Neuton.AI is an Auto TinyML platform that enables users to automatically build exceptionally tiny models without coding and natively embed them into 8, 16, and 32-bit MCUs or smart sensors! The platform has a patented Neural Network Framework under the hood, which is not based on any existing algorithms and allows to build ML models with minimal size and without loss of accuracy. Neuton.AI supports sensor and tabular data, and helps to perform the most common tiny machine learning tasks such as recognizing gestures and human activity, enhancing smart home devices and appliances, creating smart human interfaces, performing predictive maintenance, monitoring device conditions, and controlling physical assets. As part of Arm’s AI ecosystem, Neuton.AI facilitates the democratization of TinyML for users of any tech level. Thousands of developers worldwide use Neuton.AI to solve real-world challenges in varied domains absolutely free of charge.

Solution Briefs

  • thumbnail: Create TinyML Models without Сompression
    Create TinyML Models without Сompression

    A comprehensive approach to building exceptionally compact and explainable machine learning models, deployable on unbelievably tiny devices, even with 8-bit capacity.

    Learn More

Insights

  • Touch-free Interaction for Smartwatches Case Study
    Touch-free Interaction for Smartwatches

    This solution allows for controlling a smartwatch using hand gestures such as rotation, pinch, double pinch, clench, and double clench. It utilizes the Silicon Labs xG24 Dev Kit and has a total footprint of only 5Kb.

    Learn More
  • Logistics: On-device Package Tracking Case Study
    Logistics: On-device Package Tracking

    This solution can recognize seven different events that may occur during the package delivery process, leveraging Silicon Labs xG24-DK2601B and Neuton's ultra-tiny neural networks. The total footprint of the solution is less than 4Kb.

    Learn More
  • Remote Control Application Case Study
    Remote Control Application

    This solution of <4 kb in total footprint can remotely control your media system or presentation slides through gestures. Classes: 8 Accuracy: >98.8% Inference Time: <2.5 ms Total footprint: ~4 Kb

    Learn More
  • Tiny ML Teeth-brushing Tracking Solution Case Study
    Tiny ML Teeth-brushing Tracking Solution

    The solution can identify which specific area of your oral cavity needs cleaning and how effectively it is being cleaned. Classes: 11 Accuracy: >97% Inference Time: <2 ms Total footprint: ~4.5 Kb

    Learn More
  • Ultra-Tiny Solution of Daily Activities ​​Recognition Case Study
    Ultra-Tiny Solution of Daily Activities ​​Recognition

    The solution is highly efficient and has a small footprint. It can recognize complex human activity and can be easily replicated on your device. Classes: 5 Accuracy: >98.5% Inference Time: <2.5 ms Total footprint: ~5 Kb

    Learn More
  • Ultra-tiny Neuton Neural Networks at Sensors Converge 2023 - Watch now! Webinar
    Ultra-tiny Neuton Neural Networks at Sensors Converge 2023 - Watch now!

    In case you were unable to attend Sensors Converge 2023, this remarkable presentation delves into how Neuton.AI can enhance the intelligence of even sensors leveraging ultra-tiny neural networks.

    Learn More
  • Hand Activity Recognition WEBINAR Co-hosted by Neuton.AI, Arduino and Bosch Sensortec Webinar
    Hand Activity Recognition WEBINAR Co-hosted by Neuton.AI, Arduino and Bosch Sensortec

    Watch how Ultra-Tiny Neural Networks change IOT products at the Practical Webinar from Arduino, Bosch Sensortec, and Neuton.AI. Learn how to create a Hand Activity Recognition solution on the Nicla Sense ME and Bosch smart sensor.

    Learn More
  • Arm Tech Talk 2023: The Next Generation Smart Toothbrush - Watch now! Arm Tech Talk
    Arm Tech Talk 2023: The Next Generation Smart Toothbrush - Watch now!

    Watch the presentation of an ultra-efficient teeth-brushing tracking solution leveraging Neuton's ultra-tiny Neural Networks with less than 5 Kb in total footprint in action at the Arm Tech Talk event.

