Sign in

Andreas Tolias

@andreastolias.bsky.social
843 followers 160 following 27 posts

Stanford Professor | NeuroAI Scientist | Entrepreneur working at the intersection of neuroscience, AI, and neurotechnology to decode intelligence @ enigmaproject.ai

PostsRepliesMedia
Andreas Tolias @andreastolias.bsky.social · 25/04/2025
Deeply grateful to the @simonsfoundation.org for launching SCENE and thrilled to join this 10-year journey into ecological neuroscience—unraveling how sensory and motor systems interact. Excited to collaborate with an incredible team of theorists and experimentalists working across species!
0111
Andreas Tolias @andreastolias.bsky.social · 19/04/2025
Building on Lurz et al., our new Wang et al. studies movie‑data performance vs. training size and compares scaling for Conv‑LSTM vs. CvT(convolutional vision transformer)‑LSTM. Details: www.nature.com/articles/s41...
030
Reposted by Andreas Tolias
Alexander Ecker @aecker.bsky.social · 18/04/2025
In Lurz et al., ICLR 2021 we did quite some analysis on scaling and generalization across animals in the context of visual response prediction (incl. behavioral modulation) with @sinzlab.bsky.social and @andreastolias.bsky.social: openreview.net/forum?id=Tp7...
openreview.net
Generalization in data-driven models of primary visual cortex
Deep neural networks (DNN) have set new standards at predicting responses of neural populations to visual input. Most such DNNs consist of a convolutional network (core) shared across all neurons...
181
Andreas Tolias @andreastolias.bsky.social · 15/04/2025
A super exciting paper by @aecker.bsky.social and Marissa Weis, part of the #MICrONS package, deriving a set of principles to characterize the morphological diversity of excitatory neurons across cortical layers. www.nature.com/immersive/d4...
nature.com
The MICrONS Project
An unprecedented dataset of high resolution anatomical images of individual cells in mouse visual cortex, mapped on to their responses. This integrated view of function and structure lays a foundation...
1110
Andreas Tolias @andreastolias.bsky.social · 13/04/2025
We didn't know the optimal patterns driving mouse V1 neurons until the deep learning model by Walker et al. (2019). FYI: Unlike mice, Gabors actually describe macaque V1 neurons quite well (Fu et al., Cell Reports).
110
Reposted by Andreas Tolias
Sophia Sanborn @naturecomputes.bsky.social · 13/04/2025
MICrONS represents a huge step forward for the field. Big-data and AI will drive the next wave of discoveries in neuroscience
1172
Reposted by Andreas Tolias
Sophia Sanborn @naturecomputes.bsky.social · 13/04/2025
Join me, @andreastolias.bsky.social, and many of the incredible MICrONS team members in an AI-driven approach to neuroscience discovery Apply here: www.linkedin.com/jobs/view/42... Or email us at recruiting@enigmaproject.ai
linkedin.com
Enigma hiring Research Engineer: Multi-Modal Modeling in Stanford, CA | LinkedIn
Posted 11:42:35 PM. The modeling team at Enigma is seeking ML Research Engineers to build and scale the next generation…See this and similar jobs on LinkedIn.
0126
Andreas Tolias @andreastolias.bsky.social · 13/04/2025
3/3 The core strength of our approach—robust prediction of neural responses to novel visual stimulus domains. Dyer's autoregressive approach generates latent embeddings for neural decoding—an entirely different architectural paradigm with different scientific objectives.
100
Andreas Tolias @andreastolias.bsky.social · 13/04/2025
2/3 However this is not the main point, these models serve fundamentally different purposes. Ours explicitly predicts neural responses to visual stimuli (an encoding model), creating functional digital twins.
100
Andreas Tolias @andreastolias.bsky.social · 13/04/2025
1/3 Just for clarification our foundation model was introduced on March 21st, 2023—predating Dyer et al. by over six months. www.biorxiv.org/content/bior...
biorxiv.org
110
Andreas Tolias @andreastolias.bsky.social · 13/04/2025
2
000
Andreas Tolias @andreastolias.bsky.social · 13/04/2025
8/8 Deep learning simulation enables systematic representational-level characterization, though detailed circuit-cell-type-level mechanistic comprehension remains beyond current capabilities in the cortex.
210
Andreas Tolias @andreastolias.bsky.social · 13/04/2025
7/8 and characterization of the feature landscape of mouse visual cortex (Tong et al., bioRxiv 2023)—just a few examples of their applications. Most importantly, they yield in silico predictions which are subsequently verified through experimental testing.
100
Andreas Tolias @andreastolias.bsky.social · 13/04/2025
6/8 Predictive models also enabled to systematically characterize single neuron invariance properties (Ding et al., bioRxiv 2023), center-surround interactions (Fu et al., bioRxiv 2023), color-opponency mechanisms (Hofling et al., Elife 2024),
100
Andreas Tolias @andreastolias.bsky.social · 13/04/2025
5/8 Our models also revealed that mouse V1 neurons shift their selectivity toward UV when pupil dilation or running begins, despite maintaining stable spatial stimulus structure—discovered in the digital twin and validated experimentally in closed-loop studies (Franke et al., Nature 2022).
120
Andreas Tolias @andreastolias.bsky.social · 13/04/2025
4/8 For example, these simulations revealed that mouse V1 neurons exhibit complex spatial features deviating from the common notion that Gabor-like stimuli are optimal (Walker, Sinz et al., Nature Neuroscience 2019).
200
Andreas Tolias @andreastolias.bsky.social · 13/04/2025
3/8 When ANNs accurately simulate neural function, they facilitate 'mechanistic interpretability' (to borrow the AI term)—enabling rigorous representational-level analysis of neuronal tuning.
200
Andreas Tolias @andreastolias.bsky.social · 13/04/2025
