SLUUDB7 August   2025 TMS320F28P550SJ

 

  1.   1
  2.   Abstract
  3.   Trademarks
  4. 1Introduction
  5. 2TMS320F28P55x
  6. 3Edge AI Studio
  7. 4Out-of-the-Box Demo (Smart Signal Classifier)
    1. 4.1 Dataset
      1. 4.1.1 Methods for Data Collection
        1. 4.1.1.1 Collection Process
      2. 4.1.2 Data Formats
    2. 4.2 Model Training
      1. 4.2.1 Preprocessing Options
    3. 4.3 Deploying to TI's Hardware
      1. 4.3.1 TVM Compiler
      2. 4.3.2 Model Execution
  8. 5Summary

1 Introduction

Texas Instruments offers a broad portfolio of MCUs and processors, ranging from real-time microcontrollers to high-performance application processors and mmWave sensing devices. Whether you’re building low-power edge nodes or advanced AI-enabled systems, TI provides scalable solutions to meet a wide range of design needs.

To explore our full Edge AI portfolio and discover how TI enables intelligence at the edge—from development tools to deployment—visit our Edge AI Technology page, where you can find the complete story of Edge AI at TI.

This document focuses on our Edge AI Microcontrollers and explores a complete out-of-the-box demo based on those devices. MCUs often fall short when executing complex AI models, especially under constrained power and latency budgets. To meet the demanding performance and efficiency requirements of industrial use cases, dedicated hardware acceleration for machine learning (ML) workloads is essential. TI’s latest Edge AI hardware platforms are equipped with specialized accelerators optimized for running neural networks efficiently, reducing inference times and system power consumption.

Complementing the hardware, TI introduces Edge AI Studio—a fully integrated, graphical development environment that streamlines the entire ML pipeline. From data collection and labeling, to model training, optimization, and deployment onto supported TI edge devices, Edge AI Studio simplifies each step through a no-code, GUI-based interface. This empowers both AI experts and embedded developers to build robust edge intelligence solutions quickly and efficiently.