Santiago Profile picture
18 Jan, 6 tweets, 2 min read
Here are the classes I took and the money I paid to get my Master's from Georgia Tech with a specialization in machine learning:

๐Ÿงต๐Ÿ‘‡
The classes:

1. Machine Learning
2. Computer Vision
3. Reinforcement Learning
4. Intro to Graduate Algorithms
5. Machine Learning for Trading
6. