Tweet

Tivadar Danka

19 Oct, 29 tweets, 12 min read

The single best way to get into machine learning is to build something with it.

Here is an extensive list of hands-on projects that you can start right now. Take inspiration, learn tools, and find the topics you are passionate about.

Read on and go create something awesome. ↓

I am grouping the projects into the following categories.

📺 Computer vision
🗣️ NLP
🎮 Reinforcement learning
🗄️ Data engineering
📊 Visualization
☁️ Deployment

A few thoughts before we start.

These hands-on projects work the best when you
• follow along and do the coding as well,
• understand why and how things work,
• and try to bring what you built to the next level.

Most of these projects are just scratching the surface, but they are excellent for getting your feet wet and inspiring you to take them further.

The real work starts when you start building by yourself.

Let's start!

@NeuralNine

📺 Computer vision

1. Neural Network Python Project - Handwritten Digit Recognition (by @NeuralNine)

@nicholasrenotte

2. Real Time Face Mask Detection with Tensorflow and Python (by @nicholasrenotte)

@aladdinpersson

3. CycleGAN implementation from scratch in PyTorch (by @aladdinpersson)

@abhi1thakur

4. Implementing original U-Net from scratch using PyTorch (by @abhi1thakur)

@nicholasrenotte

5. Tensorflow Object Detection in 5 Hours with Python | Full Course with 3 Projects (by @nicholasrenotte)

@lmoroney

6. Anomaly detection with TensorFlow (by @lmoroney)

@Sentdex

7. Autoencoders in Python with TensorFlow/Keras (by @Sentdex)

@NeuralNine

🗣️ NLP

1. Intelligent AI Chatbot in Python (by @NeuralNine)

@python_engineer

2. Chat Bot With PyTorch - NLP Beginner Tutorial (by @python_engineer)

youtube.com/playlist?list=…

@nicholasrenotte

3. Sentiment Analysis with BERT Neural Network and Python (by @nicholasrenotte)

@curiousily

4. Text Classification | Sentiment Analysis with BERT using huggingface, PyTorch and Python (by @curiousily)

@curiousily

5. Intent Recognition with BERT using Keras and TensorFlow 2 in Python (by @curiousily)

@nicholasrenotte

🎮 Reinforcement learning

1. Deep Reinforcement Learning for Atari Games Python Tutorial (by @nicholasrenotte)

@freecodecamp

2. Deep Reinforcement Learning in Python Tutorial - A Course on How to Implement Deep Learning Papers (by Phil Tabor and @freecodecamp)

@python_engineer

3. Teach AI To Play Snake! Reinforcement Learning With PyTorch and Pygame (by @python_engineer)

youtube.com/playlist?list=…

@JimShapedCoding

🗄️ Data engineering

1. Web Scraping with Python - Beautiful Soup Crash Course (by @JimShapedCoding)

@python_engineer

2. YouTube Data API - Python Tutorials (by @python_engineer)

youtube.com/playlist?list=…

@keithgalli

3. Sales Analysis - Solving real world data science tasks with Python Pandas! (by @keithgalli)

@keithgalli

4. Solving real world data science tasks with Python Beautiful Soup! (movie dataset creation) (by @keithgalli)

@thedataprof

📊 Visualization

1. Build 12 Data Science Apps with Python and Streamlit (by @thedataprof)

@python_engineer

2. Build A Beautiful Machine Learning Web App With Streamlit And Scikit-learn (by @python_engineer)

@curiousily

☁️ Deployment

1. Deploy with FastAPI | | Sentiment Analysis with BERT using huggingface, PyTorch and Python Tutorial (by @curiousily)

@python_engineer

2. Create & Deploy A Deep Learning App - PyTorch Model Deployment With Flask & Heroku (by @python_engineer)

And that's it!

Don't forget that these are just starting points. Use what you have learned to create something even more impressive!

Your results will speak for themselves if you put in the hard work.

I post threads like this every week, diving deep into concepts in machine learning and mathematics.

If you have enjoyed this, make sure to follow me and stay tuned for more!

Now go and start building, you amazing person.

• • •

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

This Thread may be Removed Anytime!

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

More from @TivadarDanka

Tivadar Danka

@TivadarDanka

11 Oct

There is much more to machine learning than training models.

