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

01/16/2019
by   Lukas Kades, et al.
0

A formulation of Langevin dynamics for discrete systems is derived as a new class of generic stochastic processes. The dynamics simplify for a two-state system and suggest a novel 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 new dynamics, different simplified models of a neuromorphic hardware system are studied with respect to a control of emerging sources of errors.

READ FULL TEXT
research
03/22/2021

On the Role of System Software in Energy Management of Neuromorphic Computing

Neuromorphic computing systems such as DYNAPs and Loihi have recently be...
research
06/22/2023

Memristive Reservoirs Learn to Learn

Memristive reservoirs draw inspiration from a novel class of neuromorphi...
research
11/05/2013

Event-Driven Contrastive Divergence for Spiking Neuromorphic Systems

Restricted Boltzmann Machines (RBMs) and Deep Belief Networks have been ...
research
12/24/2019

Fast and deep neuromorphic learning with time-to-first-spike coding

For a biological agent operating under environmental pressure, energy co...
research
02/18/2016

A Nonparametric Framework for Quantifying Generative Inference on Neuromorphic Systems

Restricted Boltzmann Machines and Deep Belief Networks have been success...
research
09/24/2015

Mapping Generative Models onto a Network of Digital Spiking Neurons

Stochastic neural networks such as Restricted Boltzmann Machines (RBMs) ...
research
02/24/2023

Flexible Phase Dynamics for Bio-Plausible Contrastive Learning

Many learning algorithms used as normative models in neuroscience or as ...

Please sign up or login with your details

Forgot password? Click here to reset