DurstewitzLab

Tomorrow Christoph will present DynaMix, the first foundation model for dynamical systems reconstruction, at #NeurIPS2025 Exhibit Hall C,D,E #2303

Thanks for sharing! Missed it, but just downloaded it, looking forward to get into it ...

What neuroscience can tell AI about learning in continuously changing environments Nature Machine Intelligence - Durstewitz et al. explore what artificial intelligence can learn from the brain’s ability to adjust quickly to changing environments. By linking neuroscience...

Unlike current AI systems, animals can quickly and flexibly adapt to changing environments.

This is the topic of our new perspective in Nature MI (rdcu.be/eSeif), where we relate dynamical and plasticity mechanisms in the brain to in-context and continual learning in AI. #NeuroAI

Revised version of our #NeurIPS2025 paper with full code base in Julia & Python now online, see arxiv.org/abs/2505.13192

Despite being extremely lightweight (only 0.1% of params, 0.6% training corpus size, of closest competitor), it also outperforms major TS foundation models like Chronos variants on real-world TS forecasting with minimal inference times (0.2%) ...

Our #AI #DynamicalSystems #FoundationModel DynaMix was accepted to #NeurIPS2025 with outstanding reviews (6555) – first model which can *zero-shot*, w/o any fine-tuning, forecast the *long-term statistics* of time series provided a context. Test it on #HuggingFace:
huggingface.co/spaces/Durst...

Reconstructing computational system dynamics from neural data with recurrent neural networks - Nature Reviews Neuroscience The prospects for applying dynamical systems theory in neuroscience are changing dramatically. In this Perspective, Durstewitz et al. discuss dynamical system reconstruction using recurrent neural net...

Relevant publications:
www.nature.com/articles/s41...
openreview.net/pdf?id=Vp2OA...
proceedings.mlr.press/v235/brenner...
www.nature.com/articles/s41...

We have openings for several fully-funded positions (PhD & PostDoc) at the intersection of AI/ML, dynamical systems, and neuroscience within a BMFTR-funded Neuro-AI consortium, at Heidelberg University & Central Institute of Mental Health:
www.einzigartigwir.de/en/job-offer...

More info below ...

YouTube video by Gerstner Lab From Spikes To Rates

Is it possible to go from spikes to rates without averaging?

We show how to exactly map recurrent spiking networks into recurrent rate networks, with the same number of neurons. No temporal or spatial averaging needed!

Presented at Gatsby Neural Dynamics Workshop, London.

Public Statement on Supporting Science for the Benefit of All Citizens TO THE AMERICAN PEOPLE We all rely on science. Science gave us the smartphones in our pockets, the navigation systems in our cars, and life-saving medical care. We count on engineers when we drive acr...

Today I joined >1900 members of US National Academies of Science, Engineering & Medicine signing this open letter (views our own).

Leadership of science by US has been paramount for >70yrs & Admin is now acting to throw it all away!

docs.google.com/document/d/1...

www.nytimes.com/2025/03/31/s...

At 17, Hannah Cairo Solved a Major Math Mystery | Quanta Magazine After finding the homeschooling life confining, the teen petitioned her way into a graduate class at Berkeley, where she ended up disproving a 40-year-old conjecture.

What a fantastic accomplishment -- and what a fantastic story! www.quantamagazine.org/at-17-hannah...

Got prov. approval for 2 major grants in Neuro-AI & Dynamical Systems Reconstruction, on learning & inference in non-stationary environments, out-of-domain generalization, and DS foundation models. To all AI/math/DS enthusiasts: Expect job announcements (PhD/PostDoc) soon! Feel free to get in touch.

What Neuroscience Can Teach AI About Learning in Continuously Changing Environments Modern AI models, such as large language models, are usually trained once on a huge corpus of data, potentially fine-tuned for a specific task, and then deployed with fixed parameters. Their training ...

We wrote a little #NeuroAI piece about in-context learning & neural dynamics vs. continual learning & plasticity, both mechanisms to flexibly adapt to changing environments:
arxiv.org/abs/2507.02103
We relate this to non-stationary rule learning tasks with rapid performance jumps.

Feedback welcome!

Yes I think so!

