AIConfPaper
← Search

Fabian H. Sinz

16 accepted papers

2026

OmniMouse: Scaling properties of multi-modal, multi-task Brain Models on 150B Neural Tokens

Konstantin Friedrich Willeke, Polina Turishcheva, Alex Gilbert, Goirik Chakrabarty, Hasan Atakan Bedel, Paul G. Fahey +15
ICLR 2026poster

Scaling data and artificial neural networks has transformed AI, driving breakthroughs in language and vision. Whether similar principles apply to modeling brain activity remains unclear. Here we leveraged a dataset of 3.3 million neurons from the visual cortex of 78 mice across 323 sessions, totali…

Cited by 0Source ↗code ↗Scholar ↗
2025

Learning and aligning single-neuron invariance manifolds in visual cortex

Mohammad Bashiri, Luca Baroni, Ján Antolík, Fabian H. Sinz
ICLR 2025oral

Understanding how sensory neurons exhibit selectivity to certain features and invariance to others is central to uncovering the computational principles underlying robustness and generalization in visual perception. Most existing methods for characterizing selectivity and invariance identify single…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Modeling Dynamic Neural Activity by combining Naturalistic Video Stimuli and Stimulus-independent Latent Factors

Finn Schmidt, Polina Turishcheva, Suhas Shrinivasan, Fabian H. Sinz
NeurIPS 2025poster

The neural activity in the visual processing is influenced by both external stimuli and internal brain states. Ideally, a neural predictive model should account for both of them. Currently, there are no dynamic encoding models that explicitly model a latent state and the entire neuronal response d…

Cited by 0Source ↗Scholar ↗
2025

TRACE: Contrastive learning for multi-trial time series data in neuroscience

Lisa Schmors, Dominic Gonschorek, Jan Niklas Böhm, Yongrong Qiu, Na Zhou, Dmitry Kobak +6
NeurIPS 2025poster

Modern neural recording techniques such as two-photon imaging or Neuropixel probes allow to acquire vast time-series datasets with responses of hundreds or thousands of neurons. Contrastive learning is a powerful self-supervised framework for learning representations of complex datasets. Existing ap…

Cited by 0Source ↗Scholar ↗
2024

Reproducibility of predictive networks for mouse visual cortex

Polina Turishcheva, Max F Burg, Fabian H. Sinz, Alexander S Ecker
NeurIPS 2024spotlight

Deep predictive models of neuronal activity have recently enabled several new discoveries about the selectivity and invariance of neurons in the visual cortex. These models learn a shared set of nonlinear basis functions, which are linearly combined via a learned weight vector to represent a neuron'…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2024

Retrospective for the Dynamic Sensorium Competition for predicting large-scale mouse primary visual cortex activity from videos

Polina Turishcheva, Paul G. Fahey, Michaela Vystrčilová, Laura Hansel, Rachel E Froebe, Kayla Ponder +19
NeurIPS 2024poster

Understanding how biological visual systems process information is challenging because of the nonlinear relationship between visual input and neuronal responses. Artificial neural networks allow computational neuroscientists to create predictive models that connect biological and machine vision. Ma…

Cited by 3Source ↗PDF ↗Scholar ↗
2023

Bayesian Oracle for bounding information gain in neural encoding models

Konstantin-Klemens Lurz, Mohammad Bashiri, Edgar Y. Walker, Fabian H. Sinz
ICLR 2023poster

In recent years, deep learning models have set new standards in predicting neural population responses. Most of these models currently focus on predicting the mean response of each neuron for a given input. However, neural variability around this mean is not just noise and plays a central role in se…

Cited by 5Source ↗PDF ↗Scholar ↗
2023

Energy Guided Diffusion for Generating Neurally Exciting Images

Paweł A. Pierzchlewicz, Konstantin Friedrich Willeke, Arne Nix, Pavithra Elumalai, Kelli Restivo, Tori Shinn +6
NeurIPS 2023poster

In recent years, most exciting inputs (MEIs) synthesized from encoding models of neuronal activity have become an established method for studying tuning properties of biological and artificial visual systems. However, as we move up the visual hierarchy, the complexity of neuronal computations in…

Cited by 17Source ↗PDF ↗code ↗Scholar ↗
2023

Taking the neural sampling code very seriously: A data-driven approach for evaluating generative models of the visual system

