#73 overallEvergreen
Calculus
Khan Academy
6 recommenders · 6 threads · recommended in 6 years, 2011–2026 · score 6.7
Khan Academy's free online Calculus course, a video-and-exercise series covering calculus from basics through early undergraduate level, with a related set of math topics on the same site.
Commenters call Khan Academy's calculus videos one of the easiest ways to learn the math prerequisites for machine learning, and say its exercises and mastery system help the material stick.
Mathematicsbeginnerfreemixed#calculus#derivatives#video lessons#practice exercises#math prerequisites
Recommendations by year
20062026
Khan Academy is an amazing true MOOC resource. The calculus goes up to early undergrad. The differential calculus is the most important for ML, in my oppinion.
Probability and statistics will help ML as well.
I would recommend Khan Academy before any other resources, whatever your level. It has online exercises with auto-correction, and a mastering system that uses spaced repetition. This will ensure you'll actually assimilate the material. After you can use another resource as a reference.
Go for it! Khan academy calculus and algebra courses are awesome. Also, Calculus One on Coursera is really good.
Since I'm between jobs, I've been taking the time to relearn geometry, trig, calc, and linear algebra. I've finished the first two and it's both humiliating and really fun to relearn some math. As an adult, I feel a very different appreciation for how much fundamental math we take for granted. I definitely recommend https://www.khanacademy.org/ and pauls notes (https://tutorial.math.lamar.edu/).
Yes for linear algebra, though it's probably best suited to people with at least some exposure to matrix/vector math (for example you've used SVD but have no idea how or why it works): https://www.fast.ai/2017/07/17/num-lin-alg/
For probability, machine learning is more about statistics (the two are related, but courses explicitly about probability will cover different things), so I would lean towards that. An Introduction to Statistical Learning in R (ISLR) is a frequently recommended book. You can ignore the R and do the exercises in Python.
If you actually want to learn about probability, you can look at MIT's course: https://ocw.mit.edu/resources/res-6-012-introduction-to-prob...
EDIT: If you've never been exposed to calculus, many people swear by Khan Academy's videos.
Good post. I want to add several great resources.
- Grokking Deep Learning
https://www.manning.com/books/grokking-deep-learning
This is a fantastic book that assumes no prerequisites other than knowing python, and takes you through the fundamentals of DL. It has very intuitive and easy to follow explanations, and doesn't use any libraries other than NumPy, so you're building the whole thing yourself, from scratch.
- Deep Learning With Python
https://machinelearningmastery.com/deep-learning-with-python...
This is kind of the opposite of the previous one, it doesn't go into math and theory, instead it guides you through building several practical projects with a very simple to use DL library(keras). It's a great way to gain practical experience in addition to theory from the previous book. Also has no prerequisites other than python, and makes it very easy to get started.
- 3blue1brown videos on neural networks:
https://www.youtube.com/playlist?list=PLZHQObOWTQDNU6R1_6700...
Extremely brilliant high-level concise overview of how ANNs work. I highly recommend you get started here. You should also check out his videos on calulus and linear algebra, they're fantastic way to learn the math you need.
- Khan Academy videos - one of the easiest ways to learn the math prerequisites.
Calculus:
https://www.khanacademy.org/math/calculus-home
Linear Algebra:
https://www.khanacademy.org/math/linear-algebra
Probability and Statistics:
https://www.khanacademy.org/math/statistics-probability
- Hands-On Machine Learning with Scikit-Learn and TensorFlow
http://shop.oreilly.com/product/0636920052289.do
I haven't read this one yet, but it looks very promising, and a lot of people seem to find it very useful.
- Andrew Ng's Coursera course
https://www.coursera.org/learn/machine-learning
Everyone knows about this one, I just think every article on AI resources should mention it, one of the most popular ways to get started with ML.
- New MIT courses on Self-Driving cars and AGI
https://selfdrivingcars.mit.edu
https://agi.mit.edu
- The Master Algorithm
https://www.audible.com/pd/Science-Technology/The-Master-Alg...
Excellent high-level overview of ML field and algorithms.
====
Other great stuff:
- Artificial Intelligence: A Modern Approach
http://aima.cs.berkeley.edu/
The leading textbook in Artificial Intelligence. It's not the fastest way to get started, but it's considered one of the best AI textbooks ever written.
- Stanford AI course (CS 188)
https://www.youtube.com/playlist?list=PLIeooNSdhQE5kRrB71yu5...
Brilliant course based on AIMA. Not DL, but solid fundamentals of AI and ML.
- Couple of great playlists on DL, just to complete the collection:
Machine Learning with Python
https://www.youtube.com/playlist?list=PLQVvvaa0QuDfKTOs3Keq_...
Neural Networks Demystified
https://www.youtube.com/watch?v=bxe2T-V8XRs&index=1&list=PLi...
It's been 15 years since I took Calculus I and II, but looking over: http://www.khanacademy.org/#Calculus
Is there _anything_ in Stewart that isn't covered as well by Khan? You also get advantage of the video tutorial on the topic.
I'm waiting for that point in time when we reach a tipping point and Higher Education Institutions don't just delegate everything to Khan for a lot of their topics.
My Calculus Course (151) at SFU took place in Images Theater at 8:30 in the morning and had 450 Students listening to a lecture on Calculus. The ratio was approximately: 1/8 of the students were bored. 1/8 of the students were lost, 1/8 of the students were attentive, 1/8 of the students were asleep, and 1/2 of the students didn't show up. (8:30 AM!)
I see little need for Stewart in the Face of Khan's Video Collection on Calculus + a bit of wikipedia (Seriously - check out their section on Derivatives and compare it to Stewart)
I will agree with you on the Problem Sets - and perhaps that's the missing ingredient in Khan - He needs to more fully flesh out his test bank - but http://www.khanacademy.org/exercisedashboard is moving ahead nicely. (And, in my mind, is far superior to any static test bank)