Artificial Intelligence Fundamentals#
In this section you will find a list of resources to learn fundamental concepts about AI, starting with Mathematics, Machine Learning, Deep Learning and Artificial Intelligence in general.
Programming Languages and Frameworks#
Python is the most popular programming language used in AI development. You should have at least a basic understanding of Python to make the most of your AI learning journey.
AI Frameworks#
In addition to Python, a number of libraries and frameworks have been developed to help train a model and run inference after the model has been trained. We will primarily use PyTorch due to its popularity and support for AMD technologies.
Other popular AI frameworks are:
TensorFlow an end-to-end platform for machine learning.
JAX is a Python library for accelerator-oriented array computation and program transformation, designed for high-performance numerical computing and large-scale machine learning.
ONNX is an open format built to represent machine learning models.
Triton is a language and compiler for parallel programming. It aims to provide a Python-based programming environment for productively writing custom DNN compute kernels capable of running at maximal throughput on modern GPU hardware.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
OpenXLA an open ecosystem of performant, portable, and extensible machine learning (ML) infrastructure components that simplify ML development by defragmenting the tools between frontend frameworks and hardware backends. Built by industry leaders in AI modeling, software, and hardware.
Math and AI#
A good math foundation would help you understand AI/ML underlying concepts, such as convolutions, linear layers, backpropagation, gradient descent and others. Although, we will not cover these topic in details in any of the notebooks, we list a number of resources that you can use as reference. Navigate to the following sections to find more resources.
If you would like to suggest a resource, email us aup@amd.com
Copyright (C) 2025 Advanced Micro Devices, Inc. All rights reserved.
SPDX-License-Identifier: MIT