Learn more with our Technical Whitepaper

Explore the technical details behind the Reality AI approach to machine learning with signals

  • Why signals require a different approach than other machine learning problems

  • The importance of "features" to effective machine learning

  • Why the FFT probably isn't good enough, and what other options are better

  • The difference between Reality AI and Deep Learning


Reality AI technology combines machine learning with advanced signal processing math to deliver extremely accurate and computationally efficient classifiers, predictors and anomaly detectors.

Feature Discovery with AI Explore™

Use the AI Explore option in Reality AI Tools™ to create optimized feature sets for machine learning on signal inputs.

  • An automatic, data-driven process for dynamically generating features that maximize separation between training classes.

  • Generates features of varying computational complexity, and allows you to select the results best suited to your application. Especially useful when creating embedded software for constrained environments.

  • 12 patents awarded, 6 patents pending

Time frequency plot showing features based on FFT

Time-Frequency plot showing features based on FFT

Time frequency plot showing features based on Reality AI

Time-frequency plot showing features based on Reality AI

Our approach uses advanced mathematics, coupled with machine learning, to get better results.

AI on your microcontroller

AI on your M or A class microcontroller

Reality AI Tools can generate detection code suitable for real-time, embedded use on inexpensive microcontrollers.

  • Generates compact, computationally efficient code
  • Can export compiled or source code
  • Supports both real-time streaming data, and periodic samples
  • Can often run on Cortex M-class microcontrollers, or equivalent

Embeddability depends on data dimensionality, sample rate, decision window, and computational complexity of the detection.

Explore using Reality AI Tools and create an optimized solution.

Train in the cloud, deploy where you want

...and control your data at every step

Use our cloud-based application to train classifiers and detectors. Then deploy using our simple cloud API, or export code for integration into your embedded environment. There's no need to load your raw data to our servers - Reality AI Tools can access data in your own cloud service, or on your own cloud-accessible servers.

This infographic illustrates how Reality AI Tools learn in the cloud during the research and development phase. The machine learning output can be deployed via Cloud API or Embedded into a firmware for real time detection at the edge.