19 KiB
Artificial Intelligence for Beginners - A Curriculum
This curriculum is being actively developed on GitHub. Look into contributing to see which areas require active contributions. Please consider this a pre-release, and do not actively use in the classroom yet!
 |
|---|
| AI For Beginners - Sketchnote by @girlie_mac |
Azure Cloud Advocates at Microsoft are pleased to offer a 12-week, 24-lesson curriculum all about Artificial Intelligence.
In this curriculum, you will learn:
- Different approaches to Artificial Intelligence, including the "good old" symbolic approach with Knowledge Representation and reasoning (GOFAI).
- Neural Networks and Deep Learning, which are at the core of modern AI. We will illustrate the concepts behind these important topics using code in two of the most popular frameworks - TensorFlow and PyTorch.
- Neural Architectures for working with images and text. We will cover recent models but may lack a little bit on the state-of-the-art.
- Less popular AI approaches, such as Genetic Algorithms and Multi-Agent Systems.
What we will not cover in this curriculum:
- Business cases of using AI in Business. Consider taking Introduction to AI for business users learning path on Microsoft Learn, or AI Business School, developed in cooperation with INSEAD.
- Classic Machine Learning, which is well described in our Machine Learning for Beginners Curriculum
- Practical AI applications built using Cognitive Services. For this, we recommend that you start with modules Microsoft Learn for vision, natural language processing and others.
- Specific ML Cloud Frameworks, such as Azure Machine Learning or Azure Databricks. Consider using Build and operate machine learning solutions with Azure Machine Learning and Build and Operate Machine Learning Solutions with Azure Databricks learning paths.
- Conversational AI and Chat Bots. There is a separate Create conversational AI solutions learning path, and you can also refer to this blog post for more detail.
- Deep Mathematics behind deep learning. For this, we would recommend Deep Learning by Ian Goodfellow, Yoshua Bengio and Aaron Courville, which is also available online at https://www.deeplearningbook.org/.
For a gentle introduction to AI in the Cloud topics you may consider taking the Get started with artificial intelligence on Azure Learning Path.
Content
| No | Lesson | Intro | PyTorch | Keras/TensorFlow | Lab |
|---|---|---|---|---|---|
| I | Introduction to AI | PAT | |||
| 1 | Introduction and History of AI | Text | |||
| II | Symbolic AI | PAT | |||
| 2 | Knowledge Representation and Expert Systems | Text | Expert System, Ontology, Concept Graph | ||
| III | Introduction to Neural Networks | PAT | |||
| 3 | Perceptron | Text | Notebook | Lab | |
| 4 | Multi-Layered Perceptron and Creating our own Framework | Text | Notebook | Lab | |
| 5 | Intro to Frameworks (PyTorch/TensorFlow) Overfitting |
Text Text |
PyTorch | Keras/TensorFlow | Lab |
| IV | Computer Vision | MS Learn | MS Learn | PAT | |
| 6 | Intro to Computer Vision. OpenCV | Text | Notebook | ||
| 7 | Convolutional Neural Networks CNN Architectures | Text Text | PyTorch | TensorFlow | Lab |
| 8 | Pre-trained Networks and Transfer Learning Training Tricks | Text Text | PyTorch | TensorFlow Dropout sample | Lab |
| 9 | Autoencoders and VAEs | Text | PyTorch | TensorFlow | |
| 10 | Generative Adversarial Networks | Text | PyTorch | TensorFlow | |
| 11 | Object Detection | Text | PyTorch | TensorFlow | |
| 12 | Semantic Segmentation. U-Net | Text | PyTorch | TensorFlow | |
| V | Natural Language Processing | MS Learn | MS Learn | PAT | |
| 13 | Text Representation. Bow/TF-IDF | Text | PyTorch | TensorFlow | |
| 14 | Semantic word embeddings. Word2Vec and GloVe | Text | PyTorch | TensorFlow | |
| 15 | Language Modeling. Training your own embeddings | Text | PyTorch | TensorFlow | |
| 16 | Recurrent Neural Networks | Text | PyTorch | TensorFlow | |
| 17 | Generative Recurrent Networks | Text | PyTorch | TensorFlow | |
| 18 | Transformers. BERT. | Text | PyTorch | TensorFlow | |
| 19 | Named Entity Recognition | Text | PyTorch | TensorFlow | |
| 20 | Large Language Models, Prompt Programming and Few-Shot Tasks | Text | PyTorch | TensorFlow | |
| VI | Other AI Techniques | PAT | |||
| 21 | Genetic Algorithms | Text | Notebook | ||
| 22 | Deep Reinforcement Learning | Text | PyTorch | TensorFlow | |
| 23 | Multi-Agent Systems | Text | |||
| VII | AI Ethics | PAT | |||
| 24 | AI Ethics and Responsible AI | Text | |||
| Extras | |||||
| X1 | Multi-Modal Networks, CLIP and VQGAN | Text | |||
Each lesson contains some pre-reading material (linked as Text above), and some executable Jupyter Notebooks, which are often specific to the framework (PyTorch or TensorFlow). The executable notebook also contains a lot of theoretical material, so to understand the topic you need to go through at least one version of the notebooks (either PyTorch or TensorFlow). There are also Labs available for some topics, which give you an opportunity to try applying the material you have learnt to a specific problem.
