: data-brain-mind.github.io
August 4, 2025 at 3:28 PM
🚨 Excited to announce our #NeurIPS2025 Workshop: Data on the Brain & Mind
📣 Call for: Findings (4- or 8-page) + Tutorials tracks
🎙️ Speakers include @dyamins.bsky.social @lauragwilliams.bsky.social @cpehlevan.bsky.social
🌐 Learn more: data-brain-mind.github.io
📣 Call for: Findings (4- or 8-page) + Tutorials tracks
🎙️ Speakers include @dyamins.bsky.social @lauragwilliams.bsky.social @cpehlevan.bsky.social
🌐 Learn more: data-brain-mind.github.io
Reposted by Cengiz Pehlevan
The post is based on a paper written with Yue M. Lu., @jzv.bsky.social, Anindita Maiti and @cpehlevan.bsky.social evan.
Check it out now at PNAS:
doi.org/10.1073/pnas...
(2/2)
Check it out now at PNAS:
doi.org/10.1073/pnas...
(2/2)
PNAS
Proceedings of the National Academy of Sciences (PNAS), a peer reviewed journal of the National Academy of Sciences (NAS) - an authoritative source of high-impact, original research that broadly spans...
doi.org
July 28, 2025 at 7:26 PM
The post is based on a paper written with Yue M. Lu., @jzv.bsky.social, Anindita Maiti and @cpehlevan.bsky.social evan.
Check it out now at PNAS:
doi.org/10.1073/pnas...
(2/2)
Check it out now at PNAS:
doi.org/10.1073/pnas...
(2/2)
Reposted by Cengiz Pehlevan
New in the #DeeperLearningBlog: the #KempnerInstitute's Mary Letey presents work recently published in PNAS that offers generalizable insights into in-context learning (ICL) in an analytically-solvable model architecture.
bit.ly/4lPK15p
#AI @pnas.org
(1/2)
bit.ly/4lPK15p
#AI @pnas.org
(1/2)
Solvable Model of In-Context Learning Using Linear Attention - Kempner Institute
Attention-based architectures are a powerful force in modern AI. In particular, the emergence of in-context learning enables these models to perform tasks far beyond the original next-token prediction...
kempnerinstitute.harvard.edu
July 28, 2025 at 7:24 PM
New in the #DeeperLearningBlog: the #KempnerInstitute's Mary Letey presents work recently published in PNAS that offers generalizable insights into in-context learning (ICL) in an analytically-solvable model architecture.
bit.ly/4lPK15p
#AI @pnas.org
(1/2)
bit.ly/4lPK15p
#AI @pnas.org
(1/2)
Reposted by Cengiz Pehlevan
At #ICML2025, presenting work done at @flatironinstitute.org w Matt Smart and @albertobietti.bsky.social on in-context denoising (arxiv.org/abs/2502.05164). Come to Matt’s oral, Thursday, 4:15-4:30 PM, West Ballroom A, and see us right after at poster #E-3207, 4:30-7:00 PM, East Exhibition Hall A-B.
In-context denoising with one-layer transformers: connections between attention and associative memory retrieval
We introduce in-context denoising, a task that refines the connection between attention-based architectures and dense associative memory (DAM) networks, also known as modern Hopfield networks. Using a...
arxiv.org
July 16, 2025 at 6:37 PM
At #ICML2025, presenting work done at @flatironinstitute.org w Matt Smart and @albertobietti.bsky.social on in-context denoising (arxiv.org/abs/2502.05164). Come to Matt’s oral, Thursday, 4:15-4:30 PM, West Ballroom A, and see us right after at poster #E-3207, 4:30-7:00 PM, East Exhibition Hall A-B.
Great to see this one finally out in PNAS! Asymptotic theory of in-context learning by linear attention www.pnas.org/doi/10.1073/... Many thanks to my amazing co-authors Yue Lu, Mary Letey, Jacob Zavatone-Veth @jzv.bsky.social and Anindita Maiti!
Asymptotic theory of in-context learning by linear attention | PNAS
Transformers have a remarkable ability to learn and execute tasks based on examples
provided within the input itself, without explicit prior traini...
www.pnas.org
July 11, 2025 at 7:33 AM
Great to see this one finally out in PNAS! Asymptotic theory of in-context learning by linear attention www.pnas.org/doi/10.1073/... Many thanks to my amazing co-authors Yue Lu, Mary Letey, Jacob Zavatone-Veth @jzv.bsky.social and Anindita Maiti!