AutoML Seeds

There are several seeds you can use when generated a model using SensiML AutoML. See the following guide for some examples for picking a seed to use:

Basic Features

  • You are wondering where to start

  • You want execution to be as quick as possible

  • You want simple, easy-to-interpret features

Advanced Features

  • You tried “Basic Features” and didn’t get a good model

  • You don’t mind if execution takes a while

  • You want the best possible features, even if they are complex

Downsampled Features

  • You are creating a gesture recognition application

Histogram Features

  • You are creating a motor vibration application

Custom Seed

  • You tried the other seeds and didn’t get a good model

  • You want to build your own pipeline and use the genetic algorithm to find the best number of features, best number of neurons, and other model-related parameters

No Feature Generation

  • You do not want to generate any features, only test the ones you have made offline (Note: resulting Knowledge Packs will not have a feature extraction algorithm, so will not operate on a device; intended for testing only)