Towards AMS Synthesis in the Era of Machine Learning

Alex Doboli

doi:10.1007/978-3-030-98015-3_31

Towards AMS Synthesis in the Era of Machine Learning

Alex Doboli

Electrical Engineering

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

Abstract

Synthesis, the process of automatically translating information from one domain to another, is the complement of Machine Learning (ML), the process of extracting new knowledge from data. This paper presents an early vision on how analog and mixed-signal (AMS) synthesis could be jointly used with ML to exploit the advantages of AMS circuits for ML applications. The paper discusses the need to include two new concepts into AMS synthesis, (i) ontologies to describe the semantics of the application and design spaces, and (ii) defining AMS synthesis as an evolving process that combines concepts from the two ontologies to create a new solution. A case study on designing a low-energy AMS smart badge illustrates the proposed vision.

Original language	English
Title of host publication	Advances in Information and Communication - Proceedings of the 2022 Future of Information and Communication Conference, FICC
Editors	Kohei Arai
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	456-465
Number of pages	10
ISBN (Print)	9783030980146
DOIs	https://doi.org/10.1007/978-3-030-98015-3_31
State	Published - 2022
Event	Future of Information and Communication Conference, FICC 2022 - Virtual, Online Duration: Mar 3 2022 → Mar 4 2022

Publication series

Name	Lecture Notes in Networks and Systems
Volume	439 LNNS
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	Future of Information and Communication Conference, FICC 2022
City	Virtual, Online
Period	03/3/22 → 03/4/22

Keywords

AMS circuits
Concept combination
Ontology
Synthesis

Access to Document

10.1007/978-3-030-98015-3_31

Cite this

Doboli, A. (2022). Towards AMS Synthesis in the Era of Machine Learning. In K. Arai (Ed.), Advances in Information and Communication - Proceedings of the 2022 Future of Information and Communication Conference, FICC (pp. 456-465). (Lecture Notes in Networks and Systems; Vol. 439 LNNS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-98015-3_31

@inproceedings{0c5f90ec33db4738a36b3ccc16d8a862,

title = "Towards AMS Synthesis in the Era of Machine Learning",

abstract = "Synthesis, the process of automatically translating information from one domain to another, is the complement of Machine Learning (ML), the process of extracting new knowledge from data. This paper presents an early vision on how analog and mixed-signal (AMS) synthesis could be jointly used with ML to exploit the advantages of AMS circuits for ML applications. The paper discusses the need to include two new concepts into AMS synthesis, (i) ontologies to describe the semantics of the application and design spaces, and (ii) defining AMS synthesis as an evolving process that combines concepts from the two ontologies to create a new solution. A case study on designing a low-energy AMS smart badge illustrates the proposed vision.",

keywords = "AMS circuits, Concept combination, Ontology, Synthesis",

author = "Alex Doboli",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.; Future of Information and Communication Conference, FICC 2022 ; Conference date: 03-03-2022 Through 04-03-2022",

year = "2022",

doi = "10.1007/978-3-030-98015-3\_31",

language = "English",

isbn = "9783030980146",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "456--465",

editor = "Kohei Arai",

booktitle = "Advances in Information and Communication - Proceedings of the 2022 Future of Information and Communication Conference, FICC",

}

Doboli, A 2022, Towards AMS Synthesis in the Era of Machine Learning. in K Arai (ed.), Advances in Information and Communication - Proceedings of the 2022 Future of Information and Communication Conference, FICC. Lecture Notes in Networks and Systems, vol. 439 LNNS, Springer Science and Business Media Deutschland GmbH, pp. 456-465, Future of Information and Communication Conference, FICC 2022, Virtual, Online, 03/3/22. https://doi.org/10.1007/978-3-030-98015-3_31

Towards AMS Synthesis in the Era of Machine Learning. / Doboli, Alex.
Advances in Information and Communication - Proceedings of the 2022 Future of Information and Communication Conference, FICC. ed. / Kohei Arai. Springer Science and Business Media Deutschland GmbH, 2022. p. 456-465 (Lecture Notes in Networks and Systems; Vol. 439 LNNS).

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

TY - GEN

T1 - Towards AMS Synthesis in the Era of Machine Learning

AU - Doboli, Alex

PY - 2022

Y1 - 2022

N2 - Synthesis, the process of automatically translating information from one domain to another, is the complement of Machine Learning (ML), the process of extracting new knowledge from data. This paper presents an early vision on how analog and mixed-signal (AMS) synthesis could be jointly used with ML to exploit the advantages of AMS circuits for ML applications. The paper discusses the need to include two new concepts into AMS synthesis, (i) ontologies to describe the semantics of the application and design spaces, and (ii) defining AMS synthesis as an evolving process that combines concepts from the two ontologies to create a new solution. A case study on designing a low-energy AMS smart badge illustrates the proposed vision.

AB - Synthesis, the process of automatically translating information from one domain to another, is the complement of Machine Learning (ML), the process of extracting new knowledge from data. This paper presents an early vision on how analog and mixed-signal (AMS) synthesis could be jointly used with ML to exploit the advantages of AMS circuits for ML applications. The paper discusses the need to include two new concepts into AMS synthesis, (i) ontologies to describe the semantics of the application and design spaces, and (ii) defining AMS synthesis as an evolving process that combines concepts from the two ontologies to create a new solution. A case study on designing a low-energy AMS smart badge illustrates the proposed vision.

KW - AMS circuits

KW - Concept combination

KW - Ontology

KW - Synthesis

UR - https://www.scopus.com/pages/publications/85126923530

U2 - 10.1007/978-3-030-98015-3_31

DO - 10.1007/978-3-030-98015-3_31

M3 - Conference contribution

AN - SCOPUS:85126923530

SN - 9783030980146

T3 - Lecture Notes in Networks and Systems

SP - 456

EP - 465

BT - Advances in Information and Communication - Proceedings of the 2022 Future of Information and Communication Conference, FICC

A2 - Arai, Kohei

PB - Springer Science and Business Media Deutschland GmbH

T2 - Future of Information and Communication Conference, FICC 2022

Y2 - 3 March 2022 through 4 March 2022

ER -

Towards AMS Synthesis in the Era of Machine Learning

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this