How to learn machine learning as a complete beginner: a self-study guide

A step-by-step roadmap of how to learn machine learning as a beginner.

------------

BOOK RECOMMENDATIONS

Grokking Deep Learning by Andrew Trask

The 100-page Machine Learning Handbook by Andriy Burkov

Deep Learning with PyTorch by Laura Mitchell, Sri Yogesh K, and Vishnu Subramanian

1a. FEED-FORWARD NEURAL NETWORKS

Grokking Deep Learning (Chapters 2,3)

The 100-page Machine Learning Handbook (Chapter 3.1, 3.2, Chapter 6)

1b. GRADIENT DESCENT / BACKPROPAGATION

Grokking Deep Learning (Chapters 4,6)

Chapter 2 of Book by Michael Nielsen:

2. CONVOLUTIONAL NEURAL NETWORKS

Two videos by Computerphile:

Deep Learning with PyTorch (Chapter 5)

3. RECURRENT NEURAL NETWORKS

Grokking Deep Learning (Chapters 11 and 12)

4. AUTOENCODERS

Deep Learning with Pytorch (Chapter 6).

Video playlist by Digital Sreeni:

5. REINFORCEMENT LEARNING

Deep Learning with Pytorch (Chapter 9).

6. ATTENTION

Intro: (0:00)
Three book recommendations: (0:53)
Feed-Forward Neural Networks: (2:06)
Convolutional Neural Networks: (4:12)
Recurrent Neural Networks: (5:21)
Autoencoders: (6:36)
Reinforcement Learning: (7:20)
Attention: (7:54)
General Tips: (9:06)

[Aleph]

the next video is going to be a math explainer video, so stay tuned!! 👀

[iamtraditi]

Pitching in to say: make videos on whatever you want to make videos on. If this is what you want, go for it. I personally prefer the pure math stuff, so if you’d prefer to talk about that please keep at it :)

[muratkoptur]

1:47 In reality, one will use scikit-learn most of time because:

1. You will not have enough data for training neural nets.
2. Even if you have enough data for training neural nets, you need a baseline model (let's say logistic regression or random forests) for performance comparison.
3. scikit-learn is more useful for rapid prototyping.

[collatedcopies]

The Bahen Math Library is so underrated! Glad to see someone else is taking out books there too.

[asdf]

For reinforcement learning the video series by Mutual Information is an absolute must!

[syvisaur]

Shouldn't this rather be a self-study guide for deep learning rather than machine learning? (Although nowadays the difference is quite blurry)

[zerohorns]

The goat is back when we needed him the most

[DelandaBaudLacanian]

I took so many notes on the resources, books and videos you shared. Thank you! Cant wait to see more

[Saiphysics]

Hi there,

Thank you so much for this amazing self-study guide! I have a request: Could you create a self-study guide video for Analysis and the prerequisites needed to learn it? I would greatly appreciate it.

Thank you!!

[duckymomo]

I likd and learned machine learning; I didn't have a good teacher or experience -- I would like to start all over again

[vittorinomandujanocornejo]

I think this video is the part one because Deep Learning is a branch of Machine learning. Also, learning these topics need the practical part: coding in notebooks, reading repositories, get the well known datasets and training some models.

[logician]

When they OpenAI scientists were studying how to train ChatGPT to learn machine learning, it was probably called "learning machine learning, machine learning machine learning"

Btw I love your videos, keep up the good content 👍

[mabeteekay]

Michael Nielson is one of the Greats!!!

[antoine]

For a few weeks i have been wondering How could I learn machine learning once my studies were over (at the end of the year). I could not have dreamt about a better video. Thank you

[natealbatros]

I really enjoyed the topic of this video, hope you make more on many different subjects in math physics and computer science

[JM-usfr]

Thanks for this video! I’m actually really curious how machine learning might be used to search for more efficient algorithms

[MichaelMaths_]

Why are the pure math elitists so pissed off in the comments 😂

There are still a lot of pure math topics in the backbone of ML and this is nothing close to the intense meat-riding of more mainstream AI/ML channels

[oberstoffer]

thanks for the nice video and the literature list. perfect 🙂

[NathanatUuiu]

What car do you have? It looks really sleek and clean. If it’s a Tesla could you specify which model? Thanks.

[jerimiah]

PRML is the first book people should read, no question