feature article
Subscribe Now

Qeexo Takes Misery Out of EdgeML

Startup Takes a Dose of its Own Medicine

“It’s what you learn after you know it all that counts.” — John Wooden

Invention, meet your mother, Necessity. It’s an oft-told tale. A programmer hacks together a tool to solve a particular problem, then realizes the tool has broader applicability than he thought. He refines it a bit so it can be used over and over. Sometimes, the tool is even more valuable than the work product. And sometimes, that insight leads to a whole new company. 

Just like it did with Qeexo

Sang Won Lee and his colleagues from Carnegie Mellon University had been working as programmers-for-hire for several years, specializing in clever ways to detect and characterize fingertip presses on smartphone screens, using just little microcontrollers. Their technique relied on some clever ML models and inference code, which ran on ARM Cortex-M0 and M4 MCUs. They productized that as FingerSense, and life was rosy. 

Problem was, the team had to redo everything for each new project. Every screen is different, every vendor wants something different, every sensor suite is different. That meant lots of travel, lots of on-site tweaking with customer hardware, and lots of sleepless nights. It was a traveling minstrel show called ML at the Edge. 

Time to automate the process. They polished up their in-house tools and the next year cranked out 56 new variants of FingerSense without ever leaving the office. The light dawned. “Hey, we need to productize this thing.” Thus was born a new product, AutoML

The idea is that you feed AutoML the data from your sensors (accelerometers, gyroscopes, thermometers, microphones, etc.) and let it build a model. A few sliders and radio buttons let you tweak sampling rate, weighting, your favorite algorithm, target MCU, permissible code footprint, and some other variables. Press the blue GO button and you’re done. AutoML hands back executable Cortex-M code, ready to download. It’s zero-coding for MCU-based ML. 

Sang says even if you are an experienced ML coder, AutoML is faster, and therefore, more profitable for programmers and their employers. There’s little to be gained from hand-crafting models and massaging input data. Let the tool do it based on observable criteria like code size and latency. And, if you’re not an experienced ML programmer, so much the better. AutoML can make you look like one to your boss. 

Like a lot of online development tools, there are three pricing tiers. Bronze level is free (for now) and comes with 2GB of online storage for sensor data and resulting models. Silver and Gold levels permit more simultaneous users, include more storage, more training, and more hardware support. Subscription pricing for the latter two tiers is negotiable. 

Machine learning is terra incognita for most of us, like DSPs and GPUs of past years, or like VR now. There’s demand for the talent but no supply. That makes automated tools like AutoML vitally important. Experts may sniff that it’s like putting training wheels on a Ducati. If you don’t know how to operate the machine, stay off it. But product deadlines won’t wait for us to come up to speed. Nobody complains about using a C compiler instead of an assembler, or Verilog instead of a protractor and mechanical pencil. Tools like AutoML raise the level of abstraction and increase productivity by broadening the developer base. It’s a gateway to a whole new world of ML at the edge. 

Leave a Reply

featured blogs
Dec 7, 2021
We explain the fundamentals of photonics, challenges in photonics research & design, and photonics applications including communications & photonic computing. The post Harnessing the Power of Light: Photonics in IC Design appeared first on From Silicon To Software....
Dec 7, 2021
Optimization is all about meeting requirements. In the last post , you read about how you can use measurements to optimize a circuit. This post will discuss the use of curve fitting to optimize a... [[ Click on the title to access the full blog on the Cadence Community site....
Dec 6, 2021
The scary thing is that this reminds me of the scurrilous ways in which I've been treated by members of the programming and IT communities over the years....
Nov 8, 2021
Intel® FPGA Technology Day (IFTD) is a free four-day event that will be hosted virtually across the globe in North America, China, Japan, EMEA, and Asia Pacific from December 6-9, 2021. The theme of IFTD 2021 is 'Accelerating a Smart and Connected World.' This virtual event ...

featured video

PrimeShield Techtorial Series: Part 2 - Design Variation Analysis and Variation Robustness

Sponsored by Synopsys

To address increasing variations at advance nodes, design teams add guardband margins and signoff at higher sigma to manage risk, resulting in over-designing, thus paying higher PPA cost. Synopsys’ PrimeShield™ solutions’ innovative ML-driven statistical engine enables full statistical design variation analysis, lowers the overall pessimism, and in some cases catches potential risks of design optimism. In Part 2 of the PrimeShield Techtorial series, Synoposys covers Design Variation Analysis and Variation Robustness, giving a brief overview of each concept and discussing the value each of these brings in improving your power and performance.

Click here to learn more about PrimeShield

featured paper

Add Authentication Security to Automotive Endpoints Using the 1-Wire Interface

Sponsored by Analog Devices

By adding a single authentication IC, automotive designers can authenticate a component with only one signal between an ECU and endpoint component. This is particularly important as counterfeit and theft are increasingly problems in automotive applications. This application note describes how to implement the DS28E40 Deep Cover 1-Wire Authenticator in a system to provide authentication for optical cameras, headlamps, EV Batteries, occupancy sensors, and even steering wheels, and more.

Click to read more

featured chalk talk

Accelerating Physical Verification Productivity Part Two

Sponsored by Synopsys

Physical verification of IC designs at today’s advanced process nodes requires an immense amount of processing power. But, getting your design and verification tools to take full advantage of the compute resources available can be a challenge. In this episode of Chalk Talk, Amelia Dalton chats with Manoz Palaparthi of Synopsys about dramatically improving the performance of your physical verification process. 

Click here for more information about Physical Verification using IC Validator