CNS*2025 Florence: NeuroXAI: Explainable AI for Understandi... View more about this event at CNS*2025 Florence

Happy to discuss our work on parsimonious & math. tractable RNNs for dynamical systems reconstruction next week at
cns2025florence.sched.com/event/1z9Mt/...

Abstract rule learning promotes cognitive flexibility in complex environments across species Nature Communications - Whether neurocomputational mechanisms that speed up human learning in changing environments also exist in other species remains unclear. Here, the authors show that both...

Inference in rule shifting tasks: rdcu.be/etlRV

Fantastic work by Florian Bähner, Hazem Toutounji, Tzvetan Popov and many others - I'm just the person advertising!

Abstract rule learning promotes cognitive flexibility in complex environments across species Nature Communications - Whether neurocomputational mechanisms that speed up human learning in changing environments also exist in other species remains unclear. Here, the authors show that both...

How do animals learn new rules? By systematically testing diff. behavioral strategies, guided by selective attn. to rule-relevant cues: rdcu.be/etlRV
Akin to in-context learning in AI, strategy selection depends on the animals' "training set" (prior experience), with similar repr. in rats & humans.

What a line up!! With Lorenzo Gaetano Amato, Demian Battaglia, @durstewitzlab.bsky.social, @engeltatiana.bsky.social,‪ @seanfw.bsky.social‬, Matthieu Gilson, Maurizio Mattia, @leonardopollina.bsky.social‬, Sara Solla.

Into population dynamics? Coming to #CNS2025 but not quite ready to head home?

Come join us! at the Symposium on "Neural Population Dynamics and Latent Representations"! 🧠
📆 July 10th
📍 Scuola Superiore Sant’Anna, Pisa (and online)
👉 Free registration: neurobridge-tne.github.io
#compneuro

I’m really looking so much forward to this! In wonderful Pisa!

Just heading back from a fantastic workshop on neural dynamics at Gatsby/ London, organized by Tatiana Engel, Bruno Averbeck, & Peter Latham.
Enjoyed seeing so many old friends, Memming Park, Carlos Brody, Wulfram Gerstner, Nicolas Brunel & many others …
Discussed our recent DS foundation models …

We dive a bit into the reasons why current time series FMs not trained for DS reconstruction fail, and conclude that a DS perspective on time series forecasting & models may help to advance the #TimeSeriesAnalysis field.

(6/6)

Remarkably, it not only generalizes zero-shot to novel DS, but it can even generalize to new initial conditions and regions of state space not covered by the in-context information.

(5/6)

And no, it’s neither based on Transformers nor Mamba – it’s a new type of mixture-of-experts architecture based on the recently introduced AL-RNN (proceedings.neurips.cc/paper_files/...), specifically trained for DS reconstruction.
#AI

(4/6)

It often even outperforms TS FMs on forecasting diverse empirical time series, like weather, traffic, or medical data, typically used to train TS FMs.

This is surprising, cos DynaMix’ training corpus consists *solely* of simulated limit cycles & chaotic systems, no empirical data at all!

(3/6)

Unlike TS FMs, DynaMix exhibits #ZeroShotLearning of long-term stats of unseen DS, incl. attractor geometry & power spectrum, w/o *any* re-training, just from a context signal.

It does so with only 0.1% of the parameters of Chronos & 10x faster inference times than the closest competitor.

(2/6)

Can time series (TS) #FoundationModels (FM) like Chronos zero-shot generalize to unseen #DynamicalSystems (DS)?

No, they cannot!

But *DynaMix* can, the first TS/DS FM based on principles of DS reconstruction, capturing the long-term evolution of out-of-domain DS: arxiv.org/pdf/2505.131...
(1/6)

I'm presenting our lab's work on *learning generative dynamical systems models from multi-modal and multi-subject data* in the world-wide theoretical neurosci seminar Wed 23rd, 11am ET:
www.wwtns.online

--> incl. recent work on building foundation models for #dynamical-systems reconstruction #AI 🧪

Uncertainty estimation with prediction-error circuits - Nature Communications How the brain integrates sensory input and predictions to adapt to change is not fully understood. Here authors build a neural network model to show how prediction-error neurons compute uncertainty of...

Nature Communications

Uncertainty estimation with prediction-error circuits

www.nature.com/articles/s41...