We believe in the power of high-quality instruction. To allow all users to learn artificial intelligence, we have both created and precisely curated content that will allow anyone to learn the basics of machine learning and deep learning in less than a month.
With the material just on this site and our textbook, you can learn the fundamentals of Artificial Intelligence by following the plan laid out below.
Week 1: Programming and Linear Algebra Basics
- Day 1: Python - Review Tutorial #1, or if you are comfortable, skip to Tutorial #6
- Day 2: Python - Tutorial #6, StartOnAI Book: Chapter 2 and 5
- Day 3: Linear Algebra - If you are not comfortable, review Tutorial #2
- Day 4: Linear Algebra - StartOnAI Book: Chapter 1
- Day 5: Calculus - Tutorial #3, StartOnAI Book: Chapter 3
- Day 6: Probability - Tutorial #4, StartOnAI Book: Chapter 4
- Day 7: Statistics - Tutorial #5, feel free to supplement with Video 9:
Week 2: Machine Learning
- Day 1: Linear Models - Video 1, Video 2
- Day 2: Linear Models - StartOnAI Book: Chapter 6, ML Tutorial #1
- Day 3: Linear Models - Video 3, ML Tutorial #3
- Day 4: Classification - StartOnAI Book: Chapter 7, Video 4: ML Classifiers
- Day 5: Classification - ML Tutorial #2, Video 5: ML Tutorial #4
- Day 6: Classification - Video 8, ML Tutorial #6
- Day 7: Classification - StartOnAI Book: Chapters 8 and 9, Video 6 + Video 7
Week 3: Deep Learning
- Day 1: Deep Learning Basics - StartOnAI Book: Chapter 10, DL Tutorial #1
- Day 2: Deep Learning Basics - Video 10, DL Tutorial #2
- Day 3: Deep Learning Techniques - StartOnAI Book: Chapter 11
- Day 4: Deep Learning Techniques - StartOnAI Book: Chapter 12, DL Tutorial #5
- Day 5: Applied Deep Learning - StartOnAI Book: Chapter 13
- Day 6: Applied Deep Learning - DL Tutorial #3, DL Tutorial #4
- Day 7: Deep Reinforcement Learning - StartOnAI Book: Chapter 14, DL Tutorial #6
Week 4: Applications
- Day 1: Computer Vision - StartOnAI Book: Chapter 15
- Day 2: Image Classification - StartOnAI Book: Chapter 16
- Day 3: Sound Classification - StartOnAI Book: Chapter 17
- Day 4: Natural Language Processing Basics - StartOnAI Book: Chapter 18
- Day 5: Natural Language Processing - StartOnAI Book: Chapter 19
- Day 6: Genomics and Bioinformatics - StartOnAI Book: Chapter 20
- Day 7: Industrial Uses of Machine Learning - StartOnAI Book: Chapter 21
We highly encourage you to supplement StartOnAI material with the book and the curated content below - online courses, university material, etc.
Stanford Coursera with Andrew Ng (Highly Recommended for Intermediate Students)
- This course covers both machine learning fundamentals and the terminology of traditional model training. The course also later delves into state-of-the-art advancements in the field. The only drawback of this course is that it uses MATLAB for the assignments, but today, this language is not commonly used for ML model training. You could complete the exercises in Python or R. (This course is free to audit, but you will need to pay for the certificate)
Google ML Crash Course (Highly Recommended for Beginner Students)
- This course is great for pure machine learning and for understanding the theory behind the training and testing of models. It makes it easy to understand current ML optimization techniques, from loss minimization to representation and regularization. It is mainly conceptual with a few applications at the end (Cancer Prediction + Literature). The drawback is that it is quite short (less than 6-8 hours of content). However, it does take the emphasis off the math.
MIT OCW Machine Learning (Highly Recommended for Intermediate Students)
- This is an introductory machine learning course which "which gives an overview of many concepts, techniques, and algorithms in machine learning, beginning with topics such as classification and linear regression and ending up with more recent topics such as boosting, support vector machines, hidden Markov models, and Bayesian networks. The course will give the student the basic ideas and intuition behind modern machine learning methods as well as a bit more formal understanding of how, why, and when they work." This course is quite math-heavy so we do not recommend it for beginners.
Coursera Deep Learning Specialization (Highly Recommended for Advanced Students)
- This specialization is useful for students who have knowledge of machine learning and want to break into deep learning. This package of 5 courses (which can be audited at no cost) will allow students to gain a fundamental understanding of deep learning, one of the most sought after skills in technology. The course teaches "Convolutional networks, RNNs, LSTM, Adam, Dropout, BatchNorm, Xavier/He initialization, and more. As a student, you will work on case studies from healthcare, autonomous driving, sign language reading, music generation, and natural language processing. " You will master not only the theory but also see how it is applied in industry. We recommend this course since it has direct practical applications and emphasizes Python and TensorFlow.
Microsoft Introduction to AI (Highly Recommended for Beginner Students)
- If you want a high-level overview of machine learning and AI in general, then this is the course for you: "This computer science course provides an overview of AI, and explains how it can be used to build smart apps that help organizations be more efficient and enrich people's lives. It uses a mix of engaging lectures and hands-on activities to help you take your first steps in the exciting field of AI." It applies basic concepts in AI for building simple models, creating chatbots, and for design speech and vision recognition/detection systems. It is free (you can add the certificate for $99) and only requires high-school math knowledge and statistics as a pre-requisite. Python is not required.
Other Great Courses:
- Columbia University EdX Machine Learning (Intermediate)
- MIT OCW Algorithmic ML (Advanced)
- University of Michigan, Applied ML with Python (Beginner)
We highly recommend that you look through the course materials of several AI university courses. Stanford's CS221 and CS229 are foundational. All these courses are developed for a mature audience and the lecture content may assume understanding of advanced mathematics. Studying Math51 will help you to understand the prerequisites. Some courses like CS228 and CS330 are outside the scope of even most undergraduates, but we recommend that you check out the lectures, handouts, and assignments.
- CS229 (Machine Learning with probability)
- CS221 (AI introduction)
- CS230 (Deep Learning
- CS234 (Reinforcement Learning)
- CS231n (Convolutional Neural Networks)
- CS224 (Natural Language Processing)
- CS330 (Meta-Learning)
- CS228 (Probabilistic Models)
- Math51 (Learn Linear Algebra and Multivariable Calculus)
- 6.S191 (Deep Learning)
If you want less theory and more hands-on applications, then we suggest that you try out these tutorials. They present ways to get involved with certain libraries, frameworks, and ML repositories. There are also some lecture videos and series which present both fundamental theory and applications.
- Google Machine Learning Zero to Hero (Sid's personal favorite)
(Amazing Intro to ML in 30 minutes)
- Josh Gordon ML Recipes (Best for beginners)
- Practical ML (amazing explanations)
- Stanford CS Lectures (CS230)
- 3Blue1Brown Deep Learning (Great Visual Aid)
- 3Blue1Brown (Great for learning linear algebra)
- David Silver Reinforcement Learning (DeepMind)
- Coming Soon
Copyright © 2020 StartOnAI - All Rights Reserved.
Maintained by Siddharth Sharma. 2020