Santiago Profile picture
17 Apr, 11 tweets, 4 min read
Learning Python 🐍 is not just a prerequisite for getting into machine learning, but it's an investment that will help your career for the rest of your life.

A thread with my recommendations:

↓ 1/10
Before getting into it, if you have never coded before, make sure you build your Python skills to a point where you feel really comfortable solving problems.

Take your time, and don't rush it.

↓ 2/10
A lot of people want to read a book and immediately jump into machine learning.

Everything is possible in life, but I'd recommend you focus on building a strong coding foundation before moving on.

↓ 3/10
A good course you can use to start is "Introduction to Python Programming."

Here you'll learn Python's fundamentals, along with programming best practices, libraries, and everything you need to become a developer.

udacity.com/course/introdu…

↓ 4/10
Areas you should focus on:

β€’ General syntax
β€’ Basic data types
β€’ Strings
β€’ Arrays, Lists, Dictionaries, Tuples, Sets
β€’ Conditionals and control flow
β€’ Exception handling
β€’ Comprehensions
β€’ Slicing
β€’ Object-Oriented Programming
β€’ Decorators and generators

↓ 5/10
Another great resource is the Official Python Tutorial.

It will introduce you to the language's basic concepts and features and many of Python's most noteworthy features.

docs.python.org/3/tutorial/

↓ 6/10
There are a couple of libraries that you want to pay special attention to:

β€’ NumPy
β€’ Pandas

These two are fundamental for machine learning. Try to go through a few tutorials and learn how to use them early on.

↓ 7/10
My favorite source of Python information is @realpython's website.

You can learn all things Python from the ground up. Everything from the language's absolute basics to web development and web scraping to data visualization and beyond.

realpython.com

↓ 8/10
If you are looking for a book, you can't go wrong with the world's best-selling guide to the Python programming language.

amzn.to/3tZAwFq

↓ 9/10
Remember, you can do machine learning with a lot of different languages.

R, Java, C++, Julia, JavaScript, among other alternatives, are possible, but most of the community uses Python.

Why make it harder than it needs to be? Learning Python will be your best bet.

↓ 10/10
If you found this thread helpful, follow me @svpino
for weekly posts touching on machine learning and how to use it to build real-life systems.

It’s all about building value, and that’s way more fun if we do it together!

β€’ β€’ β€’

Missing some Tweet in this thread? You can try to force a refresh
γ€€

Keep Current with Santiago

Santiago Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @svpino

15 Apr
Challenge:

Here are 10 interesting questions about neural networks.

↓ 1/6
1. What's the best way to initialize the weights of a neural network?

2. What criteria would you follow to choose between mean squared error (MSE) and mean absolute error (MAE) as your loss function?

↓ 2/6
3. How do you determine the number of hidden layers that will best solve your problem?

4. How do you decide it is a good time to introduce a scheduler to decrease your learning rate?

5. For how long should you keep training your neural network?

↓ 3/6
Read 9 tweets
15 Apr
A short thread that will help you understand how a useful machine learning model differs from a crappy one.

(In English, without any jargon or math.)

This is also the way I first understood what "overfitting" means.

↓ 1/7
When building a machine learning model, our ultimate goal is to "generalize" the lessons it learns to unseen data.

When we train it, we expect it to extract what's relevant, discard what's not, and understand the data's underlying patterns.

↓ 2/7
Imagine we have an image, and we want to determine whether it's a picture of a person or not.

These are some features that could be relevant to the model:

β€’ There're two eyes
β€’ There's a nose
β€’ There's a mouth
β€’ There are ears

↓ 3/7
Read 8 tweets
14 Apr
This is a coffee from Starbucks. It costs $5.49.

You drink it in 5 minutes, and it's gone forever. And if you don't like it? Well, there's nothing you can do about that.

I have two deals for you that are much better than this. Read on.

↓
Deal 1 is the story of how I built my audience from 0 to 30,000 followers.

You can do the same, and I'll show you every trick and strategy that I followed.

And it's $5 only for the next 12 hours. The price goes back to $20 right after that.

Link: gum.co/LLhIW/crazy.
Deal 2 is even better! A few days ago, I launched a private community where I'm sharing my journey to 100,000 followers.

It's a small group right now with full access to every strategy, tip, and experiment that I'm running.

A Slack channel, weekly videos, a journal, and more.
Read 7 tweets
14 Apr
How important is having access to a GPU when we deploy a machine learning model?

Let's talk about this in this short thread.

↓ 1/7
We all know that having a GPU is a must to train a deep learning model, especially when we have a lot of data.

But that's during training. How about when using the model?

↓ 2/7
The right answer depends on the problem we are trying to solve, but more often than not, a GPU is not necessary during inference time.

And depending on its cost, a GPU might even be counterproductive: the value it gives us may pale compared to its cost.

↓ 3/7
Read 7 tweets
13 Apr
Something essential for aspiring machine learning practitioners is to find an area where they can specialize and build their reputation.

I've met many people who focus on a specific niche and have built a career in it.

Here are some examples of things you could do:

↓ 1/5
1. Computer Vision. Basically, this is about dealing with images and video.

2. Natural Language Processing and Understanding. Think about this as having to deal with text.

3. Recommendation systems is another popular area. Very useful for e-commerce companies.

↓ 2/5
4. Anomaly Detection focuses on detecting anomalous occurrences in the input data.

5. I've met a couple of people that focus exclusively on Time series analysis by helping companies forecast their metrics.

6. MLOps is a field that's gaining a lot of strength.

↓ 3/5
Read 9 tweets
12 Apr
If you are looking to get a background in math before starting with machine learning, here is all the material you need covering the following topics:

β€’ Probabilities & Statistics
β€’ Linear Algebra
β€’ Multivariate Calculus

More than enough to get started.

↓ 1/7
Seeing Theory

seeing-theory.brown.edu

An interactive website that will take you through some of the most critical concepts of Probabilities and Statistics.

These will be enough to get you started, and you will have fun while going through it!

↓ 2/7
Statistics 110: Probability

youtube.com/playlist?list=…

If you are looking for more, this course from Harvard University is an excellent introduction to probability as a language and a set of tools for understanding statistics, science, risk, and randomness.

↓ 3/7
Read 8 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!

Follow Us on Twitter!