Thread by @svpino

Thoughts about starting with machine learning.

☕️🧵👇

Three unnegotiable prerequisites:

1. Software development
2. Algorithms and data structures
3. Communication

If you build a strong foundation on these, you'll be unstoppable.

Learn to build software.

It's hard to make progress with machine learning if you struggle with programming.

Don't listen to those who shit on Algorithms and Data Structures and label them as "useless."

Believe me, if you take the time, these will give you a leg up for what's about to come.

Communication has many different angles.

Start with the following two questions:

- How do I ask the right question?
- How do I provide the right answer?

Yes, you can do machine learning with a lot of different programming languages.

But why would you make it harder on yourself?

Learn Python 🐍.

The right amount of Math at the right time is important.

I promise it's way less scary than what you currently believe.

Start working on problems. Add math as you need it.

While you are learning, don't worry about the code.

Coding is easy. Thinking is darn hard.

Focus on the analysis.

No-code tools are a superpower.

Look into Weka and learn how you can use it to avoid writing code that somebody already wrote.

If you are looking for a course, start with the first one you hear about.

Don't worry about "the best" one.

Google's Machine Learning Crash Course is a great way to start from the beginning.

Hard to beat a good book (or two). These are my all-time favorites:

Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow
💰 amzn.to/2KPuRAo

Deep Learning with Python
💰 amzn.to/3lpNEPn

When starting, focus on understanding the power of representations and getting as good as you can at feature engineering.

Feed garbage to your fancy algorithms and they will give you garbage back. No exceptions.

4 libraries you will never fully learn, but you'll have to keep trying:

- NumPy
- Pandas
- Scikit-Learn
- Matplotlib

Learn how to use notebooks (Jupyter, Google Colab.)

They will be an essential part of your career.

Here is the overall, high-level machine learning process that you'll need to follow:

1. Define the Problem
2. Prepare Data
3. Choose an algorithm
4. Improve Results
5. Present Results

If you want to get more specific, here are some of the steps:

▫️ Analyze the problem
▫️ Gather the data
▫️ Prepare the data
▫️ Choose the right model
▫️ Train the model
▫️ Evaluate the results
▫️ Look for biases
▫️ Tune it
▫️ Deploy the model
▫️ Monitor it
▫️ Retrain it

9 questions you need to keep asking:

1 What problem am I solving?
2 Why do I need to solve it?
3 What data do I have?
4 How is the data biased?
5 How do I transform it?
6 How do I collect more?
7 How do I model this?
8 What does success look like?
9 How do I productize it?

Neural networks are hot. I'd recommend you ignore them at the beginning.

Instead, here is a good list to kick off your learning:

1. Linear regression
2. Logistic regression
3. Decision Trees
4. K-NN

I source good problems from Kaggle.

I'd recommend you start with the Titanic competition.

The House Pricing challenge is another great problem where you can learn a ton.

Machine learning doesn't end with a model.

If you can't serve those predictions in a reliable and scalable way, you will have a hard time selling your value.

(Research positions work differently.)

A real problem: we are putting models out there that are horribly biased and shaping society in ways we are just beginning to see.

Ethics is not an optional subject.

Looking for kick-ass online courses?

- Coursera - Machine Learning
- Coursera - Deep Learning Specialization
- MIT 6.S191 Introduction to Deep Learning
- DS-GA 1008 Deep Learning
- UC Berkeley Full Stack Deep Learning
- Cornell Tech CS 5787 Applied Machine Learning

Machine learning is not easy, but it's not impossible.

Take it one day at a time.

I promise it's going to be well worth it.