Simple Test Event

Lorem Ipsum

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Curabitur id odio mattis, malesuada urna a, placerat diam. Nunc in euismod orci, vitae tempus nisl. Ut enim nisl, sollicitudin vitae mauris in, mattis molestie eros. Phasellus nibh nisl, tempor id nibh eget, placerat accumsan odio. Nunc nec malesuada tellus. Mauris ullamcorper vulputate magna ut fringilla. Maecenas nec mauris dui. Ut non egestas arcu. Quisque sodales nibh eget lacus malesuada, eget convallis orci condimentum. Sed risus tellus, efficitur sagittis hendrerit in, elementum eget eros. Donec sit amet nunc id nisl rhoncus condimentum.

Duis sed tempor diam. Nunc bibendum magna sed justo pharetra auctor. Etiam gravida nisl turpis, nec lobortis risus porta at. Phasellus porttitor ornare porta. Nulla aliquam, quam sit amet tincidunt dignissim, lorem sem pulvinar magna, ac commodo tortor orci et lacus. Phasellus blandit ultricies risus, in laoreet ipsum rhoncus at. Mauris et blandit felis. Quisque ut ultricies lacus. Nunc porta felis in est sollicitudin, vitae scelerisque turpis porttitor. Proin accumsan tincidunt blandit.

Date

February 12-13, 2022

Location

Austin

Contact us

Discussion

Schedule

Timezone: UTC+1

Always-on AI vision: The path to disruptive, high-scale applications

Peter BERNARD, Sr. Director, Silicon and Telecom, Azure Edge Devices, Platform & Services

Microsoft

Lian Jye SU, Principal Analyst

ABI Research

Edwin PARK, Principal Engineer

QUALCOMM Inc

Evan PETRIDIS, Chief Product Officer, EVP of Systems Engineering

Eta Compute

Tony CHIANG, Sr. Director of Marketing

Himax Imaging

Peter BERNARD, Sr. Director, Silicon and Telecom, Azure Edge Devices, Platform & Services

Microsoft

Pete holds a B.S. in Computer Engineering from Boston University. He holds numerous patents in telecom, mobility and imaging and has been driving product disruption and ecosystem partnerships in the intelligent edge, telecom and services arena for years in Silicon Valley and at Microsoft in Redmond, WA for the past 15 years.
In 2016 he coined the term and the concept of the “Always Connected PC” and helped drive Microsoft’s intelligent edge strategy and investments to enable Windows compute devices to always be connected to the cloud.
Now, he drives Microsoft’s strategy for the intersection of 5G, AI and IoT, and runs the Silicon & Telco team in the Azure Edge Devices Platforms and Services Group, which engages in strategic relationship with Microsoft’s key semiconductor and telecom partnerships.

Lian Jye SU, Principal Analyst

ABI Research

Edwin PARK, Principal Engineer

QUALCOMM Inc

Mr. Edwin Park is a Principal Engineer with Qualcomm Research since 2011. He is directly responsible for leading the system activities surrounding the Always-on Computer Vision Module (CVM) project. In this role, he leads his team in developing the architecture, creating the algorithms, and producing models so devices can “see” at the lowest power. Featuring an extraordinarily small form factor, Edwin has designed the CVM to be integrated into a wide variety of battery-powered and line-powered devices, performing object detection, feature recognition, change/motion detection, and other applications.

Since joining Qualcomm Research, Edwin has worked on a variety of projects such as making software modifications to Qualcomm radios, enabling them to support different radio standards. Edwin has also focused on facilitating carriers’ efforts worldwide to migrate from their legacy 2G cellular systems to 3G, allowing them to increase their data capacity. Edwin Park’s work at Qualcomm Research has resulted in over 40 patents.

Prior to joining Qualcomm, Park was a founder at AirHop Communications and Vie Wireless Technologies. Edwin had various engineering and management positions at Texas Instruments and Dot Wireless. He also worked at various other startups including ViaSat and Nextwave.

Park received a Master Electrical Engineering from Rice University, Houston, TX, USA and a BSEE specializing in Physical Electronics and BA in Economics also from Rice University.

