Real-time trainable data converters for general purpose applications

Loai Danial; Shahar Kvatinsky

doi:10.1145/3232195.3232209

Real-time trainable data converters for general purpose applications

Loai Danial, Shahar Kvatinsky

Electrical and Computer Engineering

Technion - Israel Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Data converters are ubiquitous in data-abundant systems, where they are heterogeneously distributed across the analog-digital interface. Unfortunately, conventional data converters trade off speed, power, and accuracy. Furthermore, intrinsic real-time and post-silicon variations dramatically degrade their performance. In this paper, we employ novel neuro-inspired approaches to design smart data converters that could be trained in real-time for general purpose applications, using machine learning algorithms and artificial neural network architectures. Our approach integrates emerging memristor technology with CMOS. This concept will pave the way towards adaptive interfaces with the continuous varying conditions of data driven applications.

Original language	English
Title of host publication	Proceedings of the 14th IEEE/ACM International Symposium on Nanoscale Architectures, NANOARCH 2018
Pages	34-36
Number of pages	3
ISBN (Electronic)	9781450358156
DOIs	https://doi.org/10.1145/3232195.3232209
State	Published - 17 Jul 2018
Event	14th IEEE/ACM International Symposium on Nanoscale Architectures, NANOARCH 2018 - Athens, Greece Duration: 18 Jul 2018 → 19 Jul 2018

Publication series

Name	Proceedings of the 14th IEEE/ACM International Symposium on Nanoscale Architectures, NANOARCH 2018

Conference

Conference	14th IEEE/ACM International Symposium on Nanoscale Architectures, NANOARCH 2018
Country/Territory	Greece
City	Athens
Period	18/07/18 → 19/07/18

Keywords

Adaptive systems
Analog-to-digital conversion
Digital-to-analog conversion
Machine learning
Memristors
Neuromorphic computing
Reconfigurable architectures

All Science Journal Classification (ASJC) codes

Electrical and Electronic Engineering
Hardware and Architecture

Access to Document

10.1145/3232195.3232209

Cite this

@inproceedings{eb4021ba6b83428696c5e6f2eedef957,

title = "Real-time trainable data converters for general purpose applications",

abstract = "Data converters are ubiquitous in data-abundant systems, where they are heterogeneously distributed across the analog-digital interface. Unfortunately, conventional data converters trade off speed, power, and accuracy. Furthermore, intrinsic real-time and post-silicon variations dramatically degrade their performance. In this paper, we employ novel neuro-inspired approaches to design smart data converters that could be trained in real-time for general purpose applications, using machine learning algorithms and artificial neural network architectures. Our approach integrates emerging memristor technology with CMOS. This concept will pave the way towards adaptive interfaces with the continuous varying conditions of data driven applications.",

keywords = "Adaptive systems, Analog-to-digital conversion, Digital-to-analog conversion, Machine learning, Memristors, Neuromorphic computing, Reconfigurable architectures",

author = "Loai Danial and Shahar Kvatinsky",

note = "Publisher Copyright: {\textcopyright} 2018 Association for Computing Machinery.; 14th IEEE/ACM International Symposium on Nanoscale Architectures, NANOARCH 2018 ; Conference date: 18-07-2018 Through 19-07-2018",

year = "2018",

month = jul,

day = "17",

doi = "10.1145/3232195.3232209",

language = "الإنجليزيّة",

series = "Proceedings of the 14th IEEE/ACM International Symposium on Nanoscale Architectures, NANOARCH 2018",

pages = "34--36",

booktitle = "Proceedings of the 14th IEEE/ACM International Symposium on Nanoscale Architectures, NANOARCH 2018",

}

Danial, L & Kvatinsky, S 2018, Real-time trainable data converters for general purpose applications. in Proceedings of the 14th IEEE/ACM International Symposium on Nanoscale Architectures, NANOARCH 2018. Proceedings of the 14th IEEE/ACM International Symposium on Nanoscale Architectures, NANOARCH 2018, pp. 34-36, 14th IEEE/ACM International Symposium on Nanoscale Architectures, NANOARCH 2018, Athens, Greece, 18/07/18. https://doi.org/10.1145/3232195.3232209

Real-time trainable data converters for general purpose applications. / Danial, Loai; Kvatinsky, Shahar.
Proceedings of the 14th IEEE/ACM International Symposium on Nanoscale Architectures, NANOARCH 2018. 2018. p. 34-36 (Proceedings of the 14th IEEE/ACM International Symposium on Nanoscale Architectures, NANOARCH 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Real-time trainable data converters for general purpose applications

AU - Danial, Loai

AU - Kvatinsky, Shahar

PY - 2018/7/17

Y1 - 2018/7/17

N2 - Data converters are ubiquitous in data-abundant systems, where they are heterogeneously distributed across the analog-digital interface. Unfortunately, conventional data converters trade off speed, power, and accuracy. Furthermore, intrinsic real-time and post-silicon variations dramatically degrade their performance. In this paper, we employ novel neuro-inspired approaches to design smart data converters that could be trained in real-time for general purpose applications, using machine learning algorithms and artificial neural network architectures. Our approach integrates emerging memristor technology with CMOS. This concept will pave the way towards adaptive interfaces with the continuous varying conditions of data driven applications.

AB - Data converters are ubiquitous in data-abundant systems, where they are heterogeneously distributed across the analog-digital interface. Unfortunately, conventional data converters trade off speed, power, and accuracy. Furthermore, intrinsic real-time and post-silicon variations dramatically degrade their performance. In this paper, we employ novel neuro-inspired approaches to design smart data converters that could be trained in real-time for general purpose applications, using machine learning algorithms and artificial neural network architectures. Our approach integrates emerging memristor technology with CMOS. This concept will pave the way towards adaptive interfaces with the continuous varying conditions of data driven applications.

KW - Adaptive systems

KW - Analog-to-digital conversion

KW - Digital-to-analog conversion

KW - Machine learning

KW - Memristors

KW - Neuromorphic computing

KW - Reconfigurable architectures

UR - http://www.scopus.com/inward/record.url?scp=85060701690&partnerID=8YFLogxK

U2 - 10.1145/3232195.3232209

DO - 10.1145/3232195.3232209

M3 - منشور من مؤتمر

T3 - Proceedings of the 14th IEEE/ACM International Symposium on Nanoscale Architectures, NANOARCH 2018

SP - 34

EP - 36

BT - Proceedings of the 14th IEEE/ACM International Symposium on Nanoscale Architectures, NANOARCH 2018

T2 - 14th IEEE/ACM International Symposium on Nanoscale Architectures, NANOARCH 2018

Y2 - 18 July 2018 through 19 July 2018

ER -

Real-time trainable data converters for general purpose applications

Abstract

Publication series

Conference

Keywords

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this