A Nonparametric Framework for Quantifying Generative Inference on Neuromorphic Systems

02/18/2016
by   Ojash Neopane, et al.
0

Restricted Boltzmann Machines and Deep Belief Networks have been successfully used in probabilistic generative model applications such as image occlusion removal, pattern completion and motion synthesis. Generative inference in such algorithms can be performed very efficiently on hardware using a Markov Chain Monte Carlo procedure called Gibbs sampling, where stochastic samples are drawn from noisy integrate and fire neurons implemented on neuromorphic substrates. Currently, no satisfactory metrics exist for evaluating the generative performance of such algorithms implemented on high-dimensional data for neuromorphic platforms. This paper demonstrates the application of nonparametric goodness-of-fit testing to both quantify the generative performance as well as provide decision-directed criteria for choosing the parameters of the neuromorphic Gibbs sampler and optimizing usage of hardware resources used during sampling.

READ FULL TEXT
research
03/26/2015

Gibbs Sampling with Low-Power Spiking Digital Neurons

Restricted Boltzmann Machines and Deep Belief Networks have been success...
research
10/28/2019

PT-MMD: A Novel Statistical Framework for the Evaluation of Generative Systems

Stochastic-sampling-based Generative Neural Networks, such as Restricted...
research
09/24/2015

Mapping Generative Models onto a Network of Digital Spiking Neurons

Stochastic neural networks such as Restricted Boltzmann Machines (RBMs) ...
research
11/05/2013

Event-Driven Contrastive Divergence for Spiking Neuromorphic Systems

Restricted Boltzmann Machines (RBMs) and Deep Belief Networks have been ...
research
11/02/2022

Nonparametric Involutive Markov Chain Monte Carlo

A challenging problem in probabilistic programming is to develop inferen...
research
01/16/2019

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

A formulation of Langevin dynamics for discrete systems is derived as a ...
research
03/27/2013

Simulation Approaches to General Probabilistic Inference on Belief Networks

A number of algorithms have been developed to solve probabilistic infere...

Please sign up or login with your details

Forgot password? Click here to reset