I use these resources and they will (hopefully) help you in understanding the theoretical aspects of machine learning very well.
Do you want to learn the maths for machine learning but don't know where to start?
This thread is for you.
🧵👇
I use these resources and they will (hopefully) help you in understanding the theoretical aspects of machine learning very well.
Read this thread for more details👇
https://t.co/sSN3jdxDwK
Are you planning to learn Python for machine learning this year?
— Pratham Prasoon (@PrasoonPratham) February 13, 2021
Here's everything you need to get started.
\U0001f9f5\U0001f447
- Trigonometry & Algebra
These are the main pre-requisites for other topics on this list.
(There are other pre-requites but these are the most common)
To manipulate and represent data.
- Calculus
To train and optimize your machine learning model, this is very important.
> A series of videos that go over how neural networks work with approach visual, must watch.
🔗youtu.be/aircAruvnKk
> This website helps you learn statistics and probability in an intuitive way.
🔗seeing-theory.brown.edu/basic-probability/index.html
> This is 15 years old but still 100% relevant today!
Despite the fact these lectures are made for freshman college students at MIT, I found it very easy to follow👌
🔗youtube.com/playlist?list=PL49CF3715CB9EF31D
https://t.co/3H7U2HJgTd
This is a beginner-friendly introduction to:
— Pratham Prasoon (@PrasoonPratham) January 24, 2021
Linear Algebra for Machine Learning.
\U0001f9f5\U0001f447
> A beautiful playlist of videos which teach you linear algebra through visualisations in an easy to digest manner.
🔗youtube.com/watch?v=fNk_zzaMoSs&list=PLZHQObOWTQDPD3MizzM2xVFitgF8hE_ab
>You'll find a course on everything here! Khan Academy is the first place I'll go to when I want to learn something.
🔗khanacademy.org/math
> A beautiful series on calculus, makes everything seem super simple.
🔗youtube.com/watch?v=WUvTyaaNkzM&list=PL0-GT3co4r2wlh6UHTUeQsrf3mlS2lk6x
More from Pratham Prasoon
This is a step-by-step guide on getting started with Python as a total beginner.
(includes free resources and everything else you need to get started)
🧵👇
Before we begin, I want to congratulate you on your decision to learn how to code using Python.
I still remember how I wrote my first piece of code 6 years and all the amazing and cool things I've been able to do with it ever since.
(2 / 24)
Make sure to keep in mind that it is probably best for you to keep your expectations in check.
Don't expect to make AAA games or state of the art machine learning models in a week.
(3 / 24)
Programming is not something that you can learn in a single week, it takes consistent effort and dedication over time to get good at it.
With all that being said, let's dive straight in.
(4 / 24)
In order to write Python code, you'll need to install Python on your system.
Linux and macOS users can skip this step because they come pre-installed with Python.
Download link: https://t.co/KSZ4Qd6CNk
(5 / 24)
(includes free resources and everything else you need to get started)
🧵👇
Before we begin, I want to congratulate you on your decision to learn how to code using Python.
I still remember how I wrote my first piece of code 6 years and all the amazing and cool things I've been able to do with it ever since.
(2 / 24)
Make sure to keep in mind that it is probably best for you to keep your expectations in check.
Don't expect to make AAA games or state of the art machine learning models in a week.
(3 / 24)
Programming is not something that you can learn in a single week, it takes consistent effort and dedication over time to get good at it.
With all that being said, let's dive straight in.
(4 / 24)
In order to write Python code, you'll need to install Python on your system.
Linux and macOS users can skip this step because they come pre-installed with Python.
Download link: https://t.co/KSZ4Qd6CNk
(5 / 24)
More from Machine learning
You May Also Like
1/ Some initial thoughts on personal moats:
Like company moats, your personal moat should be a competitive advantage that is not only durable—it should also compound over time.
Characteristics of a personal moat below:
2/ Like a company moat, you want to build career capital while you sleep.
As Andrew Chen noted:
3/ You don’t want to build a competitive advantage that is fleeting or that will get commoditized
Things that might get commoditized over time (some longer than
4/ Before the arrival of recorded music, what used to be scarce was the actual music itself — required an in-person artist.
After recorded music, the music itself became abundant and what became scarce was curation, distribution, and self space.
5/ Similarly, in careers, what used to be (more) scarce were things like ideas, money, and exclusive relationships.
In the internet economy, what has become scarce are things like specific knowledge, rare & valuable skills, and great reputations.
Like company moats, your personal moat should be a competitive advantage that is not only durable—it should also compound over time.
Characteristics of a personal moat below:
I'm increasingly interested in the idea of "personal moats" in the context of careers.
— Erik Torenberg (@eriktorenberg) November 22, 2018
Moats should be:
- Hard to learn and hard to do (but perhaps easier for you)
- Skills that are rare and valuable
- Legible
- Compounding over time
- Unique to your own talents & interests https://t.co/bB3k1YcH5b
2/ Like a company moat, you want to build career capital while you sleep.
As Andrew Chen noted:
People talk about \u201cpassive income\u201d a lot but not about \u201cpassive social capital\u201d or \u201cpassive networking\u201d or \u201cpassive knowledge gaining\u201d but that\u2019s what you can architect if you have a thing and it grows over time without intensive constant effort to sustain it
— Andrew Chen (@andrewchen) November 22, 2018
3/ You don’t want to build a competitive advantage that is fleeting or that will get commoditized
Things that might get commoditized over time (some longer than
Things that look like moats but likely aren\u2019t or may fade:
— Erik Torenberg (@eriktorenberg) November 22, 2018
- Proprietary networks
- Being something other than one of the best at any tournament style-game
- Many "awards"
- Twitter followers or general reach without "respect"
- Anything that depends on information asymmetry https://t.co/abjxesVIh9
4/ Before the arrival of recorded music, what used to be scarce was the actual music itself — required an in-person artist.
After recorded music, the music itself became abundant and what became scarce was curation, distribution, and self space.
5/ Similarly, in careers, what used to be (more) scarce were things like ideas, money, and exclusive relationships.
In the internet economy, what has become scarce are things like specific knowledge, rare & valuable skills, and great reputations.
