Fatih Dinc
@fatihdinc.bsky.social
Theoretical neuroscience + explainable AI. @kitp-ucsb.bsky.social and @geometric-intel.bsky.social postdoc. PhD in Applied Physics, Stanford.
Pinned
Fatih Dinc
@fatihdinc.bsky.social
· Mar 8
My PhD work is now out! Here, we set out to formalize the neural manifold hypothesis and explain several experimental phenomena in systems neuroscience with a single theoretical framework. I highly recommend giving it a read, though tweetprint come much later!
Reposted by Fatih Dinc
Our illustrated guide to non-Euclidian ML is finally published!
Check it out for
⭐️ gorgeous figures (with new additions!) on topology, algebra, and geometry in the field
⭐️ broken down tables for easy reading
⭐️ accessible text, additional refs, and more
iopscience.iop.org/article/10.1...
Check it out for
⭐️ gorgeous figures (with new additions!) on topology, algebra, and geometry in the field
⭐️ broken down tables for easy reading
⭐️ accessible text, additional refs, and more
iopscience.iop.org/article/10.1...
August 1, 2025 at 3:24 PM
Our illustrated guide to non-Euclidian ML is finally published!
Check it out for
⭐️ gorgeous figures (with new additions!) on topology, algebra, and geometry in the field
⭐️ broken down tables for easy reading
⭐️ accessible text, additional refs, and more
iopscience.iop.org/article/10.1...
Check it out for
⭐️ gorgeous figures (with new additions!) on topology, algebra, and geometry in the field
⭐️ broken down tables for easy reading
⭐️ accessible text, additional refs, and more
iopscience.iop.org/article/10.1...
Wow! What a great perspective! Congrats @ninamiolane.bsky.social !
Can #AI become a true scientist? @ninamiolane.bsky.social explores how new technologies are reshaping scientific discovery, and why human expertise remains essential as we enter a new era of research powered by intelligent algorithms. 🧪
plos.io/4kZi0aB
plos.io/4kZi0aB
The fifth era of science: Artificial scientific intelligence
Can AI become a true scientist? This Perspective explores how new technologies are reshaping scientific discovery, and why human expertise remains essential as we enter a new era of research powered b...
plos.io
June 11, 2025 at 6:06 PM
Wow! What a great perspective! Congrats @ninamiolane.bsky.social !
Reposted by Fatih Dinc
Two papers out today on RL in the dopaminergic neurons of the midbrain of mice (one from McGill's new PI @paulmasset.bsky.social). Both papers demonstrate heterogeneity in discount factors!
www.nature.com/articles/s41...
nature.com/articles/s41...
🧠📈 🧪 #NeuroAI
www.nature.com/articles/s41...
nature.com/articles/s41...
🧠📈 🧪 #NeuroAI
Multi-timescale reinforcement learning in the brain - Nature
Individual dopaminergic neurons encode future rewards over distinct temporal horizons.
www.nature.com
June 4, 2025 at 4:32 PM
Two papers out today on RL in the dopaminergic neurons of the midbrain of mice (one from McGill's new PI @paulmasset.bsky.social). Both papers demonstrate heterogeneity in discount factors!
www.nature.com/articles/s41...
nature.com/articles/s41...
🧠📈 🧪 #NeuroAI
www.nature.com/articles/s41...
nature.com/articles/s41...
🧠📈 🧪 #NeuroAI
Reposted by Fatih Dinc
🚨Higher-order combinatorial models in TDL are notoriously slow and resource-hungry. Can we do better?
Introducing:
🚀 𝐇𝐎𝐏𝐒𝐄: A Scalable Higher-Order Positional and Structural Encoder for Combinatorial Representations 🚀
📝 arXiv: arxiv.org/abs/2505.15405
🧵 (1/6)
Introducing:
🚀 𝐇𝐎𝐏𝐒𝐄: A Scalable Higher-Order Positional and Structural Encoder for Combinatorial Representations 🚀
📝 arXiv: arxiv.org/abs/2505.15405
🧵 (1/6)
May 26, 2025 at 11:17 AM
🚨Higher-order combinatorial models in TDL are notoriously slow and resource-hungry. Can we do better?
Introducing:
🚀 𝐇𝐎𝐏𝐒𝐄: A Scalable Higher-Order Positional and Structural Encoder for Combinatorial Representations 🚀
📝 arXiv: arxiv.org/abs/2505.15405
🧵 (1/6)
Introducing:
🚀 𝐇𝐎𝐏𝐒𝐄: A Scalable Higher-Order Positional and Structural Encoder for Combinatorial Representations 🚀
📝 arXiv: arxiv.org/abs/2505.15405
🧵 (1/6)
Announcement of a new scholarship program for Turkish students seeking internships in the US!
BTF is now officially accepting funding applications: bridgetoturkiye.org/our-work/schol…
The program requires you to apply with a mentor, who can be a PhD or a postdoc in a US institution.
BTF is now officially accepting funding applications: bridgetoturkiye.org/our-work/schol…
The program requires you to apply with a mentor, who can be a PhD or a postdoc in a US institution.
https://bridgetoturkiye.org/our-work/schol…
April 24, 2025 at 7:35 AM
Announcement of a new scholarship program for Turkish students seeking internships in the US!
BTF is now officially accepting funding applications: bridgetoturkiye.org/our-work/schol…
The program requires you to apply with a mentor, who can be a PhD or a postdoc in a US institution.
BTF is now officially accepting funding applications: bridgetoturkiye.org/our-work/schol…
The program requires you to apply with a mentor, who can be a PhD or a postdoc in a US institution.
Reposted by Fatih Dinc
How does AI memorize information? How does ChatGPT remember your name? How do RNNs keep track of simple numbers?
Our new paper led by Bariscan Kurtkaya & Fatih Dinc explores the geometry of short-term memory in neural networks—revealing limits in how information is stored!🧵
arxiv.org/abs/2502.17433
Our new paper led by Bariscan Kurtkaya & Fatih Dinc explores the geometry of short-term memory in neural networks—revealing limits in how information is stored!🧵
arxiv.org/abs/2502.17433
March 3, 2025 at 4:34 PM
How does AI memorize information? How does ChatGPT remember your name? How do RNNs keep track of simple numbers?
Our new paper led by Bariscan Kurtkaya & Fatih Dinc explores the geometry of short-term memory in neural networks—revealing limits in how information is stored!🧵
arxiv.org/abs/2502.17433
Our new paper led by Bariscan Kurtkaya & Fatih Dinc explores the geometry of short-term memory in neural networks—revealing limits in how information is stored!🧵
arxiv.org/abs/2502.17433
My PhD work is now out! Here, we set out to formalize the neural manifold hypothesis and explain several experimental phenomena in systems neuroscience with a single theoretical framework. I highly recommend giving it a read, though tweetprint come much later!
March 8, 2025 at 11:01 PM
My PhD work is now out! Here, we set out to formalize the neural manifold hypothesis and explain several experimental phenomena in systems neuroscience with a single theoretical framework. I highly recommend giving it a read, though tweetprint come much later!