Some sections also contain links to MS Learn modules that cover related topics. Microsoft Learn provides a convenient GPU-enabled learning environment, although in terms of content you can expect this curriculum to go a bit deeper.
Course sections also include the links to PATs - Progress Assessment Tool, a list of items that you are likely to get to know after completing the module. You can review it and assess your progress on the course yourself.
Getting Started
Students, there are a couple of ways to use the curriculum. First of all, you can just read the text and look through the code directly on GitHub. If you want to run the code in any of the notebooks - you can find the advice on how to do it in this blog post.
However, if you would like to take the course as a self-study project, we suggest that you fork the entire repo to your own GitHub account and complete the exercises on your own or with a group:
- Start with a pre-lecture quiz
- Read the intro text for the lecture
- If the lecture has additional notebooks, go through them, reading and executing the code. If both TensorFlow and PyTorch notebooks are provided, you can focus on one of them - chose your favourite framework
- Notebooks often contain some of the challenges that require you to tweak the code a little bit to experiment
- Take the post-lecture quiz
- If there is a lab attached to the module - complete the assignment
- Visit the Discussion board to and "learn out loud" by filling out the appropriate PAT rubric. A 'PAT' is a Progress Assessment Tool that is a rubric you fill out to further your learning. You can also react to other PATs so we can learn together
For further study, we recommend following these Microsoft Learn modules and learning paths.
Teachers, we have included some suggestions on how to use this curriculum.
Credits
✍️ Hearty thanks to our authors Dmitry Soshnikov, Evgenii Pishchik, with editors Jen Looper and Lateefah Bello
🎨 Thanks as well to our sketchnote illustrator: Tomomi Imura
🙏 Special thanks 🙏 to our Microsoft Student Ambassador authors, reviewers and content contributors, notably TBD
Meet the Team
🎥 Click the image above for a video about the project and the folks who created it!
Pedagogy
We have chosen two pedagogical tenets while building this curriculum: ensuring that it is hands-on project-based and that it includes frequent quizzes.
By ensuring that the content aligns with projects, the process is made more engaging for students and retention of concepts will be augmented. In addition, a low-stakes quiz before a class sets the intention of the student towards learning a topic, while a second quiz after class ensures further retention. This curriculum was designed to be flexible and fun and can be taken in whole or in part. The projects start small and become increasingly complex by the end of the 12 week cycle.
Find our Code of Conduct, Contributing, and Translation guidelines. Find our Support Documentation here and security information here. We welcome your constructive feedback!
A note about quizzes: All quizzes are contained in this app, for 50 total quizzes of three questions each. They are linked from within the lessons but the quiz app can be run locally; follow the instruction in the
etc/quiz-appfolder.
Offline access
You can run this documentation offline by using Docsify. Fork this repo, install Docsify on your local machine, and then in the etc/docsify folder of this repo, type docsify serve. The website will be served on port 3000 on your localhost: localhost:3000.
Help Wanted!
Would you like to contribute a translation? Please read our translation guidelines.
Other Curricula
Our team produces other curricula! Check out: