A hierarchical adaptively boosted in-memory classifier in 6T SRAM

Recent emerging machine learning applications such as Internet-of-Things and medical devices require to be operated in a battery-powered platform. As the machine learning algorithms involve heavy data-intensive computations, interest in energy-efficient and low-delay machine learning accelerators is growing. Because there is a trade-off between energy and accuracy in machine learning applications, it is a reasonable direction to provide scalable architecture which has diverse operating points. This thesis presents a high-accuracy in-memory realization of the AdaBoost machine learning classifier. The proposed classifier employs a deep in-memory architecture (DIMA), and employs foreground calibration to compensate for PVT variations and improve task-level accuracy. The proposed architecture switches between a high accuracy/high power (HA) mode and a low power/low accuracy (LP) mode via soft decision thresholding to provide an elegant energy-accuracy trade-off. The proposed realization achieves an EDP reduction of 43X over a digital architecture at an iso-accuracy of 95% for the MNIST dataset, which is an improvement of 5% over a previous in-memory implementation of AdaBoost.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Electrical & Computer Engr

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2019

Author dc:creator

• Lim, Sungmin

Contributors dc:contributor

• Shanbhag, Naresh R.

• machine learning, mixed-signal accelerator, adaptive boosting, in-memory computing, energy-efficient.

Statement dc:rights

• Copyright 2019 Sungmin Lim

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/104741

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F104741