Youtube as a Free and Full Stack Data Science Program

Source: https://nrev.jp/2020/05/18/and-the-breadcrumbs-spoke/

There are many resources to be a data scientist. Generally, for certification, many people decide to learn from courses or course bundles from MOOC platforms like Udemy, Coursera, Udacity etc. Also, some people decide to learn data science at master programs at a university. Many of these programs are paid and also have a standard syllabus. Some of these programs, may also be helpful.

Here, I try to collect some full (and tutorial length) courses from Youtube in a systematic way to build a comprehensive end to end data science syllabus. All of them are free. There are no certifications but I would recommend that take notes, build projects and upload them to your github repo. This will be your real certificate for confirmation.

Linear Algebra

source: https://myuni.swansea.ac.uk/academic-success/courses-and-workshops/linear-algebra-workshops/

• Essence of linear algebra — 3Blue1Brown
• Essence of calculus — 3Blue1Brown
• Differential equations — 3Blue1Brown
• Linear Algebra — Full College Course — freecodecamp.org
• Linear Algebra for Beginners | Linear algebra for machine learning — Geek’s Lesson
• Linear Algebra — Khan Academy
• Mathematics for Machine Learning: Linear Algebra || Linear Algebra for Machine Learning — My CS
• Computational Linear Algebra — Rachel Thomas

Statistics and Probability

source: https://study.com/academy/course/common-core-math-grade-6-statistics-probability-standards.html

• Statistics — A Full University Course on Data Science Basics — freecodecamp.org
• Statistical data analysis | Statistical Data Science | Part 1 — Geek’s Lesson
• Statistical Data Analysis | Statistical Data Science | Part 2 — CS Lesson
• Biostatistics Tutorial Full course for Beginners to Experts — Academic Lesson

Computer Science, Algorithmic Thinking and Programming

source: https://www.my-mooc.com/en/mooc/algorithmicthink1/

• Map of Computer Science
• Introduction to Computational Thinking and Data Science — MIT (old version with python)
• Introduction to Computational Thinking and Data Science — MIT (new version with julia)
• Learn Python — Full Course for Beginners [Tutorial] — freecodecamp.org
• Python for Everybody — Full University Python Course — freecodecamp.org
• R Programming Full Course In 7 Hours | R Programming For Beginners | R Tutorial — Simplilearn
• R Programming Tutorial — Learn the Basics of Statistical Computing — freecodecamp.org
• A Gentle Introduction to Julia — The Julia Programming Language
• Julia for Data Science by Huda Nassar — The Julia Programming Language

Machine Learning

source: https://seyler.eksisozluk.com/gunumuz-yazilimciliginin-yukselen-degeri-makine-ogrenmesi-machine-learning-nedir

• Machine Learning — Andrew Ng, Stanford University [FULL COURSE]
• All Machine Learning Models Explained in 5 Minutes | Types of ML Models Basics
• Real-World Python Machine Learning Tutorial w/ Scikit Learn (sklearn basics, NLP, classifiers, etc)
• Machine Learning With Python Full Course In 9 Hours | Machine Learning Tutorial — Simplilearn
• Machine Learning Basics | What Is Machine Learning? | Introduction To Machine Learning | Simplilearn
• Scikit-learn Crash Course — Machine Learning Library for Python — freecodecamp.org
• CS224W: Machine Learning with Graphs | 2021

Deep Learning

source: https://bdtechtalks.com/2018/12/03/jeremy-howard-ai-deep-learning-myths/

• MIT Introduction to Deep Learning | 6.S191
• MIT 6.S094: Deep Learning
• How Deep Neural Networks Work — Full Course for Beginners — freecodecamp.org
• Deep Learning Crash Course for Beginners — freecodecamp.org
• TensorFlow 2.0 Crash Course — freecodecamp.org
• TensorFlow 2.0 Complete Course — Python Neural Networks for Beginners Tutorial — freecodecamp.org
• Keras with TensorFlow Course — Python Deep Learning and Neural Networks for Beginners Tutorial — freecodecamp.org
• Practical Deep Learning for Coders — Full Course from fast.ai and Jeremy Howard — freecodecamp.org
• Natural Language Processing (NLP) Tutorial with Python & NLTK — freecodecamp.org
• OpenCV Python Course — Learn Computer Vision and AI
• Applied Deep Learning with PyTorch — Full Course
• Stanford CS224N: NLP with Deep Learning | Winter 2020 | BERT and Other Pre-trained Language Models
• Stanford CS224N: NLP with Deep Learning | Winter 2019 |
• Deep Unsupervised Learning — Berkeley Spring 2020
• An Introduction to Graph Neural Networks: Models and Applications

Reinforcement Learning

source: https://bdtechtalks.com/2021/06/07/deepmind-artificial-intelligence-reward-maximization/

• Introduction to reinforcement learning — David Silver — Deepmind
• Reinforcement Learning — sentdex
• Reinforcement Learning Course — Full Machine Learning Tutorial — freecodecamp.org
• Stanford CS234: Reinforcement Learning | Winter 2019
• Stanford CS330: Deep Multi-Task and Meta Learning

Model Deployment

source: https://www.explorium.ai/blog/4-steps-you-must-take-to-prepare-for-predictive-model-deployment/

• Data Science 101: Deploying your Machine Learning Model — Data Professor
• A Chat with Andrew on MLOps: From Model-centric to Data-centric AI
• MLOps Tutorials — DVCorg
• Deploy Machine Learning Model Flask

Conclusion

All of the resources shared in this article are free and if one want to build a roadmap to be a full stack data scientist for free, these resources may be helpful. Also, note that this article will be updated periodically. Enjoy it!