Machine Learning Platform
Discover what you can achieve with Qeexo AutoML
-
Machine Learning that
Runs on a Cortex-M0! Smaller, faster, betterMachine learning models built with Qeexo AutoML are highly optimized and have an incredibly small memory footprint. Models are designed to run locally on embedded devices (as small as a Cortex-M0!) – ideal for ultra low-power, low-latency applications on MCUs and other highly constrained platforms.
-
Automatically Build
ML Solutions Faster and easier than ever beforeUnlike other fragmented machine learning tools and frameworks that require expert engineers to cobble together, Qeexo AutoML walks users through the entire machine learning development process, all from within our intuitive UI – no coding necessary!
How does Qeexo AutoML work?
Qeexo AutoML Features
-
Optimized for the Edge
Supports Arm® Cortex®-M0-to-M4 class MCUs and other constrained environments
-
Leverages sensor data
Ingests data from multiple streams (sensor fusion) and is sensor agnostic
-
Wide range of ML methods
Compares results from many algorithms: regressors, decision trees & neural nets
-
Automated feature extraction
Generates and weights features from your data for the best performance
-
Intuitive user experience
Click-through UI with no coding required
-
Data visualization
Visualize collected or uploaded data to understand patterns and problems
-
Performance reporting
Provides model performance summaries, visualizations, and recommendations
-
Easy deployment
Translates models into C to compile and deploy to target embedded hardware
-
Custom hardware integration
Option to add Qeexo AutoML support to your specific hardware
Qeexo AutoML is the solution
to common machine learning challenges
Challenges
- 1. Severe shortage of skilled resources
- 2. Machine learning is labor-intensive and time-consuming
- 3. Highly constrained environments are difficult to work with
Solutions
- 1. Replaces the need for disparate experts
- 2. Automates many of the most tedious steps and putting in guardrails
- 3. Translates models to C for deployment to embedded devices
Benefits
- 1. Maximizes the efficiency of data science teams
- 2. Eliminates human-induced errors and significantly shortens time required
- 3. Builds machine learning models optimized for the Edge
Register for a free evaluation or other SaaS options.