SensiML has collaborated with Microchip Technology to deliver ultra-compact machine learning at the IoT edge combining SensiML Analytics Toolkit with the SAM-IoT WG evaluation kit, SAMD21 MCU, and MPLAB X IDE tool suite.
SensiML & Silicon Labs Partner on Cutting-Edge AI for IoT: AutoML Smart Sensing Tools for the EFR32 / EFM32 Family of Low Energy MCUs
SensiML has collaborated with Silicon Labs to enable AutoML-based rapid development of optimized machine learning sensor models for Silicon Labs’ energy-friendly EFR32 and EFM32 microcontrollers (MCUs).
Using Machine Learning to Tackle Climate Change: A HacksterIO Contest
Climate change: A huge challenge forcing us all to be smarter about how we utilize our planet’s resources. At SensiML we’re all about smarter, which is why we’re teaming up with QuickLogic and Hackster.io to create the “Challenge Climate Change” contest with over $70k in prizes. So do some good, learn about edge AI, and maybe win big!
SensiML Adds Arduino Nano 33 BLE Sense Support with PlatformIO
This month SensiML is pleased to announce SensiML Analytics Toolkit now provides native support for STMicroelectronics’ SensorTile.Box Development Kit for wireless IoT and wearable sensor applications. SensiML’s support for SensorTile.Box includes our most sophisticated MQTT-based device data collection firmware yet made available in open source for customers to extend and modify as necessary to suit their particular application needs.
Visit Us at the ST Developers Conference 2020: October 20th and 21st – An Online Event
Join SensiML on October 20 & 21 at the ST Developers Conference, this year being held entirely online. This year SensiML is pleased to be amongst the lead event sponsors and will be delivering an on-demand session presentation as well as demoing SensiML Analytics Toolkit in our virtual booth. Event registration is free and open now. SensiML will be presenting throughout the two-day event. We hope to “see” you there!
UPDATE: SensiML Integrates Google’s TensorFlow Lite for Microcontrollers
SensiML Analytics Toolkit now provides pipeline support for one of the most popular open-source AI frameworks in existence: TensorFlow, specifically its TinyML variant TensorFlow Lite for Microcontrollers. This week we’ve added a step-by-step boxing wearing tutorial showing how SensiML data collection, annotation, and feature preprocessing are combined with a neural network classifier using TFL Micro.
SensiML Integrates Google’s TensorFlow Lite for Microcontrollers
SensiML Analytics Toolkit now provides pipeline support for one of the most popular open-source AI frameworks in existence: TensorFlow, specifically its TinyML variant TensorFlow Lite for Microcontrollers. The combination of SensiML and TensorFlow Lite for Microcontrollers offers best-in-class AI code generation for TinyML applications from consumer wearables to multi-sensor industrial monitoring devices.
SensiML Adds Support for STMicroelectronics’ SensorTile.Box
This month SensiML is pleased to announce SensiML Analytics Toolkit now provides native support for STMicroelectronics’ SensorTile.Box Development Kit for wireless IoT and wearable sensor applications. SensiML’s support for SensorTile.Box includes our most sophisticated MQTT-based device data collection firmware yet made available in open source for customers to extend and modify as necessary to suit their particular application needs.
New SensiML Analytics Studio Makes AutoML for IoT Edge Easier Than Ever
This week SensiML is releasing an all new version of its industry leading AutoML application SensiML Analytics Studio for building optimized embedded sensor algorithms for IoT devices. SensiML Analytics Studio has existed since our inception as a core component of our AI Toolkit. Previously it consisted of both a Python language interface for data scientists
The Case for AI at the Edge
Artificial Intelligence (AI) is becoming increasingly commonplace as organizations seek to bring effective decision making and operational efficiencies to business in ways that transform how humans and machines work together. As this transformation takes shape, the advantages of edge-based AI implementations over centralized or cloud-based models is changing how AI tools are being deployed and