EmbeddedML was first created to be an alternative to the limited options available for Artificial Neural Networks in C. It is designed to be efficient without sacrificing ease of use. It is meant to support students as well as industry experts as it is built to be expandable and straightforward to manipulate.
- Two examples are provided to show how a simple application could use embeddedML in a learning task.
- XOR
- XOR-AND
- Learning Orientation Based on Accelerometer Data
- Video of performance on STM's SensorTile
- Learning the XOR-AND Gate
The examples are complete Embedded ML applications demonstrating training and testing Embedded ML operation.
For those experienced with SensorTile and the STMicroelectronics Datalog project, the examples can be implemented simply by replacing the Catalog main.c file with the main.c file in the corresponding repository directory.
Now, for those learning about SensorTile please see this information below on this new wireless sensor IoT platform and also Tutorial guidance:
SensorTile: https://www.st.com/en/evaluation-tools/steval-stlkt01v1.html
Then, there are Tutorials you may follow below that will prepare you for this introduction to Embedded ML
Goto -> https://sites.google.com/view/ucla-stmicroelectronics-iot/home
Then, follow Tutorials 1,2,3 and 5.
These will allow you to run the SensorTile Examples.
Tutorial 1: N/A
Tutorial 2: N/A
Tutorial 3: N/A
Tutorial 5: N/A