iiinova — where your digital self keeps evolving

Reposted by Ábel Ságodi

PessoaBrain @pessoabrain.bsky.social · 15/06/2026

𝗪𝗵𝗮𝘁 𝗮𝗿𝗲 𝗯𝗿𝗮𝗶𝗻𝘀, 𝗮𝗴𝗮𝗶𝗻?? Biological systems unlike computers, but what does that mean? Join us in the Neuroscience & Philosophy Salon discussion with Romain Brette of his great book. July 9, noon (USA-EST) Open to all; registration required. umd.zoom.us/meeting/regi... #neuroskyence

14312

Reposted by Ábel Ságodi

Renato Duarte @rcfduarte.bsky.social · 11/03/2026

I tracked every keyword in 22 years of Cosyne abstracts to map how computational neuroscience evolved — from Bayesian brains to neural manifolds to LLMs — and where it's heading next.

open.substack.com

22 years of Brain Science: what CoSyNe tells us about the evolution of Neuroscience

Tracking the intellectual DNA of Computational and Systems Neuroscience through its flagship meeting

716270

Reposted by Ábel Ságodi

Nancy Kanwisher @nancykanwisher.bsky.social · 12/04/2026

If Hungary can get rid of their corrupt anti democratic menace, so can we! www.nytimes.com/2026/04/12/w...

nytimes.com

Hungary’s Orban, Beacon to the Right, Concedes Election Defeat

0172

Reposted by Ábel Ságodi

Memming Park @memming.bsky.social · 13/03/2026

If you are at #cosyne2026 come see poster [2-152] Dynamical archetype analysis: Autonomous computation. Ábel Ságodi is presenting how you can compare dynamical systems at behaviorally relevant timescale while keeping the interpretability!

1112

Reposted by Ábel Ságodi

mpotta.bsky.social @mpotta.bsky.social · 08/03/2026

Excited to share the schedule for our COSYNE 2026 workshop, 'The Neural Code of Action Sequences,' happening on Monday, March 16. We hope you’ll join us! @cosynemeeting.bsky.social mpotta.github.io/action-seque...

mpotta.github.io

COSYNE 2026 — The Neural Code of Action Sequences

Workshop: The Neural Code of Action Sequences: From Learning to Execution. COSYNE 2026, March 16, 2026.

051

Reposted by Ábel Ságodi

Richard Gao @rdgao.bsky.social · 03/03/2026

Once you get past the first 5 minutes of me bumbling around clearly in need of media training, we settle into a nice groove talking about fitting mechanistic models, ML/AI for neuroscience, underconstrainedness vs. degeneracy, and its potential benefits for biology (plus some good chuckles).

2478

Reposted by Ábel Ságodi

Memming Park @memming.bsky.social · 13/02/2026

New preprint from the lab! Ábel Ságodi developed a theory of approximating dynamical systems that goes beyond finite time. #theoreticalNeuroscience Follow @neurabel.bsky.social Universal Approximation Theorems for Dynamical Systems with Infinite-Time Horizon Guarantees. . arxiv.org/abs/2602.08640

arxiv.org

Universal Approximation Theorems for Dynamical Systems with Infinite-Time Horizon Guarantees

Universal approximation theorems establish the expressive capacity of neural network architectures. For dynamical systems, existing results are limited to finite time horizons or systems with a global...

0187

Ábel Ságodi @neurabel.bsky.social · 12/02/2026

(TL;DR) If you are modeling neural computation over long time scales, "Fading Memory" is a fundamental limitation. We provide the theoretical framework to ensure your model can capture the memories, decisions, and rhythms that actually matter. #NeuroAI #DynamicalSystems #NeuralODEs (6/6)

000

Ábel Ságodi @neurabel.bsky.social · 12/02/2026

Subsequently, we can guarantee a temporal generalization error bound for a given precision and reliability. (5/6)

100

Ábel Ságodi @neurabel.bsky.social · 12/02/2026

Result: We prove you can approximate these dynamics with arbitrary precision and arbitrary reliability. 1️⃣ ε (Precision): Maximum allowed trajectory tracking error 2️⃣ δ (Reliability): How small to shrink the B-type error We prove a Neural ODE exists that satisfies both constraints forever. (4/6)

100

Ábel Ságodi @neurabel.bsky.social · 12/02/2026

Why not just "train longer"? You hit topological walls. We identify three specific failure modes for infinite-time dynamics: 1️⃣ B-type: Tiny errors near a decision boundary switch the outcome. 2️⃣ P-type: Oscillations drift out of phase. 3️⃣ D-type: Continuous attractors break into points. (3/6)

100

Ábel Ságodi @neurabel.bsky.social · 12/02/2026

Decision making & working memory require multistability—distinct basins of attraction to hold a choice or a continuous value. If your model has Fading Memory (like liquid state machines), it must eventually drift back to a global baseline. It literally cannot hold a memory forever. (2/6)

100

Ábel Ságodi @neurabel.bsky.social · 12/02/2026

Can we guarantee the behavior of an RNN to generalize well for infinite time? 🧠♾️ Similar to universal approximation theorems in deep nets, for systems that forget everything eventually, there are guarantees. We prove it for multistable systems! arxiv.org/abs/2602.08640 w/ @memming.bsky.social (1/6)

162

Reposted by Ábel Ságodi

natalia barbour, phd @nataliabarbour.bsky.social · 01/09/2025

Bike math is paying virtually nothing and getting a lot in return. Car math is selling your soul to waste your life in traffic and inhale kilograms of particulate matter.

1147074

Reposted by Ábel Ságodi

Champalimaud Research @champalimaudr.bsky.social · 11/07/2025

💥Good news! You have now until 18 July to submit your abstract for the ⚪ Champalimaud Research Symposium 2025! 🏆 The three best posters and the best talk will be awarded a money prize! We’re looking forward to receiving your submissions 🙌 🔗 More information: symposium.fchampalimaud.science

132