- Hardware-agnostic solution supports a broad array of edge
processors and silicon vendors
- Establishes a foundation for community-driven edge ML
innovation including generative AI, synthetic data generation, and
edge learning
PORTLAND, Ore., May 14, 2024
/PRNewswire/ -- SensiML™ Corporation, a leader in AI/ML software
for the IoT and a subsidiary of QuickLogic (NASDAQ: QUIK), today
announced it is disrupting the TinyML® market by
being the first to offer a complete, open-source AutoML solution
for the development of edge AI/ML applications with its popular
Analytics Studio application. The open-source model already
prevails for highly-adopted AI libraries such as
TensorFlow™ and PyTorch®, but until now eludes
comprehensive AutoML development tools targeting IoT edge
devices.
AutoML, or automated machine learning, simplifies and greatly
speeds up the process of creating machine learning models. This
makes machine learning more accessible to developers who may not
have specialized data science knowledge. Building ML models for IoT
microcontrollers and edge SoCs is particularly complex because it
requires blending data science with embedded code optimization for
devices with limited memory and compute power. AutoML helps
overcome these challenges.
SensiML's trailblazing open-source offering promises to deliver
enhanced creativity, innovation, and AI code transparency to the
global community of IoT device developers and expands the company's
access to the rapidly growing market projected by ABI Research to
reach 3.5 billion AI-enabled edge devices by 2027. SensiML's
Analytics Studio brings intelligent sensing capability to a broad
range of IoT edge devices such as the following real-world
application examples:
- Wearable devices and garments that analyze and coach proper
human motion and ergonomics in real-time
- Predictive maintenance and anomaly detection sensors that
recognize and react locally to faults in factory/plant machinery,
pumps, and valves
- Building automation and security endpoints with acoustic event
detection, keyword recognition, and speaker identification
Until now, IoT device developers undertaking what are often
their first AI/ML projects have had to wade through a fragmented
market of proprietary tools with varying capabilities and unclear
roadmaps. The open-source release of SensiML's Analytics Studio
marks a significant milestone for the IoT Edge AI software tools
industry providing:
Platform Agnostic Model Generation:
SensiML's plug-in style, open-source architecture supports a broad
array of MCUs, AI/ML accelerated SoCs, and AI engines inspiring
developer confidence to build ML datasets using flexible tools not
tied to specific vendors, chipsets, or inference engines.
Time-Series Sensor Inputs: Provides
support for all conceivable time-series sensors such as
microphones, accelerometers, gyros, IMUs, loadcells, strain gauges,
PIR sensors, and more. Inputs can be mixed for more complex models
with sensor fusion algorithms.
Rapid Innovation: AI/ML's fast evolution
demands an open-source approach to harness the broader developer
community expertise, accelerating key innovations such as
generative AI, synthetic data, and edge learning advancements.
Flexibility: Analytics Studio supports
multiple model development mechanisms from point-and-click AutoML
powered model generation, to code-free GUI-based modeling
with full pipeline control, to entirely programmatic Python
SDK model creation.
Extensibility: Analytics Studio provides
model generation for basic feature-based models, regression models,
classic ML, and deep learning neural networks. Its rich library of
over 80 feature generators also includes the ability to easily add
custom transforms, filters, features, and classifiers making it
easy for community developers to enhance.
By transitioning to a dual licensing model that includes an
open-source option, SensiML is offering up its IoT edge AutoML
solution as a foundation code base built up over seven years to
benefit the broader developer community for collaborative
improvement and contribution. With community support, SensiML seeks
to extend Analytics Studio to include:
- Generative AI model development and tuning
- Synthetic dataset augmentation
- Local LLM support
- Object recognition from image and video data streams
- Enhanced edge model tuning and learning
- More MCU, MPU, NPU, and GPU integrations / optimizations
- More pre-trained model templates for real-world use cases
New and existing users will have the flexibility to choose
between SensiML's open-source version of Analytics Studio or its
fully managed and supported SaaS cloud service implementation based
on the same core technology.
"Four years ago, QuickLogic, our parent company, launched
the first open-source eFPGA solution," said Chris Rogers, CEO of SensiML. "We are
leveraging this success to democratize edge AI/ML development with
our robust tools. This open-source initiative will accelerate edge
AI/ML adoption, benefit end-user flexibility, and boost SensiML's
SaaS growth and private-label tooling value for our growing list of
industry partners."
Availability
SensiML will launch its public GitHub repository and AutoML engine
documentation early this summer. Developers interested in receiving
updates and becoming contributors to this pioneering technology can
sign up at https://sensiml.com/blog/opensource.
About SensiML
SensiML, a subsidiary of QuickLogic
(NASDAQ: QUIK), offers cutting-edge software that enables ultra-low
power IoT endpoints that implement AI to transform raw sensor data
into meaningful insight at the device itself. The company's
flagship solution, the SensiML Analytics Toolkit, provides an
end-to-end development platform spanning data collection, labeling,
algorithm and firmware auto-generation, and testing. The SensiML
Toolkit supports a growing list of hardware including 8/16/32-bit
MCUs from Microchip®, Arm® Cortex®-M class and higher
microcontroller cores, Intel® x86 instruction set processors, and
heterogeneous core AI/ML optimized SoCs. For more information,
visit https://sensiml.com.
SensiML and logo are trademarks of SensiML. TensorFlow, the
TensorFlow logo and any related marks are trademarks of
Google Inc. All other trademarks are the property of their
respective holders and should be treated as such.
View original content to download
multimedia:https://www.prnewswire.com/news-releases/sensiml-launches-first-complete-open-source-automl-solution-for-edge-aiml-development-302144407.html
SOURCE SensiML Corporation