Suhas Shrinivasan, Konstantin-Klemens Lurz, Kelli Restivo, George Denfield, Andreas S. Tolias, Edgar Y. Walker +1
NeurIPS 2023poster

Prevailing theories of perception hypothesize that the brain implements perception via Bayesian inference in a generative model of the world. One prominent theory, the Neural Sampling Code (NSC), posits that neuronal responses to a stimulus represent samples from the posterior distribution over late…

Cited by 5Source ↗PDF ↗Scholar ↗
2021

A flow-based latent state generative model of neural population responses to natural images

Mohammad Bashiri, Edgar Y. Walker, Konstantin-Klemens Lurz, Akshay Kumar Jagadish, Taliah Muhammad, Zhiwei Ding +3
NeurIPS 2021spotlight

We present a joint deep neural system identification model for two major sources of neural variability: stimulus-driven and stimulus-conditioned fluctuations. To this end, we combine (1) state-of-the-art deep networks for stimulus-driven activity and (2) a flexible, normalizing flow-based generative…

Cited by 33Source ↗PDF ↗code ↗Scholar ↗
2021

Generalization in data-driven models of primary visual cortex

Konstantin-Klemens Lurz, Mohammad Bashiri, Konstantin Willeke, Akshay Jagadish, Eric Wang, Edgar Y. Walker +6
ICLR 2021spotlight

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 which learns a representation of neural computation in visual cortex and a neuron-specific readout that…

Cited by 56Source ↗PDF ↗Scholar ↗
2021

Towards robust vision by multi-task learning on monkey visual cortex

Shahd Safarani, Arne Nix, Konstantin Friedrich Willeke, Santiago A Cadena, Kelli Restivo, George Denfield +2
NeurIPS 2021poster

Deep neural networks set the state-of-the-art across many tasks in computer vision, but their generalization ability to simple image distortions is surprisingly fragile. In contrast, the mammalian visual system is robust to a wide range of perturbations. Recent work suggests that this generalization…

Cited by 53Source ↗PDF ↗code ↗Scholar ↗
2020

Factorized Neural Processes for Neural Processes: K-Shot Prediction of Neural Responses

Ronald (James) Cotton, Fabian H. Sinz, Andreas Tolias
NeurIPS 2020poster

In recent years, artificial neural networks have achieved state-of-the-art performance for predicting the responses of neurons in the visual cortex to natural stimuli. However, they require a time consuming parameter optimization process for accurately modeling the tuning function of newly observed…

Cited by 8Source ↗PDF ↗code ↗Scholar ↗
2020

Rotation-invariant clustering of neuronal responses in primary visual cortex

Ivan Ustyuzhaninov, Santiago A. Cadena, Emmanouil Froudarakis, Paul G. Fahey, Edgar Y. Walker, Erick Cobos +5
ICLR 2020talk

Similar to a convolutional neural network (CNN), the mammalian retina encodes visual information into several dozen nonlinear feature maps, each formed by one ganglion cell type that tiles the visual space in an approximately shift-equivariant manner. Whether such organization into distinct cell typ…

Cited by 15Source ↗Scholar ↗
2019

A rotation-equivariant convolutional neural network model of primary visual cortex

Alexander S. Ecker, Fabian H. Sinz, Emmanouil Froudarakis, Paul G. Fahey, Santiago A. Cadena, Edgar Y. Walker +4
ICLR 2019poster

Classical models describe primary visual cortex (V1) as a filter bank of orientation-selective linear-nonlinear (LN) or energy models, but these models fail to predict neural responses to natural stimuli accurately. Recent work shows that convolutional neural networks (CNNs) can be trained to predic…

Cited by 63Source ↗PDF ↗code ↗Scholar ↗
2017

Normalizing the Normalizers: Comparing and Extending Network Normalization Schemes

Mengye Ren, Renjie Liao, Raquel Urtasun, Fabian H. Sinz, Richard S. Zemel
ICLR 2017poster

Normalization techniques have only recently begun to be exploited in supervised learning tasks. Batch normalization exploits mini-batch statistics to normalize the activations. This was shown to speed up training and result in better models. However its success has been very limited when dealing wit…

Cited by 113Source ↗Scholar ↗