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 equations.

https://t.co/GarhvVxXhG
⭐️ Introduction to Complex Analysis ⭐️

Learn about the geometry of complex numbers.

https://t.co/DgMuMCgAhr
⭐️ 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 well.

https://t.co/H4hK05t44b
⭐️ 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 basics.

https://t.co/ETeMiwTry1
⭐️ Data Mining Specialization ⭐️

The courses in this specialization provide a great overview of data mining techniques used for structured and unstructured data.

https://t.co/oGzoOGOMnU
⭐️ Algorithms ⭐️

In machine learning, we are programming sophisticated algorithms and it's important to understand key concepts in this subject before jumping straight into ML algorithms. In general, an Algorithms course builds a strong CS foundation.

https://t.co/bdlXphoJud
⭐️ Mathematics for Machine Learning Specialization ⭐️

Note: Includes courses for multivariate calculus and linear algebra. One of my favorite courses due to the quality of lectures and focused topics.

https://t.co/3Uf3iuni3z
⭐️ Statistics with Python Specialization ⭐️

This course is focused on the basics of statistics which is important when dealing with uncertainties, modeling, inference, etc. Although the courses focus on Python, there are other options using R as well.

https://t.co/yZOUQBTZNI
⭐️ An Intuitive Introduction to Probability ⭐️

Probability can become a difficult topic but it's a core concept of building probabilistic prediction models. This course can provide an intuitive introduction to core topics like conditional probability.

https://t.co/sGirM58T9p
Exposure to topics in these courses can help improve your knowledge/intuition needed to transition to machine learning.

The list is not exhaustive so if you have any courses you recommend, please reply below. In time, I will prepare a better and more focused ramping up guide.

More from elvis

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.
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

More from Education

** Schools have been getting ready for this: a thread **

In many ways, I don't blame folks who tweet things like this. The media coverage of the schools situation in Covid-19 rarely talks about the quiet, day-in-day-out work that schools have been doing these past 9 months. 1/


Instead, the coverage focused on the dramatic, last minute policy announcements by the government, or of dramatic stories of school closures, often accompanied by photos of socially distanced classrooms that those of us in schools this past term know are from a fantasy land. 2/


If that's all you see & hear, it's no wonder that you may not know what has actually been happening in schools to meet the challenges. So, if you'd like a glimpse behind the curtain, then read on. For this is something of what teachers & schools leaders have been up to. 3/

It started last March with trying to meet the challenges of lockdown, being thrown into the deep end, with only a few days' notice, to try to learn to teach remotely during the first lockdown. 4/

https://t.co/S39EWuap3b


I wrote a policy document for our staff the weekend before our training as we anticipated what was to come, a document I shared freely & widely as the education community across the land started to reach out to one another for ideas and support. 5/
https://t.co/m1QsxlPaV4
An appallingly tardy response to such an important element of reading - apologies. The growing recognition of fluency as the crucial developmental area for primary education is certainly encouraging helping us move away from the obsession with reading comprehension tests.


It is, as you suggest, a nuanced pedagogy with the tripartite algorithm of rate, accuracy and prosody at times conflating the landscape and often leading to an educational shrug of the shoulders, a convenient abdication of responsibility and a return to comprehension 'skills'.

Taking each element separately (but not hierarchically) may be helpful but always remembering that for fluency they occur simultaneously (not dissimilar to sentence structure, text structure and rhetoric in fluent writing).

Rate, or words-read-per-minute, is the easiest. Faster reading speeds are EVIDENCE of fluency development but attempting to 'teach' children(or anyone) to read faster is fallacious (Carver, 1985) and will result in processing deficit which in young readers will be catastrophic.

Reading rate is dependent upon eye-movements and cognitive processing development along with orthographic development (more on this later).

You May Also Like