    Learn More
  • Automated Design of Tiny Machine Learning Models: Part 2 News
    Automated Design of Tiny Machine Learning Models: Part 2

    Meet the long-awaited IEEE newsletter issue with the release of the second part of A Practical Guide with 3 full-cycle use cases illustrating the innovative Automated Design of Tiny Machine Learning Models.

    Learn More
  • Solving Real-World Challenges with Arm and Neuton - Watch now! Arm Tech Talk
    Solving Real-World Challenges with Arm and Neuton - Watch now!

    Food safety has become a global challenge! Neuton’s 18-year-old embedded engineer, Sumit Kumar, will present an innovative AI solution that can help farmers check the quality of agrochemicals they use for their crops and avoid dangerous consequences.

    Learn More
  • Automated Design of Tiny Machine Learning Models: Part 1 News
    Automated Design of Tiny Machine Learning Models: Part 1

    Together with colleagues from STM, Neuton's team shares a new approach to creating TinyML models in the article, published in the latest IEEE newsletter issue.

    Learn More
  • Bottoms-up Approach to Building Extremely Small Models - Watch now! Arm Tech Talk
    Bottoms-up Approach to Building Extremely Small Models - Watch now!

    Join Arm & Neuton at our AI Tech Talk to hear all about Neuton’s approach to building models 1000x smaller and faster than competing frameworks.

    Learn More
  • Making the Famous Magic Wand 33x Faster Case Study
    Making the Famous Magic Wand 33x Faster

    Most of “magic wand” experiments are created using TensorFlow codes and Arduino’s Nano 33 BLE board with Cortex-M4F Arm processor. Is it possible to automatically create a faster and more accurate magic wand, given the same hardware? Let’s find out!

    Learn More
  • Using AI-based Sensor Fusion for Smoke Detection Case Study
    Using AI-based Sensor Fusion for Smoke Detection

    Can AI save lives? Definitely yes! Learn how to implement sensor fusion and tiny machine learning to detect smoke and get notified in a timely way if a fire starts.

    Learn More
  • Predictive Maintenance of Compressor Water Pumps Case Study
    Predictive Maintenance of Compressor Water Pumps

    Ever thought about how water enters the central heating pipes? The secret is the proper operation of water pumps. Learn how to use RSL10 sensors and Neuton to run models for timely pump maintenance.

    Learn More
  • TinyML Summit 2022. The ideal weight for a tinyML model is less than 1Kb! Webinar
    TinyML Summit 2022. The ideal weight for a tinyML model is less than 1Kb!

    Our CTO, Blair Newman, made a sensational statement at the tinyML Summit 2022 in March as he declared that the ideal weight of a tinyML model is <1 Kb!

    Learn More
  • TinyML Cookbook Release Webinar
    TinyML Cookbook Release

    A great chance for you to meet the author of the TinyML Cookbook, Gian Marco Iodice, a team and tech lead in the Machine Learning Group at Arm, Co-founder of the tinyML Foundation UK and get useful knowledge from the Arm, Arduino, and Neuton teams!

    Learn More
  • Tiny Machine Learning for Edge Devices in Three Clicks Webinar
    Tiny Machine Learning for Edge Devices in Three Clicks

    Watch a special practical master class organized by Neuton.AI in collaboration with the IEEE-Eta Kappa Nu club and Arm.

    Learn More
  • Finalists for 2022 Go: Tech Awards Announced News
    Finalists for 2022 Go: Tech Awards Announced

    Neuton.AI became the finalist for the 2022 Go:Tech Awards in the AI/Machine Learning category! Find out more about the Award and all 14 categories in this post.

    Learn More
  • MLOps for Edge Compute IOT Use Case with GCP, MQTT and Neuton TinyML Blog
    MLOps for Edge Compute IOT Use Case with GCP, MQTT and Neuton TinyML

    The era of industrial IoT provokes new challenges - now engineers need to deploy ML models to the IoT devices that have lower memory/RAM footprint and lower CPU. Learn how to easily implement IoT use cases with TinyML or Deep Learning in this piece.

    Learn More