Most courses focus exclusively on this, but this is just a small part of the pipeline.

Here are the skills that will make you a true full stack machine learning engineer. ↓

1. git

Breaking things is an inevitable consequence of building. Once your projects become serious, smashing Ctrl + Z won't get you out of trouble anymore.

This is where version control comes into play, which is essential to learn. (Especially when working in teams.)

Learning git can seem difficult at first because of the extensive use of the command line.

To start, I recommend these interactive tutorials:

• Git Immersion (gitimmersion.com/index.html)
• Learn Git Branching (learngitbranching.js.org)

Read 22 tweets

Tivadar Danka

@TivadarDanka

8 Oct

The reason PhD school is difficult is not because of the research.

Besides that, there are several key choices whose importance is underestimated by the students. Most of them are unrelated to your hard skills.

Here are the most impactful ones. ↓

1. Picking your advisor.

Young researchers usually value fame and prestige over personal relations. However, your advisor and your fellow labmates will determine your everyday work environment.

Don't sacrifice this for some scientific pedigree.

A healthy relationship with your advisor is essential for your professional performance. Pick someone who is not only a good scientist but a good person as well. Avoid abusive personalities.

Interview students and lab alumni about your prospective advisor if you can.

Read 16 tweets

Tivadar Danka

@TivadarDanka

5 Oct

There is one big reason we love the logarithm function in machine learning.

Logarithms help us reduce complexity by turning multiplication into addition. You might not know it, but they are behind a lot of things in machine learning.

Here is the entire story.

🧵 👇🏽

First, let's start with the definition of the logarithm.

The base 𝑎 logarithm of 𝑏 is simply the solution of the equation 𝑎ˣ = 𝑏.

Despite its simplicity, it has many useful properties that we take advantage of all the time.

You can think of the logarithm as the inverse of exponentiation.

Because of this, it turns multiplication into addition. Exponentiation does the opposite: it turns addition into multiplication.

(The base is often assumed to be a fixed constant. Thus, it can be omitted.)

Read 10 tweets

Tivadar Danka

@TivadarDanka

4 Oct

As you know, I am working on teaching mathematics in a way that maximizes value for machine learning practitioners.

Do you have any work stories where mathematical knowledge was a genuine advantage?

I would appreciate it if you could share!

I'll start. ↓

As a bioimage analyst, one of my projects involved the pixel-perfect identification of very thin objects: plant seedlings. (Like below.)

This was a classical semantic segmentation problem.

At first, I trained a UNet model using cross-entropy loss, but it didn't quite work.

The problem was that on the segmentation output, objects were not defined at all. My model predicted almost every pixel as background.

With some basic mathematical thinking, I suspected that the problem is caused by the cross-entropy loss.

Read 8 tweets

Tivadar Danka

@TivadarDanka

30 Sep

🤔 Should you learn mathematics for machine learning?

Let's do a thought experiment! Imagine moving to a new country without speaking the language and knowing the way of life. However, you have a smartphone and a reliable internet connection.

How do you start exploring?

1/8

With Google Maps and a credit card, you can do many awesome things there: explore the city, eat in nice restaurants, have a good time.

You can do the groceries every day without speaking a word: just put the stuff in your basket and swipe your card at the cashier.

2/8

After a few months, you'll start to pick up some language as well—simple things, like saying greetings or introducing yourself. You are off to a good start!

There are built-in solutions for common tasks that just work. Food ordering services, public transportation, etc.

3/8

Read 8 tweets

Tivadar Danka

@TivadarDanka

29 Sep

I just released a new chapter for the early access of my book, the Mathematics of Machine Learning!

This week, we are diving deep into the geometry of matrices.

What does this have to do with machine learning? Read on to find out. ↓

tivadar.gumroad.com/l/mathematics-…

Matrices are the basic building blocks of learning algorithms.

Multiplying the data vectors with a matrix is equivalent to transforming the feature space. We think about this as a "black box", but there is a lot to discover.

For one, how they change the volume of objects.

This is described by the determinant of the matrix, which is given by

• how the transformation scales the volume,
• and how it changes the orientation of basis vectors.

The determinant is given by the formula below. I am a mathematician, and even I find this intimidating.

Read 5 tweets

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!