AUP AI Tutorials

Welcome to the AMD University Program AI Educational Guide

This guide takes you through every stage of the AI workflow—from training to deployment—on AMD technology. The first release of this material focuses on AMD CPUs, APUs and GPUs, including: AMD EPYC™ Processors AMD Ryzen™ Processors AMD Ryzen™ AI Processors, and AMD GPUs: AMD Instinct™ Accelerators AMD Radeon™ RX Graphics Cards AMD Radeon™ PRO Graphics Cards.

For a full list of supported hardware see supported hardware.

What You will Learn

This guide is divided into three sections, covering everything from AI/ML fundamentals to advanced optimization techniques for maximizing performance on AMD hardware.

You will explore:

• Running a range of machine learning models, from CNNs like LeNet, ResNet and Yolo for computer vision tasks, to LLMs such as LLaMA, FLAN, and Whisper for natural language processing and chatbots.

• Using pre-trained models from Hugging Face and fine-tuning them for your specific needs.

• Designing, training, and optimizing your own custom models for deployment.

Each example includes a Jupyter Notebook that can be run in a Docker container for easy experimentation.

Guide Structure

Get started by choosing your learning path:

• Running Inference: Learn how to deploy and run pre-trained models on AMD technology.

• Model Training: Train your own AI models from scratch using AMD hardware.

• Model Optimization: Fine-tune and optimize models for maximum performance on AMD platforms.

Additionally, this guide provides external resources to help you expand your AI knowledge on AMD hardware.

Below you can find the table of contents of this guide.

Paths

• Organization

AI Fundamentals

• Artificial Intelligence Fundamentals
  • Mathematics for AI
  • Machine Learning
  • Generative AI

Setup Environment

• Configuring the Environment

Get Started

• Get Started with AI on AMD Platforms
  • Using Hugging Face pre-trained models
    • MNIST Classification with an MLP Hugging Face Model
    • Semantic Segmentation
    • Image Classification using Yolov10
    • Fine-tuned LAnguage Net Text-To-Text Transfer Transformer
    • Google Enhanced Multimodal Machine Learning 2
    • OpenAI Whisper - Speech Recognition
    • Phi-3-vision Instruct Open Multimodal Model
    • Phi-3 Instruct Open Model
  • Using PyTorch Hub Models
    • LeNet
    • Residual Network - ResNet50
  • Generative AI on AMD platforms

Design your own Model

• Design your own model on AMD Platforms
  • Create Mandelbrot Dataset
  • Mandelbrot Multi-Layer Perceptron Model
  • Machine Learning Training and Inference with PyTorch
  • Model Training for Pneumonia Detection
  • Train YOLOv8 on a Custom Dataset using CLI

Specializing

• Specializing a pre-trained Model
  • Re-training a model using PyTorch and Transfer Learning
  • DistilBERT for Sentiment Analysis
  • Fine-tune Llama 3.2 to generate Markdown friendly Python functions

Optimizing

• Optimizing Computation

Tutorials

• Tutorials

Model Serving

• Model Serving

Glossary

• Glossary

Contribute

• Contributing to AUP AI Tutorials

Contributing

If you would like to contribute to this material, please review the contribution guidelines.

---

Copyright (C) 2025 Advanced Micro Devices, Inc. All rights reserved.

SPDX-License-Identifier: MIT