Georgia Institute of Technology
Analog and Neuromorphic computing with a framework on a reconfigurable platform
Abstract
dc:description.abstractThe objective of the research is to demonstrate energy-efficient computing on a configurable platform, the Field Programmable Analog Array (FPAA), by leveraging analog strengths, along with a framework, to enable real-time systems on hardware. By taking inspiration from biology, fundamental blocks of neurons and synapses are built, understanding the computational advantages of such neural structures. To enable this computation and scale up from these modules, it is important to have an infrastructure that adapts by taking care of non-ideal effects like mismatches and variations, which commonly plague analog implementations. Programmability, through the presence of floating gates, helps to reduce these variations, thereby ultimately paving the path to take physical approaches to build larger systems in a holistic manner.
Degree
thesis:*- Level thesis:degree_level
- Doctoral
- Department dc:contributor.department
- Electrical and Computer Engineering
- Grantor dc:publisher
- Georgia Institute of Technology
- Year dc:date.issued
- 2021
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Natarajan, Aishwarya
- Advisor dc:contributor.advisor
-
- Hasler, Jennifer
- Committee members dc:contributor.committeemember
-
- Inan, Omer
- Naeemi, Azad
- Lanterman, Aaron
- Baer, Steven
Subjects
dc:subject × 6Rights
- Language dc:language.iso
- en_US
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- http://hdl.handle.net/1853/66130