DOE OSTI · 1821523
Mapping Stochastic Devices to Probabilistic Algorithms
Abstract
Probabilistic and Bayesian neural networks have long been proposed as a method to incorporate uncertainty about the world (both in training data and operation) into artificial intelligence applications. One approach to making a neural network probabilistic is to leverage a Monte Carlo sampling approach that samples a trained network while incorporating noise. Such sampling approaches for neural networks have not been extensively studied due to the prohibitive requirement of many computationally expensive samples. While the development of future microelectronics platforms that make this sampling more efficient is an attractive option, it has not been immediately clear how to sample a neural network and what the quality of random number generation should be. This research aimed to start addressing these two fundamental questions by examining basic “off the shelf” neural networks can be sampled through a few different mechanisms (including synapse “dropout” and neuron “dropout”) and examine how these sampling approaches can be evaluated both in terms of evaluating algorithm effectiveness and the required quality of random numbers.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Aimone, James, Safonov, Alexander. 2021-09-01. Mapping Stochastic Devices to Probabilistic Algorithms. https://doi.org/10.2172/1821523. https://searchnasa.com/record/osti%3A1821523/mapping-stochastic-devices-to-probabilistic-algorithms
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Search NASA by Indiciae: BibTeX · RIS.