Welcome to Ocademy for Data Science, Machine Learning, and Deep Learning! Our target is to provide online resources for university students and working professionals, who are preparing for or currently involved in fields such as Data Science, Machine Learning, and Deep Learning. The project is hosted on GitHub and is free for anyone to use and learn.
The goals of this project are:
- To provide high-quality online resources that are accessible to university students who are interested in Data Science, Machine Learning, and Deep Learning.
- To create a community of students and educators who are passionate about these topics and who can collaborate to improve the project over time.
- To foster a culture of open source education, where students can learn from each other and from industry experts, and where educators can share their knowledge and expertise with a wider audience.
This project includes the following features:
- A curated list of online courses, tutorials, and other resources for learning about Data Science, Machine Learning, and Deep Learning. These resources are suitable for beginners and are organized by topic, making it easy to find what you're looking for.
- Open source code examples and projects that demonstrate best practices in these fields. These examples are designed to help students learn by doing and can be modified and adapted for use in their own projects.
- Collaborative learning opportunities, such as hackathons and online forums, where students can work together on projects and share their knowledge with each other. These events are open to anyone who wants to participate and are a great way to meet other students who are interested in these topics.
- Guest lectures and other industry events that provide students with insights into the latest trends and developments in Data Science, Machine Learning, and Deep Learning. These events are hosted by industry experts and are a great way to learn about the practical applications of these fields.
To use this project, simply visit the GitHub repository and explore the resources that are available. You can use the curated list of resources to find online courses, tutorials, and other materials that are relevant to your interests. You can also browse the open source code examples and projects to see how these concepts are applied in practice.
If you're interested in participating in hackathons or online forums, simply join the relevant group and start contributing. These groups are open to anyone who wants to participate and are a great way to meet other students who are interested in these topics.
This Online Textbook is designed to provide a comprehensive introduction to Data Science, Machine Learning, and Deep Learning, from the fundamentals to the latest advanced techniques, with a focus on practical applications. It is intended for developers, data scientists, engineers, and anyone who wants to learn how to use machine learning to solve real-world problems.
It is divided into four main parts.
- Chap 1 covers the prerequisites, including an introduction to Python programming and its advanced concepts.
- Chap 2 focuses on the Data Science lifecycle, from data acquisition to data visualization, and introduces the best practices for working with data in the cloud.
- Chap 3 covers the fundamentals of Machine Learning, including regression, classification, and model deployment.
- Chap 4 covers advanced Machine Learning techniques, such as Clustering, Ensemble Learning, and Deep Learning.
- …
Each chapter includes theoretical concepts, hands-on exercises, and real-world examples to help you develop a solid understanding of the topic. By the end of the textbook, you will have the knowledge and skills to build and deploy Machine Learning models in a production environment.
- PREREQUISITES
- 1. Python programming introduction
- 2. Python programming basics
- 3. Python programming advanced
- DATA SCIENCE
- 4. Introduction
- 5. Working with data
- 6. Data visualization
- 7. Data Science lifecycle
- 8. Data Science in the cloud
- 9. Data Science in the real world
- FUNDAMENTALS OF MACHINE LEARNING
- 10. Machine Learning overview
- 11. Regression models for Machine Learning
- 12. Build a web app to use a Machine Learning model
- 13. Getting started with classification
- ADVANCED MACHINE LEARNING
- 14. Clustering models for Machine Learning
- 15. Kernel method
- 16. Model selection
- 17. Ensemble learning
- 18. Unsupervised learning (TBD)
- 19. Generative models
- DEEP LEARNING
- 20. Deep learning overview (TBD)
- 21. Convolutional Neural Networks
- 22. Generative adversarial networks
- 23. Recurrent Neural Networks
- 24. Autoencoder (TBD)
- 25. Long-short term memory
- 26. NLP (TBD)
- 27. Time series (TBD)
- 28. DQN (TBD)
- 29. Summary of deep learning (TBD)
- 30. Image classification
- MACHINE LEARNING PRODUCTIONIZATION
- 31. Overview
- 32. Problem framing
- 33. Data engineering
- 34. Model training & evaluation
- 35. Model deployment
- SUPPORTING MATERIALS
- 36. PyTorch
- 37. Bamboolib
- 38. Mito
- 39. KNN (TBD)
- 40. Semi-supervised learning (TBD)
- 41. Unbalanced problems
- 42. AutoML (TBD)
- OTHERS
- 43. Assignments
- 44. Slides
We are committed to delivering high-quality and practical courses on schedule every week, featuring instructors from both academia and industry, including technical experts from leading technology companies. Currently, we have completed the section on Data Science and are now in progress with the Machine Learning section. Please find the class schedule (TODO) below.
| Time | Monday | Tuesday | Wednesday | Thursday | Friday | Saturday | Sunday |
|---|---|---|---|---|---|---|---|
| Morning | |||||||
| Afternoon | |||||||
| Evening |
TODO
TODO
We welcome contributions from students and educators who are passionate about Data Science, Machine Learning, and Deep Learning. If you'd like to contribute to the project, simply fork the repository and make your changes. You can then submit a pull request to have your changes reviewed and merged into the main repository.
If you're new to open source or aren't sure where to start, don't worry! We have a guide for beginners that can help you get started. We also have a code of conduct that we ask all contributors to follow to ensure that our community is welcoming and inclusive.
See this for more information about how to make your contribution.
If you have any questions or comments about this project, please feel free to contact us by email. We look forward to hearing from you!