I have always emphasized on the importance of mathematics in machine learning.

Here is a compilation of resources (books, videos & papers) to get you going.

(Note: It's not an exhaustive list but I have carefully curated it based on my experience and observations)

There is a lot of interest in large language models.

As a developer or researcher, you are probably looking for a guide on how to ramp up on LLMs.

Here is a study plan you could try:

My suggested study plan for now: 1) get familiar with concepts, 2) learn about Transformers, 3) learn about the foundation models, 4) continue keeping track of code, papers, and results, and 5) get building.

1) CS224N: Natural Language Processing with Deep Learning

It doesn't hurt to learn some of the concepts first. Depending on your level of knowledge it might be suitable to try a more basic

2) Stanford CS25 - Transformers United

Learn all about transformers in this fantastic

3) Foundation Models

You can learn about all types of foundation models like GPT-3, DINO, CLIP, Codex, among

Recently, I shared a list of some courses that were useful in my transition to machine learning.

While I took most of the courses in person, there are some alternative online courses you can check out.

Here is a thread of a few interesting online courses based on the list:

⭐️ Linear Algebra ⭐️

A classical online course by Professor Gilbert Strang based on his popular textbook "Introduction to Linear Algebra". Learn about matrix theory and systems of

⭐️ Introduction to Complex Analysis ⭐️

Learn about the geometry of complex

⭐️ Differential Calculus ⭐️

Pay close attention to the chain rule as it's heavily referenced in machine learning, specifically when discussing optimization. This course is part of a specialization called MathTrackX. I recommend checking that as

⭐️ Information Theory ⭐️

When you are working with machine learning algorithms applied to data you are dealing with information processing which in essence relies on ideas from information theory such as entropy. This course should provide the

🔥 Applied Deep Learning - 2021 🔥

Just came across this absolute gem.

200+ free video lectures on all sorts of topics related to deep learning.

From Graph Attention Networks to RL algorithms.

repo: https://t.co/2IRF3CcR5p

playlist: https://t.co/N4zqkqnfdu

Some of the most amazing applications of machine learning will probably come from folks working on brain-computer interface (BCI).

Check out this new paper discussing high-performance brain-to-text communication via handwriting.

Future of programming?

https://t.co/I5DUnE4vpy

Tired of word clouds? Want to do better sentiment analysis? Not sure how to look at the words underneath your measures?

Our long overdue paper on generalized word shift graphs is finally here!
https://t.co/lIBXvbMJWX
https://t.co/vSL1REYT8V

So what are they?

1/n

If we have two texts, there are many ways we can compare them. Weighted averages are a particularly useful measure because they're flexible and interpretable

Proportions, Shannon entropy, the KLD, the JSD, and dictionary methods can all be written as weighted averages

2/n

But weighted avgs are also slippery. When we try to compress complex phenomena like happiness, surprise, divergence, or diversity into a single number, it can be unclear what we're measuring

If the measure goes up, what does that mean? Why did it do that? Can we trust it?

3/n

Very often, that's the end of the line and we're left with an uneasy feeling in the pit of our stomach that our weighted avg is actually picking up a data artifact or some other unintended peculiarity

Word shift graphs help us address those concerns

4/n

First, word shifts look under the hood of weighted averages to see what's going on

All weighted averages are a sum of contributions from individual words. We can pull out those words, and rank which ones contribute the most to the difference between two texts

5/n

This post is pretty bizarre, but it manages to hit on so many false beliefs that I've seen hurt junior data scientists that it deserves some explicit

(1) The notion that R is well-suited to "building web applications" seems totally out of left field. I don't feel like most R loyalists think this is a good idea, but it's worth calling out that no normal company will be glad you wrote your entire web app in R.

(2) It is true that Python had some issues historically with the 2-to-3 transition, but it's not such a big deal these days. On the flip side, I have found interesting R code that doesn't run in modern R interpreters because of changes in core operations (e.g. assignment syntax).

(3) "Most of the time we only need a latest, working interpreter with the latest packages to run the code" -- this is where things get real and reveal some things that hurt data scientists. If this sentence is true, it's likely because you don't share code with coworkers.

(3) Really is a broader issue in data science: people only think of what they need to do their work if no one else existed and code was never maintained. Junior data scientists almost always operate on projects they start from scratch and don't have to maintain for long.