- ProxylessNAS [ICLR’19], an efficient neural architecture search algorithm with a light-weight pre-trained model for mobile AI is integrated by AWS AutoGluon and Facebook PyTorch.
[paper][code][demo][poster][MIT news][IEEE Spectrum]
- Temporal Shift Module (TSM) [ICCV’19], a fast and light-weight video recognition model is integrated by NVIDIA.
[paper][demo][code][poster][MIT News][Engadget][MIT Technology Review][NVIDIA News][NVIDIA Jetson Developer Forum] - Once-For-All Network (OFA) for on-device AI is highlighted by Qualcomm.
- March 2020: “Faster, Power-Efficient Video Recognition” @ EmTech Digital.
- April 2020: “AutoML for TinyML with Once-for-all-Network” @ ICLR’20 NAS workshop
- April 2020: “Once-for-All: Train One Network and Specialize it for Efficient Deployment” @ TinyML Webinar.
- Nov 2020: “Putting AI on a Diet: TinyML and Efficient Deep Learning” @ MIT ILP webinar session on low power/edge/efficient computing
- Jan 2021: “Putting AI on a Diet: TinyML and Efficient Deep Learning” @ Microsoft
- Jan 2021: “Putting AI on a Diet: TinyML and Efficient Deep Learning” @ Stanford MLSys seminar
- Jan 2021: “Putting AI on a Diet: TinyML and Efficient Deep Learning” @ Boeing
- Jan 2021: “Efficient AI: Reducing the Carbon Footprint of AI in the Internet of Things (IoT)” @ MIT ILP Japan conference
- March 2021: “Putting AI on a Diet: TinyML and Efficient Deep Learning” @ TinyML Summit as Keynote.
- April 2021: “Putting AI on a Diet: TinyML and Efficient Deep Learning” @ ISQED’21 Embedded Tutorials.
- April 2021: “Putting AI on a Diet: TinyML and Efficient Deep Learning” @ MLSys’21 On-Device Intelligence Workshop.
- April 2021: “Putting AI on a Diet: TinyML and Efficient Deep Learning” @ Apple’s On-Device ML Workshop.