Manuel Brenner

95 posts

Manuel Brenner

Manuel Brenner

@brenner_manuel

Theoretical neuroscience @durstewitzlab with applications to psychiatry. Medium writer @ https://t.co/NvWDVW3MeW. Science podcaster @ https://t.co/UuL1bP3YdB

Mannheim Katılım Aralık 2019
216 Takip Edilen237 Takipçiler
Manuel Brenner retweetledi
DurstewitzLab
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: arxiv.org/pdf/2410.04814 1/4
DurstewitzLab tweet media
English
5
31
159
19.1K
Manuel Brenner retweetledi
DurstewitzLab
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!
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: osf.io/preprints/psya… #DigitalTwin #SocialBehavior

English
0
4
23
1.9K
Manuel Brenner retweetledi
DurstewitzLab
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
English
1
13
44
5.7K
Manuel Brenner retweetledi
IMMERSE Project 🧠📱
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 doi.org/10.1017/S00332…
IMMERSE Project 🧠📱 tweet media
English
0
7
12
1K
Manuel Brenner retweetledi
DurstewitzLab
DurstewitzLab@DurstewitzLab·
Weight pruning by size is a standard #ML #AI technique to produce sparse models, but in our @icmlconf paper arxiv.org/abs/2406.04934 we find it doesn’t work for learning #DynamicalSystems! Instead, via geometry-based pruning we find *network topology* is far more important! (1/5)
English
3
27
129
15.8K
Manuel Brenner retweetledi
DurstewitzLab
DurstewitzLab@DurstewitzLab·
Cool, 3 papers accepted at #icml2024: 1) Out-of-Domain Generalization in Dynamical Systems Reconstruction (prelim. vers.: arxiv.org/abs/2402.18377) 2) Optimal Recurrent Network Topologies for Dynamical Systems Reconstruction (details to follow) ...
English
6
18
83
13.4K
Manuel Brenner retweetledi
DurstewitzLab
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: arxiv.org/abs/2402.18377 #AI #ML (1/3)
DurstewitzLab tweet media
English
7
90
431
47.6K
Manuel Brenner retweetledi
DurstewitzLab
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 tweet media
English
1
2
8
823
Manuel Brenner retweetledi
DurstewitzLab
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: arxiv.org/abs/2212.07892 #AI #ML (1/4)
DurstewitzLab tweet media
English
3
41
184
22.4K
Manuel Brenner retweetledi
Eleonora Russo
Eleonora Russo@russo_eleon·
Great Perspective piece on dynamical system reconstructions from @DurstewitzLab, @GeorgiaKoppe, and @maxinthur!
DurstewitzLab@DurstewitzLab

Our Perspective on reconstructing computat. system dynamics from neural data finally out in @NatRevNeurosci! nature.com/articles/s4158… We survey generative models that can be trained on time series to mimic the behavior of the neural substrate. #AI #neuroscience #DynamicalSystems

English
0
3
23
5K
Manuel Brenner retweetledi
Towards Data Science
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. buff.ly/3LSDiYx
English
0
6
12
5.1K
Manuel Brenner retweetledi
Towards Data Science
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. buff.ly/3DX1epb
English
0
7
20
6K

Keşfet

@NeurIPSConf @Zahra__Monfared @DurstewitzLab @icmlconf @niclas_goering @GeorgiaKoppe @lukasironman @NatRevNeurosci