Goals for my ML course

▪️ For beginners
▪️ End-to-end
▪️ Practice instead of theory
▪️ Intuition instead of definition
▪️ Minimum math
▪️ Real-world dataset
▪️ Flexible example applications
▪️ Built with community feedback

Let's go through these points 👇
For beginners

Only Python knowledge will be required to do the course. No previous machine learning experience needed.
End-to-end

We will cover the whole pipeline - from collecting and cleaning data to deploying a trained model.

We will also discuss some topics like ethics and bias and problem framing.
Practice instead of theory

The course will be practice-oriented. It will not teach you the latest theoretical advances in the ML field, but it will give you the basics for all the building blocks you need to start building ML applications yourself.
Intuition instead of definition

I don't plan to go deep and explain all the details of concepts like backpropagation, optimization etc - there are enough courses that do that.

I will teach you the most important ideas and give you intuition on how you can use these concepts.
Minimum math

The point above means also less focus on math. While important to get a deep understanding and develop new techniques, only minimal math knowledge is needed to get started with ML and build a useful application!
Real-world dataset

We are not going to use MNIST or CIFAR 😀. All exercises will be using the (amazing) @unsplash dataset!

unsplash.com/data
Flexible example applications

There will also be no predefined application - you will be able to work on a problem you find interesting!
Built with community feedback

I plan to post lots of information about the creation process and collect feedback. I'm just finishing the first tutorial and I'll make it publicly available for anybody who is interested to take a look and share their opinion.

Stay tuned! 😀

• • •

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

Keep Current with Vladimir Haltakov

Vladimir Haltakov 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 @haltakov

15 Sep
Did you ever want to learn how to read ROC curves? 📈🤔

This is something you will encounter a lot when analyzing the performance of machine learning models.

Let me help you understand them 👇 Image
What does ROC mean?

ROC stands for Receiver Operating Characteristic but just forget about it. This is a military term from the 1940s and doesn't make much sense today.

Think about these curves as True Positive Rate vs. False Positive Rate plots.

Now, let's dive in 👇
The ROC curve visualizes the trade-offs that a binary classifier makes between True Positives and False Positives.

This may sound too abstract for you so let's look at an example. After that, I encourage you to come back and read the previous sentence again!

Now the example 👇
Read 19 tweets
14 Sep
Most people seem to use matplotlib as a Python plotting library, but is it really the best choice? 🤔

We are going to compare 5 free and popular libraries:
▪️ Matplotlib
▪️ Seaborn
▪️ Plotly
▪️ Bokeh
▪️ Altair

Which one is the best? Find out below 👇
In a survey I did the other day, matplotlib had the most users by a large margin. This was quite surprising to me since I don't really like it...



But let's first look at each library 👇
Matplotlib 📈

Matplotlib is one of the most popular libraries out there.

✅ Supports many types of plots
✅ Lots of customization options

❌ Plots look ugly
❌ Limited interactivity
❌ Not very intuitive to use
Read 11 tweets
9 Sep
I highly recommend listening to the latest eposide of @therobotbrains podcast with @ilyasut.

therobotbrains.ai/podcasts/episo…

Here are some insights I found particulalry interesting 👇
"Neural networks are parallel computers"

That is why they are so powerful - you can train a generic computer to solve your problem. This is also the driver behind Software 2.0 - neural network are becoming more and more capable of solving all kinds of problems.
"Neural networks perform well on tasks that humans can perform very quickly"

Humans don't think much when listening, observing or performing simple tasks.

This means that a neural network can be trained to be good at it as well: NLP, computer vision and reinforcement learning.
Read 4 tweets
9 Sep
My setup for recording videos for my machine learning course 🎥

A lot of people asked about my setup the other day, so here a short thread on that. It's nothing fancy, but it does a good job 🤷‍♂️

Details 👇
Hardware ⚙️

▪️ MacBook Pro (2015 model) - screen sharing and recording
▪️ iPhone XS - using the back camera for video recording
▪️ Omnidiretional external mic - connected to the iPhone
▪️ Highly professional camera rig - books mostly about cooking and travel 😄

👇
Software 💻

▪️ OBS Studio - recording of the screen and the camera image
▪️ EpocCam - use your iPhone as a web cam. You can connect your iPhone both over WiFi and cable.
▪️ Google Slides - for presentation
▪️ Jupyter notebooks and Google Colab - for experimenting with code

👇
Read 5 tweets
7 Sep
Let's talk about a common problem in ML - imbalanced data ⚖️

Imagine we want to detect all pixels belonging to a traffic light from a self-driving car's camera. We train a model with 99.88% performance. Pretty cool, right?

Actually, this model is useless ❌

Let me explain 👇
The problem is the data is severely imbalanced - the ratio between traffic light pixels and background pixels is 800:1.

If we don't take any measures, our model will learn to classify each pixel as background giving us 99.88% accuracy. But it's useless!

What can we do? 👇
Let me tell you about 3 ways of dealing with imbalanced data:

▪️ Choose the right evaluation metric
▪️ Undersampling your dataset
▪️ Oversampling your dataset
▪️ Adapting the loss

Let's dive in 👇
Read 13 tweets
6 Sep
How I format my Jupyter notebooks in VS Code 📒

I like using VS Code when working with Jupyter notebooks. One pain point has always been automatic code formatting, but now I have a good solution.

You need:
▪️ VS Code 1.60 (August 2021)
▪️ YAPF formatter

Details 👇
VS Code 1.60

The latest VS Code version from August 2021 contains many improvements for the native display of Jupyter notebooks (which came in July 2021). They now support the command Format Cell with which you can automatically format your code.

👇
Keyboard shortcuts

You can quickly do it with a keyboard shortcut.

▪️ Windows: Shift + Alt + F
▪️ Mac: Shift + Option + F
▪️ Linux: Ctrl + Shift + I

I had to remap Shift + Option + F on my Mac, because it seems to be a macOS shortcut for some strange character...
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!

:(