AN 1011: TinyML Applications in Altera FPGAs Using LiteRT for Microcontrollers
ID
848984
Date
9/29/2025
Public
1. Overview
2. Preparing LiteRT Inference Model
3. Generating Nios® V Processor System
4. Generating Arm Processor System
5. Programming and Running
6. Nios® V Processor with TinyML Design Example
7. Appendix
8. Document Revision History for the AN 1011: TinyML Applications in Altera FPGAs Using LiteRT for Microcontrollers
2.1. Defining the Problem
Before developing any ML problem, determine the project's objective. Explore the project's key characteristics and identify the type of problem as regression or classification.
- Regression - Establish a relationship between input variables and output variables.
- Classification - Assign input data to specific predefined categories.
This example consists of the following aspects:
- The goal is to classify a single digit from 0 to 9, which presents a classification problem.
- Based on the MNIST (Modified National Institute of Standards and Technology) database that contains a large collection of handwritten digits.
- Implements the LeNet-5 Convolutional Neural Network (CNN) model architecture.