Machine learning is a type of artificial intelligence that allows software applications to become more accurate at predicting outcomes without being explicitly programmed to do so. Machine learning algorithms use historical data as input to predict new output values.

In this lesson, you will use Edge Impulse to train a machine-learning algorithm to classify data from your phone's sensors. Edge Impulse is a cloud-based platform that makes developing and deploying machine learning models on embedded devices easy.

Prerequisites

• A smartphone
• An Edge Impulse account (free)

Instructions

• Create an Edge Impulse account: https://studio.edgeimpulse.com/signup.
• Follow the Edge Impulse website tutorials to train a machine-learning algorithm to classify data from your phone's sensors.
  • You get to pick from the tutorials available. https://docs.edgeimpulse.com/docs/tutorials/end-to-end-tutorials . However, I would recommend that you stick to the ones listed in the "Image classification,” "Movement classification” and “Anomaly detection" categories.

Example

<aside> 💡

A gesture recognition model is one example of a machine learning algorithm that you could train using Edge Impulse. This model could control a device or application using hand gestures.

To train a gesture recognition model, you must first collect data about yourself performing different gestures. This data can be managed using your phone's accelerometer and gyroscope sensors.

Once you have collected enough data, you can import it into Edge Impulse and train your model. Edge Impulse provides a variety of pre-trained models that you can use as a starting point.

Once your model is trained, you can test it by performing different gestures and seeing how it classifies them. If the model is not classifying your gestures correctly, you can collect more data and retrain the model.

</aside>

Deploying your model

Once you are satisfied with your model's performance, you can deploy it to your phone or other embedded device. Edge Impulse provides various tools and resources to help you deploy your model.