Reconstructing computational system dynamics from neural data with recurrent neural networks
Computational models in neuroscience usually take the form of systems of differential
equations. The behaviour of such systems is the subject of dynamical systems theory …
equations. The behaviour of such systems is the subject of dynamical systems theory …
Constructing neural network based models for simulating dynamical systems
Dynamical systems see widespread use in natural sciences like physics, biology, and
chemistry, as well as engineering disciplines such as circuit analysis, computational fluid …
chemistry, as well as engineering disciplines such as circuit analysis, computational fluid …
A variational perspective on diffusion-based generative models and score matching
Discrete-time diffusion-based generative models and score matching methods have shown
promising results in modeling high-dimensional image data. Recently, Song et al.(2021) …
promising results in modeling high-dimensional image data. Recently, Song et al.(2021) …
Diffusion generative flow samplers: Improving learning signals through partial trajectory optimization
We tackle the problem of sampling from intractable high-dimensional density functions, a
fundamental task that often appears in machine learning and statistics. We extend recent …
fundamental task that often appears in machine learning and statistics. We extend recent …
Efficient and accurate gradients for neural sdes
Neural SDEs combine many of the best qualities of both RNNs and SDEs, and as such are a
natural choice for modelling many types of temporal dynamics. They offer memory efficiency …
natural choice for modelling many types of temporal dynamics. They offer memory efficiency …
[HTML][HTML] Bayesian learning via neural Schrödinger–Föllmer flows
F Vargas, A Ovsianas, D Fernandes, M Girolami… - Statistics and …, 2023 - Springer
In this work we explore a new framework for approximate Bayesian inference in large
datasets based on stochastic control. We advocate stochastic control as a finite time and low …
datasets based on stochastic control. We advocate stochastic control as a finite time and low …
Predicting the impact of treatments over time with uncertainty aware neural differential equations.
E De Brouwer, J Gonzalez… - … Conference on Artificial …, 2022 - proceedings.mlr.press
Predicting the impact of treatments from ob-servational data only still represents a major
challenge despite recent significant advances in time series modeling. Treatment …
challenge despite recent significant advances in time series modeling. Treatment …
Thermodynamic AI and the fluctuation frontier
PJ Coles, C Szczepanski, D Melanson… - 2023 IEEE …, 2023 - ieeexplore.ieee.org
Many Artificial Intelligence (AI) algorithms are inspired by physics and employ stochastic
fluctuations. We connect these physics-inspired AI algorithms by unifying them under a …
fluctuations. We connect these physics-inspired AI algorithms by unifying them under a …
Bayesian neural controlled differential equations for treatment effect estimation
Treatment effect estimation in continuous time is crucial for personalized medicine.
However, existing methods for this task are limited to point estimates of the potential …
However, existing methods for this task are limited to point estimates of the potential …
Gotube: Scalable statistical verification of continuous-depth models
We introduce a new statistical verification algorithm that formally quantifies the behavioral
robustness of any time-continuous process formulated as a continuous-depth model. Our …
robustness of any time-continuous process formulated as a continuous-depth model. Our …