2/8 Moreover, both task- and data-driven neural predictive models are powerful tools to gain neuroscientific insights as we and others have demonstrated repeatedly.
200
Andreas Tolias @andreastolias.bsky.social · 13/04/2025
1/8: This quote from our abstract refers to task-driven modeling approaches (e.g., Yamins, DiCarlo, et al.) which define computational objectives and reveal hidden representations closely matching brain activity—widely recognized for deepening insights into brain computations.
200
Andreas Tolias @andreastolias.bsky.social · 13/04/2025
3/3 The core strength of our approach—robust prediction of neural responses to novel visual stimulus domains. Dyer's autoregressive approach generates latent embeddings for neural decoding—an entirely different architectural paradigm with different scientific objectives.
110
Andreas Tolias @andreastolias.bsky.social · 13/04/2025
2/3 However this is not the main point, these models serve fundamentally different purposes. Ours explicitly predicts neural responses to visual stimuli (an encoding model), creating functional digital twins.
100
Andreas Tolias @andreastolias.bsky.social · 13/04/2025
1/3 Just for clarification our foundation model was introduced on March 21st, 2023—predating Dyer et al. by over six months. www.biorxiv.org/content/bior...
biorxiv.org
110
Andreas Tolias @andreastolias.bsky.social · 11/04/2025
Huge thanks to @IARPAnews for funding this groundbreaking effort through the @BRAINinitiative, and to our amazing team at @stanforduniversity.bsky.social @stanfordmedicine.bsky.social @BCM @Allen @Princeton @unigoettingen.bsky.social #MICrONS #NeuroAI #Connectomics #FoundationModels #AI
050
Andreas Tolias @andreastolias.bsky.social · 11/04/2025
Foundation models offer a powerful way to systematically decode the neural code of natural intelligence, bridging the gap between brain structure and function.
120
Andreas Tolias @andreastolias.bsky.social · 11/04/2025
Instead, they preferentially connect based on shared functional tuning, choosing partners with similar feature selectivity (“what”) rather than merely receptive field overlap (“where”).
110
Andreas Tolias @andreastolias.bsky.social · 11/04/2025
Using the digital twin of the MICrONS mouse—where exact neuronal wiring was known—we found that neurons don’t connect randomly, even when anatomically close enough. www.nature.com/articles/s41...
nature.com
Functional connectomics reveals general wiring rule in mouse visual cortex - Nature
The MICrONS mouse visual cortex dataset shows that neurons with similar response properties preferentially connect, a pattern that emerges within and across brain areas and layers, and independently e...
110
Andreas Tolias @andreastolias.bsky.social · 11/04/2025
Crucially, this robust generalization allowed us to create precise functional digital twins of individual mouse brains, combining functional predictions with known anatomical wiring.
110
Andreas Tolias @andreastolias.bsky.social · 11/04/2025
Our foundation model generalized robustly to new neurons, new animals, and even previously unseen stimulus domains. It also accurately predicted entirely new modalities, such as anatomically defined cell types.
110
Andreas Tolias @andreastolias.bsky.social · 11/04/2025
To systematically characterize neuronal function, we built the first foundation model of the mouse visual cortex—trained using deep learning on data pooled from multiple mice and cortical areas. www.nature.com/articles/s41...
nature.com
Foundation model of neural activity predicts response to new stimulus types - Nature
A foundation model trained on neural activity of visual cortex from multiple mice accurately predicts responses to video stimuli and cell types, dendritic features and connectivity within the MICrONS ...
110
Andreas Tolias @andreastolias.bsky.social · 11/04/2025
After 7 years, thrilled to finally share our #MICrONS functional connectomics results! We recorded activity from ~75K neurons in the visual cortex of a single mouse, then mapped its wiring using electron microscopy. nature.com/immersive/d42859-025-00001-w/index.html
nature.com
The MICrONS Project
An unprecedented dataset of high resolution anatomical images of individual cells in mouse visual cortex, mapped on to their responses. This integrated view of function and structure lays a foundation...
14814
Reposted by Andreas Tolias
Blake Richards @tyrellturing.bsky.social · 26/03/2025
Eva Dyer and I wrote an opinion piece for @thetransmitter.bsky.social on why neuroscience needs to embrace complexity and accept the "bitter lesson" by using a data-driven regime at scale. With commentary from several wonderful researchers! 🧠📈 #NeuroAI 🧪
511134
Reposted by Andreas Tolias
The Transmitter @thetransmitter.bsky.social · 28/03/2025
What could large-scale AI do for neuroscience? What barriers prevent us from pursuing an AlphaFold for the brain? What are the limits of scale, and where will we need more tailored solutions? Eva ​​Dyer and @tyrellturing.bsky.social ask nine neuroscientists to weigh in. bit.ly/4iXjK3q
bit.ly
Accepting “bitter lesson” and embracing brain’s complexity
To gain insight into complex neural data, we must move toward a data-driven regime, employing large models trained on vast amounts of data. Experts weigh in.
1124
Reposted by Andreas Tolias
Rick Huganir @rhuganir.bsky.social · 15/02/2025
I have been talking to the media, Time, Fortune, NBC, etc., to explain how the onslaught on science and NIH will impact the health of all Americans. Everyone knows someone who has cancer, heart disease, or depression. Spread the word about how cutting science impacts all. time.com/7216299/nih-...
time.com
Experts Call NIH Budget Cuts an 'Apocalypse' for Science
The reductions target indirect costs that cover administrative and equipment costs.
452061903