This is the last issue of TheSequence in 2021. Thank you for reading us, giving us your feedback, and spreading the word. Recently, we’ve started to develop our Twitter account. With over 12,000 followers there, we see that the ML courses are in high demand. So we decided to put together a list of eight great courses that were highly acclaimed on our Twitter. All courses are online and free. Enjoy and share with your friends. 🎄We wish you a very Happy New Year!🎄

Follow us on Twitter

• Yann LeCun and Alfredo Canziani’s Deep Learning Course at the Center of Data Science at NYU.

  “This course concerns the latest techniques in deep learning and representation learning, focusing on supervised and unsupervised deep learning, embedding methods, metric learning, convolutional and recurrent nets, with applications to computer vision, natural language understanding, and speech recognition.”

TheSequence @TheSequenceAI

Yann LeCun’s @ylecun Deep Learning Course is now free & fully online at @NYUDataScience Videos, slides, notes, and notebooks! cds.nyu.edu/deep-learning/

November 13th 2021

684 Retweets2,271 Likes

Share

• Linear Algebra Course by Gilbert Strang at MIT.

  “This course covers matrix theory and linear algebra, emphasizing topics useful in other disciplines such as physics, economics and social sciences, natural sciences, and engineering. It parallels the combination of theory and applications in Professor Strang’s textbook Introduction to Linear Algebra.”

• NLP with Deep Learning by Christopher Manning at Stanford University.

  “Natural language processing (NLP) is a crucial part of artificial intelligence (AI), modeling how people share information. In recent years, deep learning approaches have obtained very high performance on many NLP tasks. In this course, students gain a thorough introduction to cutting-edge neural networks for NLP.”

• Learning From Data is an introductory course in ML by Yaser Abu-Mostafa at Caltech.

  “This course balances theory and practice, and covers the mathematical as well as the heuristic aspects. The lectures follow each other in a story-like fashion: What is learning? Can a machine learn? How to do it? How to do it well?

• Full-stack production deep learning (DL) by Full Stack Deep Learning and UC Berkeley.

  “Training the model is just one part of shipping a DL project. This course teaches full-stack production DL: Formulating the problem and estimating project cost; Finding, cleaning, labeling, and augmenting data; Picking the right framework and compute infrastructure; Troubleshooting training and ensuring reproducibility; Deploying the model at scale. It is aimed at people who already know the basics of DL and want to understand the rest of the process of creating production DL systems.”

• Introduction to Robotics course by Khatib Oussama at Stanford University.

  “The purpose of this course is to introduce you to basics of modeling, design, planning, and control of robot systems. In essence, the material treated in this course is a brief survey of relevant results from geometry, kinematics, statics, dynamics, and control.”

• Linear Algebra Review by J. Zico Kolter at Carnegie Melon University.

  “This short course is a quick review of linear algebra, intended for students who have already taken a previous course in linear algebra or have some experience with vectors and matrices. The goal of the review is to highlight basic notation, operations, and matrix manipulations that are used frequently in fields like machine learning and optimization.”

• Math Background for Machine Learning from Carnegie Melon University.

  “This course provides a place for students to practice the necessary mathematical background for further study in machine learning. Topics covered include probability, linear algebra (inner product spaces, linear operators), multivariate differential calculus, optimization, and likelihood functions.”

😎 For your 2022 reading resolution

We highly recommend these book recommendations from our interviews with ML practitioners.

TheSequence

📚 Your Reading List for 2022

📕📒📗 Happy holidays dear friends! In case you were planning your reading lists for the next year or a gift for a friend, we put together a few recommendations from the ML practitioners and entrepreneurs we talked to this year. Enjoy the reading and share this list if you like it! 💜…

Read more

8 days ago · 11 likes · Ksenia Semenova

We will continue to cover all the important concepts and papers in 2022 and we will introduce you to the variety of startups working in the ML field. It’s a fascinating time of rapid development and fruitful competition. And it’s very hard to keep up. That’s why we are here for you. If you’d like to stay tuned and also support our cause – consider subscribing or giving a gift subscription. Thank you!