The following resources provide a great introduction to expert curriculum for learning machine learning. If you are new to programming and have a high school background in mathematics I would recommend following the path of the rocket 🚀, placed next to while if you have a year of programming background and some university mathematical background please follow the path of the scooter🛵. The two paths outlined in the following are surrounded by alternatives if the selected resource does not suit your experience or learning style. Many of the following courses seem to require payment for a certificate upon successful completion of the course. All the included courses offer a free option to watch the videos, complete exercises and quizzes without payment.
This is a fantasia introduction to the data science and machine learning using the open source WECA tool. Ian Witten is the lecturer I wish I had while studying my undergrad. The WECA tool allows quick visualisation, cleaning and analysis of data without added confusion of programming.
Andrew Ng introduces AI concepts without including programming. The course runs over 4 weeks and is targeted at non technical people interested in AI generally or how to specifically include in thier organisation.
Machine Learning (Coursera-Stanford): 🛵
This is THE introductory machine learning course. The course is also taken by Andrew Ng who teaches at a higher level compared to the above "AI for Everybody" course.
The course covers linear algebra and regression, logistic regression, regularisation and neural networks.
Great basic introductory walk through of python programming.
How to Think Like a Computer Scientist
This resource provides a book like guide with interactive tutorials on the bottom half of the screen.
This book introduces python fundamentals in application to real world problems.
Python for data science (Udemy) 🚀🛵(Experienced programmers with data science experience may want to skip this).
This course extremely useful. The course is a great introduction to data science concepts and some application of machine learning. This first half of the course introduces Numpy, Pandas, MatPlotLit, Seaborn. The second half of the course covers linear regression, logistic regression, random forrests and NLP. The course even discusses how to use AWS and how to create a portfolio.
Kaggle
AWS
FastAI 🛵🚀
This course is designed for those with one year of programming experience developing software or general programming. The course provides a great library and video lectures to apply the tool to machine learning problems. The lecturer, Jeremy Howard guides students towards competing on Kaggle, real world machine learning problems. I would recommend taking the introduction to machine learning course before moving onto the deep learning for coders course.
This course combines machine learning with cloud computing concepts. As AWS is currently the industry standard tool in implementing Machine Learning, this course is extremely useful in learning how to use cloud technology combined with earlier skills learnt in machine learning.
Deep Learning Certification (deeplearning.ai)
this course follows on from the Andrew Ng machine learning course. The specialisation start with the skills reuiqred to build, train and apply fully connected deep nueral networks, explores hyperparameter tuning and training and deploying of complex computer vision projects.
Machine Learning A-Z: Hands on Python and R in Data science community (Udemy):
The course focuses on choosing the right model for machine learning problems.
The course covers machine learning in both python and r
Machine Learning, Data Science and Deep Learning with Python:
create real products such as recommender engine and optical character recognition. This course is designed for software developers or programmers who want to transition into machine learning roles. The course is designed by developers at google, LinkedIn and Uber giving the course a very employment focused feel.
Nvidia:
Key concepts required for machine learning understanding include linear algebra, matrix algebra, probability and statistics, optimization. The following resources provide rich, clear instruction of key mathematical concepts.
3Blue1Brown provides clear, comprehensive mathematical introductory YouTube videos. These will provide a good introduction to linear algebra required
Khan academy also provides great content for mathmatical fundamentals related to machine learning.
Matrix algebra for engineers: Coursera
This course defines matricies, systems of linear equations, vector spaces, determinants. This is an in depth discovery with assignments and quizzes to ensure you understand fundamentals of matrices.
Fat Chance: Probability from ground up: EdX
This Harvard University course introduces fundamental concepts related to probability.
Linear Algebra: Great Courses Plus
Advanced Machine Learning Specialisation (Coursera)
This course introduces deep learning, reinforcement learning and applied to computer vision and natural language processing. The course is aimed at introducing advanced machine learning concepts through seven sub courses.
Machine Learning specialisation (EdX)
This course includes a wide range of machine learning models at a n advanced level . The first half of the course focuses on supervised learning, while second half unsupervised models such as reinforcement learning. Key models covered include: maximum likelihood estimation, linear regression and least squares, all the way through to continuous state-space models and association analysis.
Reinforcement Slides:
David Silver
Good info on Pandas: Data Science Made Simple
Reference Book: Wes Mckinney: Python for Data Analysis
Conferences: Pydata