Skip to yearly menu bar Skip to main content

Workshop

2nd On-Device Intelligence Workshop

Paul Whatmough · Vijay Janapa Reddi · Chuteng Zhou · Igor Federov · Matthew Mattina · Pete Warden · Ganesh Venkatesh · Vikas Chandra

Project Page

Abstract

Ubiquitous on-device artificial intelligence (AI) is the next step in transforming the myriad of mobile computing devices in our everyday lives into a new class of truly “smart” devices capable of constantly observing, learning and adapting to their environment. The 2nd on-device intelligence workshop aims to advance the state-of-the-art by bringing together researchers and practitioners to discuss the key problems, disseminate new research results, and provide practical tutorial material.

Video

Chat is not available.

Schedule

Timezone: America/Los_Angeles

7:00 AM

Paul Whatmough, Arm Research Opening Remarks

Paul Whatmough

7:15 AM

Putting AI on Diet: TinyML and Efficient Deep Learning (Song Han, MIT) Keynote 1

8:15 AM

MORNING BREAK

8:30 AM

Efficient ML on the Edge with Apache TVM (Thierry Moreau, OctoML) Invited 1

Thierry Moreau

9:15 AM

A Flexible, Extensible Software Framework for Model Compression Based on the LC Algorithm (Yerlan Idelbayev, University of California, Merced) Contributed 1

9:30 AM

TorchQuant: A Hackable Quantization Library For Researchers, By Reseachers (Shyam A Tailor, University of Cambridge) Contributed 2

Shyam Tailor

9:45 AM

Towards Real-Time 3D Object Detection with Pruning Search on Edge Devices (Pu Zhao, Northeastern University) Contributed 3

PU ZHAO

10:00 AM

A Compiler-aware Framework of Network Pruning Search Achieving Beyond Real-Time Mobile Acceleration (Yanyu Li, Northeastern University) Contributed 4

10:15 AM

On-device federated learning with Flower (Akhil Mathur, Nokia Bell Labs) Contributed 5

10:30 AM

Semi-supervised on-device neural network adaptation for remote and portable laser-induced breakdown spectroscopy (Kshitij Bhardwaj, LLNL) Contributed 6

Kshitij Bhardwaj

10:45 AM

QAPPA: Quantization-Aware Power, Performance, and Area Modeling of DNN Accelerators (Ahmet Inci, CMU) Contributed 7

11:00 AM

LUNCH BREAK

12:00 PM

Customizing Federated Learning to the Edge Device (Venkatesh Saligrama, Boston University) Keynote 2

12:45 PM

Enabling standardized behavior for ML operations with TOSA (Eric Kunze, Arm) Invited 2

1:15 PM

On-Device NLP at Facebook (Ahmed Aly and Kshitiz Malik, Facebook) Invited 3

1:45 PM

TinyML Model Design (Igor Fedorov, Arm Research) Tutorial 1

2:00 PM

Deploying and Profiling TinyML Models (Colby Banbury, Harvard) Tutorial 2

2:15 PM

Vijay Reddi, Harvard Closing Remarks