Here are the best 10 machine learning threads I posted in February.
They go all the way from beginner-friendly content to a broader dive into specific machine learning concepts and techniques.
I'd love to hear which one is your favorite!
🧵👇
They go all the way from beginner-friendly content to a broader dive into specific machine learning concepts and techniques.
I'd love to hear which one is your favorite!
🧵👇
Having to pick only 10 threads is painful. I always struggle to decide what should stay out of the list.
This, however, is a great incentive when I'm writing the content: I have to compete against myself to make sure what I write ends up being part of the list!
[2 / 13]
This, however, is a great incentive when I'm writing the content: I have to compete against myself to make sure what I write ends up being part of the list!
[2 / 13]
[Thread 1]
An explanation about three of the most important metrics we use: accuracy, precision, and recall.
More specifically, this thread shows what happens when we focus on the wrong metric using an imbalanced classification problem.
[3 / 13]
An explanation about three of the most important metrics we use: accuracy, precision, and recall.
More specifically, this thread shows what happens when we focus on the wrong metric using an imbalanced classification problem.
[3 / 13]
https://twitter.com/svpino/status/1357302018428256258?s=20
[Thread 2]
My attempt to introduce how Convolutional Neural Networks work. Well, in reality, this is specifically about convolutions.
I love the idea of finding ways to relate convolutions to software development to make it more intuitive.
[4 / 13]
My attempt to introduce how Convolutional Neural Networks work. Well, in reality, this is specifically about convolutions.
I love the idea of finding ways to relate convolutions to software development to make it more intuitive.
[4 / 13]
https://twitter.com/svpino/status/1359107240519749637?s=20
[Thread 3]
After going through convolutions, this thread explains how neural networks generalize.
There are many pictures of bunnies involved, but I really liked the storyline to explain things as simply as possible.
[5 / 13]
After going through convolutions, this thread explains how neural networks generalize.
There are many pictures of bunnies involved, but I really liked the storyline to explain things as simply as possible.
[5 / 13]
https://twitter.com/svpino/status/1360462217829900290?s=20
[Thread 4]
Active Learning is an iterative approach to supervised learning that helps when we have a lot of data, but very few labels.
This thread is an overview of this technique and how it works.
[6 / 13]
Active Learning is an iterative approach to supervised learning that helps when we have a lot of data, but very few labels.
This thread is an overview of this technique and how it works.
[6 / 13]
https://twitter.com/svpino/status/1365307434856820736?s=20
[Thread 5]
If you've heard about one/few-shot learning before but aren't sure exactly what it is, this is a good introduction to it.
Specifically, this thread talks about Siamese Networks and how they work.
[7 / 13]
If you've heard about one/few-shot learning before but aren't sure exactly what it is, this is a good introduction to it.
Specifically, this thread talks about Siamese Networks and how they work.
[7 / 13]
https://twitter.com/svpino/status/1365683368030052355?s=20
[Thread 6]
Explaining a solution line by line is always fun.
This thread goes to an excruciating amount of detail through a Convolutional Neural Network that solves the MNIST problem.
An explanation for every single line of code.
[8 / 13]
Explaining a solution line by line is always fun.
This thread goes to an excruciating amount of detail through a Convolutional Neural Network that solves the MNIST problem.
An explanation for every single line of code.
[8 / 13]
https://twitter.com/svpino/status/1364539168567746563?s=20
[Thread 7]
When using Gradient Descent, the batch size is one of the most consequential hyperparameters at our disposal.
This thread explains everything you need to know about the batch size.
[9 / 13]
When using Gradient Descent, the batch size is one of the most consequential hyperparameters at our disposal.
This thread explains everything you need to know about the batch size.
[9 / 13]
https://twitter.com/svpino/status/1358286876822679552?s=20
[Thread 8]
Encoding features from a dataset is a very common transformation that data scientists have to do before running machine learning algorithms.
This thread covers Label and One-Hot encoding, how they work and how to use them.
[10 / 13]
Encoding features from a dataset is a very common transformation that data scientists have to do before running machine learning algorithms.
This thread covers Label and One-Hot encoding, how they work and how to use them.
[10 / 13]
https://twitter.com/svpino/status/1364923419922493444?s=20
[Thread 9]
Bayes' theorem is very useful, but I didn't want to make it boring so that this thread will introduce it through an excellent little (surprising) problem.
And after you read it, you'll want to use it at your next dinner party.
[11 / 13]
Bayes' theorem is very useful, but I didn't want to make it boring so that this thread will introduce it through an excellent little (surprising) problem.
And after you read it, you'll want to use it at your next dinner party.
[11 / 13]
https://twitter.com/svpino/status/1362354925548810241?s=20
[Thread 10]
I'm sure you've heard that we split our datasets into different subsets right before running our machine learning algorithms.
This thread is an explanation of why we do that. What's the goal of each subset, and how to use them.
[12 / 13]
I'm sure you've heard that we split our datasets into different subsets right before running our machine learning algorithms.
This thread is an explanation of why we do that. What's the goal of each subset, and how to use them.
[12 / 13]
https://twitter.com/svpino/status/1359827674097672195?s=20
March is about to start, and my challenge is to end up the month with 10 threads that completely kick the ass of February's Top 10.
Stay tuned because this is just getting started!
Which of these threads was your favorite one?
🦕
[13 / 13]
Stay tuned because this is just getting started!
Which of these threads was your favorite one?
🦕
[13 / 13]
• • •
Missing some Tweet in this thread? You can try to
force a refresh
