tinyML Research Symposium 2021

First International Research Symposium on Tiny Machine Learning (tinyML)

Burlingame, CA Mar 22 2021 https://tinyml.org/home/index.html tinyml-research-symposium@googlegroups.com

About tinyML Research Symposium

Tiny machine learning (tinyML) is a fast-growing field of machine learning technologies and applications including algorithms, hardware, and software capable of performing on-device sensor (vision, audio, IMU, biomedical, etc.) data analytics at extremely low power, typically in the mW range and below, and hence enabling a variety of always-on use-cases and targeting battery-operated devices. tinyML systems are becoming “good enough” for (i) many commercial applications and new systems on the horizon; (ii) significant progress is being made on algorithms, networks, and models down to 100 kB and below; and (iii) initial low power applications in vision and audio are becoming mainstream and commercially available. There is growing momentum demonstrated by technical progress and ecosystem development.

To nurture innovation and growth in this emerging area within machine learning, the first annual tinyML research symposium serves as a flagship venue for research at the intersection of machine learning applications, algorithms, software, and hardware in deeply embedded machine learning systems. Accepted papers will be published in the form of peer-reviewed online proceedings. An author of an accepted paper will have the opportunity to attend the research symposium to give an oral presentation.

Call for Papers

We solicit papers from academia and industry combining cross-layer innovations across topics. Submissions must describe tinyML innovations that intersect and leverage synergy between at least two of the following subject areas:

== tinyML Datasets ==

·  Public release of new datasets to tinyML

·  Frameworks that automate dataset development

·  Survey and analysis of existing tiny datasets that can be used for research
== tinyML Applications ==

·  Novel applications across all fields and emerging use cases

·  Discussions about real-world use cases

·  User behavior and system-user interaction

·  Survey on practical experiences
== tinyML Algorithms ==

·  Federated learning or stream-based active learning methods

·  Deep learning and traditional machine learning algorithms

·  Pruning, quantization, optimization methods

·  Security and privacy implications
== tinyML Systems ==

·  Profiling tools for measuring and characterizing system performance and power

·  Solutions that involve hardware and software co-design

·  Characterization of tiny real-world embedded systems

·  In-sensor processing, design, and implementation
== tinyML Software ==

·  Interpreters and code generator frameworks for tiny systems

·  Optimizations for efficient execution

·  Software memory optimizations

·  Neural architecture search methods
== tinyML Hardware ==

·  Power management, reliability, security, performance

·  Circuit and architecture design

·  Ultra-low-power memory system design

·  MCU and accelerator architecture design and evaluation
== tinyML Evaluation ==

·  Measurement tools and techniques

·  Benchmark creation, assessment and validation

·  Evaluation and measurement of real production systems

Program Committee

·  Edith Beigne, Facebook

·  Vikas Chandra, Facebook

·  Yiran Chen, Duke Univ.

·  Hiroshi Doyu, Ericsson

·  Adam Fuks, NXP

·  Wolfgang Furtner, Infineon

·  Song Han, MIT

·  Jeremy Holleman, Syntiant

·  Prateek Jain, Microsoft

·  Kurt Keutzer, Berkeley

·  H. T. Kung, Harvard

·  Matthew Mattina, ARM

·  Tinoosh Mohsenin, Univ. of Maryland

·  Edwin Park, Qualcomm

·  Priyanka Raina, Stanford Univ.

·  Jae-sun Seo, ASU

·  Mingoo Seok, Columbia Univ.

·  Dennis Sylvester, Univ. of Michigan

·  Jonathan Tapson, GrAI Matter Labs

·  Marian Verhelst, KU Leuven

·  Pete Warden, Google

·  Hoi-Jun Yoo, KAIST
Please see the detailed Call for Papers.

Important Dates

·  Submission Deadline: November 30, 2020 11:59pm AOE

·  Author Notification: Jan 15th, 2021

·  Camera Ready: Feb 15th, 2021

Submission Format

·  Page limit is 6 to 8 pages, including references and any appendix material

·  Submissions must be blind for the double-blind review process

·  For paper formatting, please use the ACM template.

Submission Deadline: November 23, 2020 11:59pm AOE

Submit your manuscript at https://openreview.net/group?id=tinyml.org/tinyML/2021/Research_Symposium