Andes Technology and Deeplite, Inc. Join Forces to Deploy Highly Compact Deep Learning Models Into Daily Life

MONTREAL, Dec. 10, 2019 — (PRNewswire) — Andes Technology, a leading Asia-based supplier of high-performance low-power compact 32/64-bit RISC-V CPU cores and a founding Platinum member of the RISC-V Foundation, and Montreal based AI startup Deeplite, Inc., the creators of Lightweight Intelligence™ making deep learning AI models smaller, faster and more energy efficient, today announced the results of their joint collaboration to deploy highly optimized deep learning models on Andes RISC-V CPU cores based on AndeStar™ V5 architecture . 

The proliferation of smart devices like AI-enabled home assistants in recent years provides an ideal target platform for deploying highly compact deep learning models into daily life. These devices are designed to operate at both low power and low computation resources. To function effectively, a home assistant must be easy to use and respond to user requests in real-time. Today, due to the compute and power requirements of complex AI models, most smart devices must send user data and requests to the cloud to carry out AI processing then returning the results to the smart devices. 

Andes and Deeplite teamed up to enable human-machine interfaces like home assistants, to operate locally with little to no cloud connectivity required. The scenario is an embedded solution where a home assistant "wakes up" when it detects a person via a small camera. The goal was to optimize a deep learning model running on Andes A25 and D25F that are the first commercial RISC-V cores with DSP SIMD ISA for low-cost edge AI applications. The team started with a MobileNet model trained on a Visual Wake Words (VWW) dataset that was 13MB in size. Using Deeplite's hardware-aware optimization engine automatically found, trained and deployed a new model less than 188KB in size and with only a 1% drop in accuracy. 

"We have more and more industry use cases where we see a need for embedded, optimized deep learning models running on our RISC-V cores such as A25 and D25F that have DSP instructions to accelerate deep learning algorithms," said Dr. Charlie Su, CTO and Executive VP of Andes Technology. "Deeplite has provided a solution that can be leveraged both internally within Andes as well as for our customers to bring deep learning on Andes RISC-V CPU cores to resource-limited devices at the edge."

"I am thrilled with the results of this collaboration! Not only has Deeplite delivered a 69x industry-changing deep learning optimization with minimal accuracy impact but we have done so by automating formerly manual techniques for neural architecture design that were time-consuming and error prone," said Nick Romano, CEO of Deeplite, Inc. "What used to take weeks of expensive trial and error is now accomplished automatically in a few hours! Lightweight Intelligence™ by Deeplite and best of breed hardware from Andes are taking us one step closer to enabling AI in the things we use every day."

By combining industry leading optimization by Deeplite with Andes' state of the art hardware for use cases like voice recognition or person detection to meet microcontroller-level memory and compute requirements, device OEMs and application developers may offer users the benefit of keeping their data on-device, while still providing the real-time and seamless responses necessary for real-world AI everywhere.

To receive our white paper on this collaboration, please contact Davis Sawyer, cofounder and VP, Product at davis@deeplite.ai.

About Andes Technology

In only 14 years, Andes Technology Corporation is now a world class creator of innovative high-performance/low-power 32/64-bit processor cores and associated development environment to serve the rapidly growing global embedded system applications. Andes is also a founding Platinum member of the RISC-V Foundation and the first mainstream CPU vendor that adopted RISC-V as the base of its fifth-generation architecture, the AndeStar™ V5. In order to meet the demanding requirements of today's electronic devices, Andes delivers highly configurable and performance-efficient CPU cores with a full-featured integrated development environment and comprehensive software/hardware solutions to help customers innovate their SoC in a shorter time frame. Since 2018, the yearly volume of Andes-Embedded™ SoCs has surpassed the 1-billion mark. Andes Technology's comprehensive RISC-V CPU families cover from entry-level 32-bit N22, mid-range 32-bit N25F/D25F/A25 and 64-bit NX25F/AX25F, to high-end multicore A(X)25MP.

For more information, please visit https://www.andestech.com 

About Deeplite

Founded in 2018 and based in Montreal, Deeplite is an AI software company dedicated to enabling deep learning in the devices we use every day. Deeplite researches, designs and develops intelligent optimization software powered by reinforcement learning to make Deep Neural Networks (DNNs) faster, smaller and energy-efficient from cloud to edge computing. 

Deeplite has received many industry recognitions including being named a 2019 Canadian Innovation Exchange (CIX) Top20early company and the 2019 Innovation Award Quebec.  Deeplite is currently participating in both the MobilityXlab and L-Spark QNX autonomous vehicle accelerator programs. For more information please visit www.deeplite.ai

 

 

 

 

Cision View original content: http://www.prnewswire.com/news-releases/andes-technology-and-deeplite-inc-join-forces-to-deploy-highly-compact-deep-learning-models-into-daily-life-300972366.html

SOURCE Deeplite

Contact:
Company Name: Deeplite
KY Kaung-Yeu Hsieh, Sr. Marketing Manager, Andes Technology Corporation
Email Contact Davis Sawyer, Cofounder and VP, Product, Deeplite, Inc.
Email Contact




Review Article Be the first to review this article

Featured Video
Editorial
More Editorial  
Latest Blog Posts
Bob Smith, Executive DirectorBridging the Frontier
by Bob Smith, Executive Director
Remembering Jim Hogan
Colin WallsEmbedded Software
by Colin Walls
Variable declarations in C – plenty of pitfalls
Anupam BakshiAgnisys Automation Review
by Anupam Bakshi
AUGER: Celebrating Our Users
Jobs
Business Operations Planner for Global Foundaries at Santa Clara, California
ASIC Engineer for Amazon at seattle, Washington
SerDes Applications Design Engineer for Xilinx at San Jose, California
Staff SerDes Applications Design Engineer for Xilinx at San Jose, California
Circuit Design & Layout Simulation Engineer - Co-Op (Spring 2021) for Global Foundaries at Santa Clara, California
Technical Product Manager- SISW-EDA 238452 for Siemens AG at Fremont, California
Upcoming Events
IPC APEX EXPO 2021 Goes Virtual at - Mar 8 - 12, 2021
ADAS Sensors 2021 at The Henry Hotel 300 Town Center Drive Dearborn MI - Apr 7 - 8, 2021
ISQED'21 - 22nd International Symposium at POB 607 Los Altos CA - Apr 7 - 9, 2021
SEMI MEMS & Sensors Industry Group (MSIG), MSTC 2021 at United States - Apr 13 - 15, 2021



© 2021 Internet Business Systems, Inc.
670 Aberdeen Way, Milpitas, CA 95035
+1 (408) 882-6554 — Contact Us, or visit our other sites:
AECCafe - Architectural Design and Engineering TechJobsCafe - Technical Jobs and Resumes GISCafe - Geographical Information Services  MCADCafe - Mechanical Design and Engineering ShareCG - Share Computer Graphic (CG) Animation, 3D Art and 3D Models
  Privacy PolicyAdvertise