SensiML's Analytics Studio Delivers Software Tools to the AI Edge
May 21, 2024
News
Portland, Oregon. SensiML Corporation (subsidiary of QuickLogic) declared it is first to deliver a complete open-source AutoML solution for designing edge AI/ML applications with its invented Analytics Studio delivering enhanced creativity, innovation, and AI code transparency. According to SensiML, its Analytics Studio provides IoT Edge AI software tools such as platform agnostic model generation, time-series sensor inputs, rapid innovation, flexibility, and extensibility.
“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.”
Platform Agnostic Model Generation:
- SensiML’s open-source environment supports various MCUs, AI/ML accelerated SoCs, and AI engines aiding in the design of ML datasets leveraging various vendors, chipsets, or inference engines.
Time-Series Sensor Inputs:
- Support for microphones, accelerometers, gyros, IMUs, loadcells, strain gauges, PIR sensors, and more.
Rapid Innovation:
- As AI/ML demands are constantly evolving, an open-source approach enhances the developer community and promotes the acceleration of generative AI, synthetic data, and edge learning advancements.
Flexibility:
- Analytics Studio supports point-and-click AutoML powered model generation through code-free GUI-based modeling with full pipeline control, to entirely programmatic Python SDK model creation.
Extensibility:
- Model generation is provided for basic feature-based models, regression models, classic ML, and deep learning neural networks. A library of over 80 feature generators includes the competence to easily add custom transforms, filters, features, and classifiers.
SensiML is contributing its IoT edge AutoML solution as a foundation code base built up over seven years. With community support, SensiML seeks help from the open-source community to extend Analytics Studio to incorporate:
- 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
For more information, visit sensiml.com.
Chad Cox. Production Editor, Embedded Computing Design, has responsibilities that include handling the news cycle, newsletters, social media, and advertising. Chad graduated from the University of Cincinnati with a B.A. in Cultural and Analytical Literature.
