iiinova — where your digital self keeps evolving

Reposted by A Erdem Sagtekin

Colin Bredenberg @colin-bredenberg.bsky.social · 09/10/2026

Hi all, I'm happy to announce that I have started at the University of Oregon as an assistant professor! My group will use computational methods to study learning and synaptic plasticity. I will be hiring grad students this year--please reach out if you're interested! colinbre@uoregon.edu

36320

Reposted by A Erdem Sagtekin

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 08/10/2026

Neural circuit mechanisms for multi-tasking www.biorxiv.org/content/10.64898/20…

092

Reposted by A Erdem Sagtekin

Matthijs Pals @matthijspals.bsky.social · 02/10/2026

What kind of dynamics underlie sequence working memory? In the last project of my PhD we developed and analysed RNNs fitted to multi-session single-unit data of macaques. Now out on: www.biorxiv.org/content/10.6... With @jakhmack.bsky.social and data from Chen et al., Neuron 2024. [1/4]

14820

Reposted by A Erdem Sagtekin

David G. Clark @david-g-clark.bsky.social · 31/07/2026

This September, I will join the @flatironinstitute.org Center for Computational Neuroscience as a Group Leader, where I will launch the High-Dimensional Dynamics & Computation Group. Information for postdocs and grad students is forthcoming. I am grateful to my mentors who made this possible!

Exterior view of the Flatiron Institute in Manhattan

810411

Reposted by A Erdem Sagtekin

Alex Williams @itsneuronal.bsky.social · 19/03/2026

Cosyne invited me to give a long tutorial (4 hours!) on methods to quantify differences high-d neural recordings across animals, brain regions, deep neural nets, etc. The recording is up on youtube. I hope it inspires more research on this fundamental topic! www.youtube.com/watch?v=n44x...

youtube.com

Cosyne 2026 - Cosyne Tutorial: Comparative Analysis of Neural Population Codes

YouTube video by Cosyne Talks

316156

Reposted by A Erdem Sagtekin

David G. Clark @david-g-clark.bsky.social · 04/03/2026

I am totally pumped about this new work . "Task-trained RNNs" are a powerful and influential framework in neuroscience, but have lacked a firm theoretical footing. This work provides one, and makes direct contact with the classical theory of random RNNs: www.biorxiv.org/content/10.6...

29432

A Erdem Sagtekin @aesagtekin.bsky.social · 08/01/2026

7/7 Overall, EF is a powerful temporal credit assignment mechanism and a promising candidate model for learning in biological systems. It was an incredible experience working on this with @colin-bredenberg.bsky.social and Cristina, and I’m looking forward to feedback and discussing error forcing!

050

A Erdem Sagtekin @aesagtekin.bsky.social · 08/01/2026

6/7 We tried three different tasks with varying difficulties and showed that using EF together with BPTT improves learning, relative to using TF with BPTT or using BPTT alone. For biological plausibility, we also tried error forcing with RFLO, and found that it can improve RFLO as well.

$Multi-panel figure comparing Error Forcing, Teacher Forcing, and backpropagation through time on three RNN tasks: delayed XOR, sine wave generation, and evidence integration. Across increasing delay and task settings, Error Forcing consistently yields a higher fraction of networks that learn and lower test error than Teacher Forcing or backpropagation alone.$

110

A Erdem Sagtekin @aesagtekin.bsky.social · 08/01/2026

5/7 We then provided a probabilistic perspective, showing that EF is an approximation to the expectation-maximization algorithm with a reparameterization trick, where, in the E step, neural activities are adjusted, and, in the M step, synaptic weights are adjusted (similar to predictive coding).

111

A Erdem Sagtekin @aesagtekin.bsky.social · 08/01/2026

4/7 We first showed this by providing a geometric perspective. In scenarios where the dimensionality of the network is higher than that of the output, TF overconstrains the network dynamics during learning, which degrades its benefits. In contrast, EF minimally intervenes in the network dynamics.

Three-panel schematic comparing BPTT, Teacher Forcing, and Error Forcing in a two-dimensional neuron-activity space. A diagonal “zero-error manifold” is shown; BPTT follows a free-running state trajectory, Teacher Forcing projects to a fixed target state on the manifold, and Error Forcing produces corrected states that are more flexible.

120

A Erdem Sagtekin @aesagtekin.bsky.social · 08/01/2026

3/7 Building on their work, as well as Kenji Doya’s and many others’, we realized that a slight modification to teacher forcing, in which we feed the error in a specific way (hence the name Error Forcing) rather than feeding the teacher (target) activity to RNN states, leads to better optimization.

120

A Erdem Sagtekin @aesagtekin.bsky.social · 08/01/2026

2/7 In our NeurIPS 2025 spotlight paper, we introduced Error Forcing (EF). Our method builds on Teacher Forcing (TF), a beautiful method proposed more than 35 years ago to improve RNN learning. Recently, the Durstewitz Lab elegantly showed the benefits of Generalized Teacher Forcing.

110

A Erdem Sagtekin @aesagtekin.bsky.social · 08/01/2026

1/7 How should feedback signals influence a network during learning? Should they first adjust synaptic weights, which then indirectly change neural activity (as in backprop.)? Or should they first adjust neural activity to guide synaptic updates (e.g., target prop.)? openreview.net/forum?id=xVI...

Diagram of a recurrent neural network: input goes into the network, output is compared to a target to produce an error, and dotted feedback arrows show updates to neural activity and to synaptic weights.

1435

Reposted by A Erdem Sagtekin

Owen Marschall @omarschall.bsky.social · 15/12/2025

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...

biorxiv.org

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...

18721

Reposted by A Erdem Sagtekin

Friedemann Zenke @fzenke.bsky.social · 27/05/2025

1/6 Why does the brain maintain such precise excitatory-inhibitory balance? Our new preprint explores a provocative idea: Small, targeted deviations from this balance may serve a purpose: to encode local error signals for learning. www.biorxiv.org/content/10.1... led by @jrbch.bsky.social

518257

Reposted by A Erdem Sagtekin

Matthijs Pals @matthijspals.bsky.social · 11/12/2024

How to find all fixed points in piece-wise linear recurrent neural networks (RNNs)? A short thread 🧵  In RNNs with N units with ReLU(x-b) activations the phase space is partioned in 2^N regions by hyperplanes at x=b 1/7

16312

Reposted by A Erdem Sagtekin

David G. Clark @david-g-clark.bsky.social · 03/12/2024

(1/5) Fun fact: Several classic results in the stat. mech. of learning can be derived in a couple lines of simple algebra! In this paper with Haim Sompolinsky, we simplify and unify derivations for high-dimensional convex learning problems using a bipartite cavity method. arxiv.org/abs/2412.01110

arxiv.org

Simplified derivations for high-dimensional convex learning problems

Statistical physics provides tools for analyzing high-dimensional problems in machine learning and theoretical neuroscience. These calculations, particularly those using the replica method, often invo...

25716

A Erdem Sagtekin @aesagtekin.bsky.social · 09/11/2024

This list likely reflects mainly my interests and circle, and I’m sure I’ve missed many people, but I gave it a try: (I’ll be slowly editing it until it reaches 150/150) go.bsky.app/7VFUkdn (also, I tried but couldn't remove my profile...)

go.bsky.app

Comp Neuro Starter Pack

Join the conversation

488151

A Erdem Sagtekin @aesagtekin.bsky.social · 01/11/2024

i enjoyed reading the geometry of plasticity paper and felt that something important was coming, this is it:

141