DurstewitzLab
@DurstewitzLab
Scientific machine learning, AI & data analysis, dynamical systems theory, applications in (computat.) neuroscience & psychiatry. @durstewitzlab.bsky.social
Our new preprint compares naïve baselines, network models (incl. PLRNN-based SSMs), and Transformers on 3x40‑day EMA+EMI datasets. PLRNNs gave the most accurate forecasts, yielded interpretable networks, and flagged “sad” & “down” as top leverage points. doi.org/10.1101/2025.0…
Got prov. approval for 2 major grants in Neuro-AI & Dynamical Systems Recons., on learning & inference in non-stationary environments, OOD generalization, and DS foundation models. To all AI/math enthusiasts: Expect job announcements (PhD/PostDoc) soon! Feel free to get in touch.
Mathematics & kindness
Which important skill is slowly fading
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 w rapid jumps. Feedback welcome!
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 📍@ScuolaSantAnna, Pisa (and online) Free registration: 👉neurobridge-tne.github.io
Our revised #ICLR2025 paper & code for a foundation model architecture for dynamical systems is now online: openreview.net/pdf?id=Vp2OAxM… ... incl. add. examples of how this may be used for identifying drivers (control par.) of non-stationary processes. And please switch platform!
Interested in interpretable #AI foundation models for #DynamicalSystems reconstruction? In a new paper we move into this direction, training common latent DSR models with system-specific features on data from multiple different dynamic regimes and DS: arxiv.org/pdf/2410.04814 1/4
Transfer & few-shot learning for dynamical systems ... our paper just got accepted for #ICLR2025 @iclr_conf ! Thread below; strongly updated version will be available soon ... ... and don't forget to move to bsky! durstewitzlab.bsky.social
Interested in interpretable #AI foundation models for #DynamicalSystems reconstruction? In a new paper we move into this direction, training common latent DSR models with system-specific features on data from multiple different dynamic regimes and DS: arxiv.org/pdf/2410.04814 1/4
Periodic reminder that MSE or explained var. are not good stats for assessing quality of dynamical systems reconstructions, cos of exponential trajectory divergence in chaotic systems. And please follow us at durstewitzlab.bsky.social !
Can really recommend this excellent talk by Christoph Bergmeir at neurips.cc/virtual/2024/w… yesterday … on the inability of Transformer- & LLM-based recent time series models to beat even simple baselines *if you do the stats and testing right*! A lesson in careful stat. eval.
📢PhD position @BristolUni (with Ross Purple and @seanfw, UK) and joint supervision @SantAnnaPisa (with @russo_eleon, IT) on the reinforcement of traumatic memories during sleep using advanced machine learning techniques. Deadline: 6 Jan. 2025 Detailed project information here👇