Manuel Brenner

Theoretical neuroscience @durstewitzlab with applications to psychiatry. Medium writer @ Science podcaster @

[Towards Data Science @TDataScience]

The field of ML has evolved to balance these 2 forces: leveraging the simplicity of linear models where possible, while incorporating nonlinearity to handle the complexity of the world. Read more from @brenner_manuel.

#LLM #MachineLearning

https://t.co/9u3Z4rqgWP

[DurstewitzLab @DurstewitzLab]

Symbolic dynamics bridges from #DynamicalSystems to computation/ #AI!

In our #NeurIPS2024 (@NeurIPSConf) paper we present a new network architecture, Almost-Linear RNNs, that finds most parsimonious piecewise-linear representations of DS from data: https://t.co/sePJ4WHGkg

1/4

[DurstewitzLab @DurstewitzLab]

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:
https://t.co/uaf1RcyTBi
1/4

[DurstewitzLab @DurstewitzLab]

This is awesome - using neural flow operators trained by multimodal teacher forcing to produce generative dynamics models of human behavior in social contexts ... social strategies as attractors in state space!

[DurstewitzLab @DurstewitzLab]

Just wanted to stop by & say: We have 2 new accepted #NeurIPS2024 papers:

1) @brenner_manuel , Hemmer, @Zahra__Monfared, DD:
Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems Reconstruction
--> *this takes DSR to a new level!*, details to follow

[Georgia Koppe @GeorgiaKoppe]

Creating digital twins of social interaction behavior with #AI! Our study shows how generative models can predict interactions from limited data, revealing hidden dynamics. Together with @brenner_manuel @DurstewitzLab. Explore: https://t.co/4zoEniAQcc #DigitalTwin #SocialBehavior

[IMMERSE Project 🧠📱 @immerse_project]

⚠️New paper out in Psychological Medicine⚠️ The experience sampling methodology as a digital clinical tool for more person-centered mental health care: an implementation research agenda.

Read it here https://t.co/vopCy3AXLO

[DurstewitzLab @DurstewitzLab]

Weight pruning by size is a standard #ML #AI technique to produce sparse models, but in our @icmlconf paper https://t.co/R3u5M3cxkX we find it doesn’t work for learning #DynamicalSystems!

Instead, via geometry-based pruning we find *network topology* is far more important! (1/5)

[DurstewitzLab @DurstewitzLab]

3) Integrating Multimodal Data for Joint Generative Modeling of Complex Dynamics
(prelim. vers.: https://t.co/9SFba4iiyC)

Fantastic teamwork, as usual, by @niclas_goering, Florian Hess, @brenner_manuel, @Zahra__Monfared, Jürgen Hemmer, @GeorgiaKoppe

[DurstewitzLab @DurstewitzLab]

Cool, 3 papers accepted at #icml2024:

1) Out-of-Domain Generalization in Dynamical Systems Reconstruction
(prelim. vers.: https://t.co/urxNeLE6wh)

2) Optimal Recurrent Network Topologies for Dynamical Systems Reconstruction
(details to follow)

...

[DurstewitzLab @DurstewitzLab]

Can we learn from time series data a dynamical systems model that *generalizes* to unobserved dynamical regimes (basins of attraction), like a good scientific theory should?

Out-of-domain generalization in #DynamicalSystems reconstruction:
https://t.co/urxNeLE6wh

#AI #ML
(1/3)

[DurstewitzLab @DurstewitzLab]

Surprisingly, our framework enables to reconstruct chaotic attractors from just *symbolic* time series alone under certain conditions. This gives hope that it may be possible to infer dynamical systems just from behavioral class labels or language.
(3/4)

[DurstewitzLab @DurstewitzLab]

How to reconstruct #DynamicalSystems from many different data modalities observed simultaneously?
Here we introduce a novel generative modeling framework for this, based on control-theoretic ideas for efficiently guiding the training process: https://t.co/9SFba4iiyC
#AI #ML
(1/4)

[DurstewitzLab @DurstewitzLab]

How to analyze comput. & dynamic mechanisms of RNNs?

1/2 Our #NeurIPS2023 spotlight on a highly efficient algo for locating all fixed points, cycles, and bifurcation manifolds in RNNs: https://t.co/qmINjJB40h
@NeurIPSConf
By brilliant @Zahra__Monfared, @lukasironman, Nic Göring

[IMMERSE Project 🧠📱 @immerse_project]

⚠️ New PhD blog alert ⚠️

Dive into the future of mental health care! Explore the incredible potential of 𝐀.𝐈. in predicting trends and uncovering hidden patterns. Curious? Check out this month's blog by @brenner_manuel

https://t.co/Tzu02qQuDA

[DurstewitzLab @DurstewitzLab]

Our Perspective on reconstructing computat. system dynamics from neural data finally out in @NatRevNeurosci!
https://t.co/mje21ShyWC
We survey generative models that can be trained on time series to mimic the behavior of the neural substrate.
#AI #neuroscience #DynamicalSystems

[Eleonora Russo @russo_eleon]

Great Perspective piece on dynamical system reconstructions from @DurstewitzLab, @GeorgiaKoppe, and @maxinthur!

[Towards Data Science @TDataScience]

In this article, @brenner_manuel dives into the fundamental mechanisms of several classes of generative models, shedding light on their inner workings and exploring their origins in and connections to neuroscience and cognition. https://t.co/X4t0zo8vNP

[Towards Data Science @TDataScience]

"SGD, along with its derivative optimizers, forms the core of many self-learning algorithms."

@brenner_manuel walks us through the inner workings of stochastic gradient descent. https://t.co/z3OC2Ee0OX

[AI Coffee Break with Letitia @AICoffeeBreak]

Thanks @brenner_manuel for your knowledgeable questions and for having me on your great podcast! 🎙️

🎧 Listen on Spotify: https://t.co/vaY3I5K0cN

🎧 or Apple Podcasts: https://t.co/OweHSe523m