Evan PETRIDIS, Chief Product Officer, EVP of Systems Engineering

Eta Compute

Evan Petridis, Chief Product Officer, EVP of Systems Engineering, Eta Compute
With nearly 30 years of experience, Evan Petridis, Chief Product Officer and Executive Vice President of Systems Engineering, leads Eta Compute’s system solution strategy and helps define and develop a portfolio of innovative products that leverage the company’s low-power endpoint AI technology. He has a diverse and extended history of developing systems, from networking to tiny IoT sensing devices. Most recently he worked as Executive Vice President of Engineering at Enlighted Inc. (now part of Siemens Building Technologies) where he spearheaded all development and production activities for the company’s end-to-end IoT systems. While there, he oversaw one of the largest commercial IoT systems, with millions of deployed sensors and cloud infrastructure for multiple applications. Mr. Petridis serves as an advisor and board member to a number of global technology companies. He earned his bachelor’s degree with First Class Honors from the University of Western Australia, Perth, Australia.

Tony CHIANG, Sr. Director of Marketing

Himax Imaging

Tony Chiang is Sr. Director of Marketing at Himax Imaging, a subsidiary of Himax Technologies. He launched the company’s automotive sensor, structured light 3D near infrared sensor, and most recently, Always On Vision ultra low power sensor product line, spearheading product strategy, sensor definition, partner engagement and customer marketing.

Before joining Himax Imaging, he held senior product planning and system applications engineering positions in multiple semiconductor companies in the areas of Global Positioning System, CMOS image sensor, digital camera processor, and data storage.

Tony received his MBA and BSEE degrees from University of California at Irvine, and has been awarded 4 patents in the fields of Image Sensor operation and system.

Abstract (English)

Vision is the most challenging AI/ML task to tackle in power and resource-constrained battery-operated devices. This panel will focus on the state-of-the-art and the innovation roadmap ahead, discussing which/how/when specific R&D breakthroughs will enable disruptive, high-scale use cases and applications in the future.
• Which use cases/applications are driving always-on AI vision? Both today and in the future?
• What are the biggest gaps in achieving the long-term potential of always-on AI vision, and how is industry addressing it?
• What does the innovation roadmap look like? When and how will technology advances open up new applications and drive scale, adoption, and new investments?

16-bit CNN accuracy in 5.5 mm2 package FPGA Human Presence Detection @ 10mW_

Hussein OSMAN, Market Segment Manager

Lattice Semiconductor

Hussein OSMAN, Market Segment Manager

Lattice Semiconductor

A ½ mWatt, 128-MAC Sparsity Aware Neural Processing Unit for Classification and Semantic Segmentation

Joseph HASSOUN, Sr. Director Neural Processor Architecture

Samsung Semiconductor

Joseph HASSOUN, Sr. Director Neural Processor Architecture

Samsung Semiconductor

Joseph Hassoun is Sr. Director of the Neural Processing Lab at Samsung Advanced Institute of Technology (SAIT), Samsung Electronics. Joseph led the architecture of NPUs for the last four years. The first implementation of NPUs at Samsung went into production in the Galaxy S10 phones. Before joining Samsung Semiconductor, he spent seven years at Nvidia’s architecture team, later driving the auto-grade Xavier System-on-chip (SOC) architecture. His career spans Xilinx’s Virtex FPGA architecture, Hewlett-Packard Enterprise’s server architecture, and several start-ups.

Joseph received MSEE degree from Stanford University and BSEE from the University of Michigan. He was awarded 15 patents in the fields of Computer Architecture and circuit design

Abstract (English)

This Presentation describes an energy-efficient neural processing unit for battery-operated devices. The architecture utilizing threefold of parallelisms for computing Convolutional and Fully Connected layers to achieve object detection for the at-the far-edge-computation. In this presentation, we will present the underlying technology of co-designing neural net models and neural net accelerators to achieve the right tradeoff for the highest energy efficiency. This 128-MAC structure is capable of running a low-precision modified 2-bit Group-Net Network that can perform Image classification and accurate semantic segmentation of 23 frames per seconds while operating at one-half of one mWatt.

Timezone: UTC+1

A frame-free event-based approach to low-power real-time machine vision

Christoph POSCH, CTO

PROPHESEE

Christoph POSCH, CTO

PROPHESEE

Schedule subject to change without notice.

Sponsors

( Click on a logo to get more information)