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)

📘 Mathematics for Machine Learning

by Marc Peter Deisenroth, A. Aldo Faisal, and Cheng Soon Ong

https://t.co/zSpp67kJSg

Note: this is probably the place you want to start. Start slowly and work on some examples. Pay close attention to the notation and get comfortable with it.
📘 Pattern Recognition and Machine Learning

by Christopher Bishop

Note: Prior to the book above, this is the book that I used to recommend to get familiar with math-related concepts used in machine learning. A very solid book in my view and it's heavily referenced in academia.
📘 The Elements of Statistical Learning

by Jerome H. Friedman, Robert Tibshirani, and Trevor Hastie

Mote: machine learning deals with data and in turn uncertainty which is what statistics teach. Get comfortable with topics like estimators, statistical significance,...
📘 Probability Theory: The Logic of Science

by E. T. Jaynes

Note: In machine learning, we are interested in building probabilistic models and thus you will come across concepts from probability theory like conditional probability and different probability distributions.
📺 Multivariate Calculus by Imperial College London

by Dr. Sam Cooper & Dr. David Dye

https://t.co/OYaqzlXmJG

Note: backpropagation is a key algorithm for training deep neural nets that rely on Calculus. Get familiar with concepts like chain rule, Jacobian, gradient descent,.
📜 The Matrix Calculus You Need For Deep Learning

by Terence Parr & Jeremy Howard

https://t.co/Gk96dRsX5t

Note: In deep learning, you need to understand a bunch of fundamental matrix operations. If you want to dive deep into the math of matrix calculus this is your guide.
📺 Mathematics for Machine Learning - Linear Algebra

by Dr. Sam Cooper & Dr. David Dye

https://t.co/lNYLiMKLma

Note: a great companion to the previous video lectures. Neural networks perform transformations on data and you need linear algebra to get better intuitions.
📘 Information Theory, Inference and Learning Algorithms

by David J. C. MacKay

Note: When you are applying machine learning you are dealing with information processing which in essence relies on ideas from information theory such as entropy and KL Divergence,...

More from elvis

Amazing resources to start learning MLOps, one of the most exciting areas in machine learning engineering:



📘 Introducing MLOps

An excellent primer to MLOps and how to scale machine learning in the enterprise.

https://t.co/GCnbZZaQEI


🎓 Machine Learning Engineering for Production (MLOps) Specialization

A new specialization by https://t.co/mEjqoGrnTW on machine learning engineering for production (MLOPs).

https://t.co/MAaiRlRRE7


⚙️ MLOps Tooling Landscape

A great blog post by Chip Huyen summarizing all the latest technologies/tools used in MLOps.

https://t.co/hsDH8DVloH


🎓 MLOps Course by Goku Mohandas

A series of lessons teaching how to apply machine learning to build production-grade products.

https://t.co/RrV3GNNsLW
The past month I've been writing detailed notes for the first 15 lectures of Stanford's NLP with Deep Learning. Notes contain code, equations, practical tips, references, etc.

As I tidy the notes, I need to figure out how to best publish them. Here are the topics covered so far:


I know there are a lot of you interested in these from what I gathered 1 month ago. I want to make sure they are high quality before publishing, so I will spend some time working on that. Stay


Below is the course I've been auditing. My advice is you take it slow, there are some advanced concepts in the lectures. It took me 1 month (~3 hrs a day) to take rough notes for the first 15 lectures. Note that this is one semester of

I'm super excited about this project because my plan is to make the content more accessible so that a beginner can consume it more easily. It's tiring but I will keep at it because I know many of you will enjoy and find them useful. More announcements coming soon!

NLP is evolving so fast, so one idea with these notes is to create a live document that could be easily maintained by the community. Something like what we did before with NLP Overview: https://t.co/Y8Z1Svjn24

Let me know if you have any thoughts on this?

More from Data science

✨✨ BIG NEWS: We are hiring!! ✨✨
Amazing Research Software Engineer / Research Data Scientist positions within the @turinghut23 group at the @turinginst, at Standard (permanent) and Junior levels 🤩

👇 Here below a thread on who we are and what we

We are a highly diverse and interdisciplinary group of around 30 research software engineers and data scientists 😎💻 👉
https://t.co/KcSVMb89yx #RSEng

We value expertise across many domains - members of our group have backgrounds in psychology, mathematics, digital humanities, biology, astrophysics and many other areas 🧬📖🧪📈🗺️⚕️🪐
https://t.co/zjoQDGxKHq
/ @DavidBeavan @LivingwMachines

In our everyday job we turn cutting edge research into professionally usable software tools. Check out @evelgab's #LambdaDays 👩‍💻 presentation for some examples:

We create software packages to analyse data in a readable, reliable and reproducible fashion and contribute to the #opensource community, as @drsarahlgibson highlights in her contributions to @mybinderteam and @turingway: https://t.co/pRqXtFpYXq #ResearchSoftwareHour
Wellll... A few weeks back I started working on a tutorial for our lab's Code Club on how to make shitty graphs. It was too dispiriting and I balked. A twitter workshop with figures and code:


Here's the code to generate the data frame. You can get the "raw" data from https://t.co/jcTE5t0uBT


Obligatory stacked bar chart that hides any sense of variation in the data


Obligatory stacked bar chart that shows all the things and yet shows absolutely nothing at the same time


STACKED Donut plot. Who doesn't want a donut? Who wouldn't want a stack of them!?! This took forever to render and looked worse than it should because coord_polar doesn't do scales="free_x".

You May Also Like

So the cryptocurrency industry has basically two products, one which is relatively benign and doesn't have product market fit, and one which is malignant and does. The industry has a weird superposition of understanding this fact and (strategically?) not understanding it.


The benign product is sovereign programmable money, which is historically a niche interest of folks with a relatively clustered set of beliefs about the state, the literary merit of Snow Crash, and the utility of gold to the modern economy.

This product has narrow appeal and, accordingly, is worth about as much as everything else on a 486 sitting in someone's basement is worth.

The other product is investment scams, which have approximately the best product market fit of anything produced by humans. In no age, in no country, in no city, at no level of sophistication do people consistently say "Actually I would prefer not to get money for nothing."

This product needs the exchanges like they need oxygen, because the value of it is directly tied to having payment rails to move real currency into the ecosystem and some jurisdictional and regulatory legerdemain to stay one step ahead of the banhammer.