iiinova — where your digital self keeps evolving

Reposted by Fatih Dinc

Geometric Intelligence Lab @geometric-intel.bsky.social · 30/07/2026

🎉Congratulations to Guillermo Bernárdez Gil! Thrilled to share that our postdoc, Guille, has been awarded the 2026 Extraordinary Doctoral Award by the Universitat Politècnica de Catalunya (UPC). Congrats, Guille, so proud to have you on our team👏 🔗https://tinyurl.com/43hbr9t3

275

Reposted by Fatih Dinc

Nina Miolane @ninamiolane.bsky.social · 22/07/2026

Our review on superposition in AI & brains is published in @nature.com #Machine #Intelligence 🌐 Neural networks encode concepts in superposition. We can recover them in 3 steps: identifiability, compressed sensing, interpretability. W/ @david-klindt.bsky.social O'Neil Reizinger & Maurer 🌟

13315

Reposted by Fatih Dinc

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 15/07/2026

A geometric and dynamical theory of latent computations in biological neural networks www.biorxiv.org/content/10.64898/20…

091

Reposted by Fatih Dinc

UCSB Electrical and Computer Engineering Department @ucsbece.bsky.social · 08/07/2026

🔵⚡Big feature in @cnn.com this week on our very own Prof. Shuji Nakamura (Materials & ECE). The man who lit up the world with blue LEDs, and now wants to power it too. 🔗https://tinyurl.com/msm4h9bf @ucsantabarbara.bsky.social @ucsbengineering.bsky.social

154

Fatih Dinc @fatihdinc.bsky.social · 23/06/2026

Why did RNNs fail to learn long-term dependencies? What if we added one more modification, maybe now? It turns out we can give a pretty broad, analytical answer! See the attached paper for a rigorous treatment using centre manifolds, low-rank RNNs, and dynamical systems theory! go.aps.org/4fXWEeF

go.aps.org

Ghost Mechanism: An Analytical Model of Abrupt Learning in Recurrent Networks

This study establishes the ghost mechanism as an underlying mechanism for abrupt learning, whereby the recurrent neural network develops ghost points---transient dynamical bottlenecks---and identifies...

03510

Reposted by Fatih Dinc

Physical Review X @physrevx.aps.org · 23/06/2026

Why do neural networks undergo abrupt learning after training on memory tasks? New research traces this phenomenon to a “ghosting” mechanism that locks the system into a no-learning zone and proposes two practical fixes to address these pitfalls. 📝 go.aps.org/4fXWEeF

Panel B displays a series of four three dimensional graphs plotting the progression of speed minima in the neural activities of full-rank recurrent neural networks (RNNs) performing a DCD task. PC1 is on the x-axis, PC3 is on the y-axis, and PC2 is on the z-axis. The four graphs correlate to Epoch 11, Epoch 201, Epoch 1001, and Epoch 3001, from left to right. The speed minimum is denoted with diamonds. Trial type is denoted with F for fixed-point, S for slow-point, and G for ghost. Cue 1 is denoted with a blue line, and Cue 2 with an orange line. Panel D displays similar graphs but for an RNN performing an DMTS task. Here, match is colored with blue and orange lines, and no-match is colored with green and red lines. On the right, a color scale denotes the normalized speed of the fixed, slow, or ghost points increasing from dark blue to dark red.

062

Fatih Dinc @fatihdinc.bsky.social · 20/06/2026

Blessed to be surrounded by amazing mentors, thank you @andyalexander.bsky.social

010

Reposted by Fatih Dinc

UCSB Electrical and Computer Engineering Department @ucsbece.bsky.social · 18/06/2026

🎉 Congratulations to @fatihdinc.bsky.social, postdoc in UC Santa Barbara #ECE and the Kavli Institute for Theoretical Physics, on winning the Richard C. DiPrima Prize from the Society for Industrial and Applied Mathematics (SIAM). 🏆 🔗 Read the full story: lnkd.in/gd27SUAA

175

Reposted by Fatih Dinc

UCSB Electrical and Computer Engineering Department @ucsbece.bsky.social · 05/05/2026

The Robert Mehrabian College of Engineering is launching METL — the Master of Engineering & Technology Leadership — the first fully online master's degree at UC Santa Barbara, built for working tech professionals around the world 🎓 @ucsbengineering.bsky.social @ucsantabarbara.bsky.social

165

Reposted by Fatih Dinc

andy alexander @andyalexander.bsky.social · 28/04/2026

Very excited to announce the first preprint from the lab @ucsantabarbara.bsky.social -- "Predictive pursuit emerges in high-dimensional RNNs." @wtredman.bsky.social (starting his own group at JHU this fall) summarizes the work nicely in this thread.

13510

Reposted by Fatih Dinc

Will Redman @wtredman.bsky.social · 28/04/2026

New preprint out 🚨 “Predictive pursuit emerges in high-dimensional recurrent neural networks”! This was an awesome collaboration with co-first author @fatihdinc.bsky.social , @andyalexander.bsky.social, @xiaoxiao-lin.bsky.social, and May Chen biorxiv.org/content/10.6... 1/

biorxiv.org

12911

Reposted by Fatih Dinc

Will Redman @wtredman.bsky.social · 12/03/2026

Super excited about this work and to have gotten a chance to work with @andyalexander.bsky.social @fatihdinc.bsky.social @xiaoxiao-lin.bsky.social and May Chan on predictive pursuit in RNNs and mice!

082

Reposted by Fatih Dinc

andy alexander @andyalexander.bsky.social · 12/03/2026

Come check out our poster "[2-018] Predictive pursuit emerges in high dimensions" Friday from 1-4p if you are at #cosyne2016! This work was led (and is presented) by the amazing @wtredman.bsky.social alongside an awesome team incld. @xiaoxiao-lin.bsky.social, @fatihdinc.bsky.social, and May Chan.

2185

Reposted by Fatih Dinc

ai-ucsb.bsky.social @ai-ucsb.bsky.social · 30/01/2026

We’re excited to kick off this year’s REAL AI Seminar Series! 🤖✨ Thrilled to start with @fatihdinc.bsky.social , thanks for joining us to launch the series. Dr. Fatih Dinc gave a wonderful talk on biological versus artificial neural networks 🤯 @ucsbece.bsky.social @geometric-intel.bsky.social

2154

Reposted by Fatih Dinc

Geometric Intelligence Lab @geometric-intel.bsky.social · 30/01/2026

Love to see it from @fatihdinc.bsky.social 😼🐼 Looking forward to seeing future talks from @ai-ucsb.bsky.social @ucsbece.bsky.social

033

Reposted by Fatih Dinc

Mathilde Papillon @mathildepapillon.bsky.social · 01/08/2025

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...

15219

Fatih Dinc @fatihdinc.bsky.social · 06/07/2025

Visiting Wisconsin-Madison this week to attend #SIAMAG25. Would love to connect with fellow researchers, say hi if you are around!

000

Reposted by Fatih Dinc

Blake Richards @tyrellturing.bsky.social · 04/06/2025

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

nature.com

Multi-timescale reinforcement learning in the brain - Nature

Individual dopaminergic neurons encode future rewards over distinct temporal horizons.

28326

Reposted by Fatih Dinc

Martin Carrasco @martin.topology.rocks · 26/05/2025

🚨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)

1125

Fatih Dinc @fatihdinc.bsky.social · 24/04/2025

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.

bridgetoturkiye.org

100

Reposted by Fatih Dinc

Nina Miolane @ninamiolane.bsky.social · 03/03/2025

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

1148

Fatih Dinc @fatihdinc.bsky.social · 08/03/2025

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!

0145