Off-campus UMass Amherst users: To download campus access dissertations, please use the following link to log into our proxy server with your UMass Amherst user name and password.
Non-UMass Amherst users: Please talk to your librarian about requesting this dissertation through interlibrary loan.
Dissertations that have an embargo placed on them will not be available to anyone until the embargo expires.
Author ORCID Identifier
N/A
AccessType
Open Access Dissertation
Document Type
dissertation
Degree Name
Doctor of Philosophy (PhD)
Degree Program
Electrical and Computer Engineering
Year Degree Awarded
2015
Month Degree Awarded
September
First Advisor
Csaba Andras Moritz
Second Advisor
Israel Koren
Third Advisor
C. Mani Krishna
Fourth Advisor
Jayasimha Atulasimha
Subject Categories
Computer and Systems Architecture | Nanoscience and Nanotechnology | Other Computer Engineering | VLSI and Circuits, Embedded and Hardware Systems
Abstract
Machines today lack the inherent ability to reason and make decisions, or operate in the presence of uncertainty. Machine-learning methods such as Bayesian Networks (BNs) are widely acknowledged for their ability to uncover relationships and generate causal models for complex interactions. However, their massive computational requirement, when implemented on conventional computers, hinders their usefulness in many critical problem areas e.g., genetic basis of diseases, macro finance, text classification, environment monitoring, etc. We propose a new non-von Neumann technology framework purposefully architected across all layers for solving these problems efficiently through physical equivalence, enabled by emerging nanotechnology. The architecture builds on a probabilistic information representation and multi-domain mixed-signal circuit style, and is tightly coupled to a nanoscale physical layer that spans magnetic and electrical domains. Based on bottom-up device-circuit-architecture simulations, we show up to four orders of magnitude performance improvement (using computational resolution of 0.1) vs. best-of-breed multi-core machines with 100 processors, for BNs with about a million variables. Smaller problem sizes of ~100 variables can be realized at 20 mW power consumption and very low area around a few tenths of a mm2. Our vision is to enable solving complex Bayesian problems in real time, as well as enable intelligence capabilities at a small scale everywhere, ushering in a new era of machine intelligence.
DOI
https://doi.org/10.7275/7367075.0
Recommended Citation
Khasanvis, Santosh, "Physically Equivalent Intelligent Systems for Reasoning Under Uncertainty at Nanoscale" (2015). Doctoral Dissertations. 456.
https://doi.org/10.7275/7367075.0
https://scholarworks.umass.edu/dissertations_2/456
Included in
Computer and Systems Architecture Commons, Nanoscience and Nanotechnology Commons, Other Computer Engineering Commons, VLSI and Circuits, Embedded and Hardware Systems Commons