Qeexo Announces General Availability of the Qeexo AutoML Platform to Enable TinyML for Edge Devices

Share Article

Qeexo AutoML Now Supports New Expert Features and New Machine Learning Algorithms

With an intuitive end-to-end workflow and easy online access, Qeexo AutoML will significantly improve the efficiency of TinyML model development and deployment for all users from novices to expert data scientists.

Qeexo, developer of an automated machine learning (ML) platform that accelerates the deployment of TinyML at the edge/endpoint, announced today the general availability of its Qeexo AutoML platform on Amazon Web Services (AWS).

“We are excited to announce the general availability of Qeexo AutoML as a web application hosted on AWS. With an intuitive end-to-end workflow and easy online access, Qeexo AutoML will significantly improve the efficiency of TinyML model development and deployment for all users from novices to expert data scientists,” said Sang Won Lee, CEO of Qeexo.

Beginning today, users can sign up at https://automl.qeexo.com, for a “Bronze” package where they can upload or collect datasets and automatically build lightweight machine learning models that can be deployed to, and tested on, select embedded hardware platforms. The Bronze evaluation package is FREE for a limited time.

“Qeexo AutoML now has advanced control features, new machine learning algorithms, and several new hardware platform support that will provide more flexibility for the TinyML developers,” added Lee.

New key features include: manual selection of sensors post data recording and sensor data features in model building; class-separability visualizations; fine-tuning of classification sensitivity using visualization and sensitivity analysis; and configuration for neural network parameters including quantization-aware training. These new features enable users to build predictive maintenance solutions to detect anomalies in industrial machines; gesture and context awareness algorithms for consumer/wearable use cases such as fitness trackers and elderly care; and other machine-learning-based algorithms for sensor-enabled smart IoT devices.

Significant model updates are also being released, including: a classifier ideally suited for anomaly detection in industrial applications and support of Recurrent Neural Network (RNN), Isolation Forest, and Local Outlier Factor algorithms. This adds to the existing extensive algorithm support of ANN, CNN, GBM, XGBoost, Random Forest, Logistic Regression, and Decision Tree. Qeexo AutoML enables sensor data collection and visualization, automated model building, and one-click deployment on the following hardware platforms: Arduino Nano 33 BLE Sense, Renesas RA6M3 ML Sensor Module, STMicroelectronics STWINKT1, and STMicroelectronics SensorTile.box.

About Qeexo
Qeexo is the first company to automate end-to-end machine learning for embedded edge devices (Cortex M0-M4 class). Our one-click, fully-automated, Qeexo AutoML platform allows customers to leverage sensor data to rapidly build machine learning solutions for highly constrained environments with applications in mobile, IoT, wearables, automotive, and more.
Delivering high performance, solutions built with Qeexo AutoML are optimized to have ultra-low latency, ultra-low power consumption, and an incredibly small memory footprint.
As billions of sensors collect data on every device imaginable, Qeexo can equip them with machine learning to discover knowledge, make predictions, and generate actionable insights.
Spun out of Carnegie Mellon University, Qeexo is venture-backed and headquartered in Mountain View, CA, with offices in Pittsburgh, Shanghai, and Beijing. To learn more, visit http://automl.qeexo.com.

Share article on social media or email:

View article via:

Pdf Print

Contact Author

Lisa Langsdorf
GoodEye Public Relations
+1 646-828-7415
Email >
Visit website

Media