paper-with-me

홈 › Papers

The Discrete Langevin Machine: Bridging the Gap Between Thermodynamic and Neuromorphic Systems

2019-01-16 · Lukas Kades, Jan M. Pawlowski

A formulation of Langevin dynamics for discrete systems is derived as a class of generic stochastic processes. The dynamics simplify for a two-state system and suggest a network architecture which is implemented by the Langevin machine. The Langevin machine represents a promising approach to compute successfully quantitative exact results of Boltzmann distributed systems by LIF neurons. Besides a detailed introduction of the dynamics, different simplified models of a neuromorphic hardware system are studied with respect to a control of emerging sources of errors.

📄 PDF Abstract BibTeX arXiv:1901.05214

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Partitioned integrators for thermodynamic parameterization of neural networks

2019-08-30 · Benedict Leimkuhler, Charles Matthews, Tiffany Vlaar

Traditionally, neural networks are parameterized using optimization procedures such as stochastic gradient descent, RMSProp and ADAM. These procedures tend to drive the parameters of the network toward a local minimum. I…

Thermodynamic Bayesian Inference

2024-10-02 · Maxwell Aifer, Samuel Duffield, Kaelan Donatella, Denis Melanson 외

A fully Bayesian treatment of complicated predictive models (such as deep neural networks) would enable rigorous uncertainty quantification and the automation of higher-level tasks including model selection. However, the…

Bayesian InferenceModel SelectionUncertainty Quantification

Consistent Projection of Langevin Dynamics: Preserving Thermodynamics and Kinetics in Coarse-Grained Models

2025-12-03 · Vahid Nateghi, Lara Neureither, Selma Moqvist, Carsten Hartmann 외 arxiv

Coarse graining (CG) is an important task for efficient modeling and simulation of complex multi-scale systems, such as the conformational dynamics of biomolecules. This work presents a projection-based coarse-graining f…

A Blueprint for Equilibrium-Based Differentiable Continuous-Variable Thermodynamic Computing

2026-07-17 · Owen Lockwood, Jérémy Béjanin, Joost Bus, Christopher Chamberland 외 arxiv

To address the escalating energy and latency demands of machine-learning workloads, we introduce a blueprint for an energy-efficient and fast thermodynamic computing stack that leverages stochastic analog processes in ph…

Learning Stochastic Thermodynamics Directly from Correlation and Trajectory-Fluctuation Currents

2025-04-26 · Jinghao Lyu, Kyle J. Ray, James P. Crutchfield

Markedly increased computational power and data acquisition have led to growing interest in data-driven inverse dynamics problems. These seek to answer a fundamental question: What can we learn from time series measureme…