paper-with-me

홈 › Papers

Generative Modeling of Neural Dynamics via Latent Stochastic Differential Equations

2024-12-01 · Ahmed ElGazzar, Marcel van Gerven

We propose a probabilistic framework for developing computational models of biological neural systems. In this framework, physiological recordings are viewed as discrete-time partial observations of an underlying continuous-time stochastic dynamical system which implements computations through its state evolution. To model this dynamical system, we employ a system of coupled stochastic differential equations with differentiable drift and diffusion functions and use variational inference to infer its states and parameters. This formulation enables seamless integration of existing mathematical models in the literature, neural networks, or a hybrid of both to learn and compare different models. We demonstrate this in our framework by developing a generative model that combines coupled oscillators with neural networks to capture latent population dynamics from single-cell recordings. Evaluation across three neuroscience datasets spanning different species, brain regions, and behavioral tasks show that these hybrid models achieve competitive performance in predicting stimulus-evoked neural and behavioral responses compared to sophisticated black-box approaches while requiring an order of magnitude fewer parameters, providing uncertainty estimates, and offering a natural language for interpretation.

📄 PDF Abstract BibTeX arXiv:2412.12112

Code (0)

등록된 구현이 없습니다.

Tasks

Variational Inference

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
Variational Inference 설명 없음

Similar Papers 제목 키워드 기반

SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations

2025-02-04 · Grigory Bartosh, Dmitry Vetrov, Christian A. Naesseth

The Latent Stochastic Differential Equation (SDE) is a powerful tool for time series and sequence modeling. However, training Latent SDEs typically relies on adjoint sensitivity methods, which depend on simulation and ba…

SensitivityTime Series

Stochastic Deep Learning: A Probabilistic Framework for Modeling Uncertainty in Structured Temporal Data

2026-01-08 · James Rice arxiv

I propose a novel framework that integrates stochastic differential equations (SDEs) with deep generative models to improve uncertainty quantification in machine learning applications involving structured and temporal da…

Improving the Noise Estimation of Latent Neural Stochastic Differential Equations

2024-12-23 · Linus Heck, Maximilian Gelbrecht, Michael T. Schaub, Niklas Boers

Latent neural stochastic differential equations (SDEs) have recently emerged as a promising approach for learning generative models from stochastic time series data. However, they systematically underestimate the noise l…

Noise EstimationTime Series

Generative Modeling of Clinical Time Series via Latent Stochastic Differential Equations

2025-11-20 · Muhammad Aslanimoghanloo, Ahmed ElGazzar, Marcel van Gerven arxiv

Clinical time series data from electronic health records and medical registries offer unprecedented opportunities to understand patient trajectories and inform medical decision-making. However, leveraging such data prese…

Learning Continuous-Time Dynamics by Stochastic Differential Networks

2020-06-11 · Yingru Liu, Yucheng Xing, Xuewen Yang, Xin Wang 외

Learning continuous-time stochastic dynamics is a fundamental and essential problem in modeling sporadic time series, whose observations are irregular and sparse in both time and dimension. For a given system whose laten…

Time SeriesTime Series Analysis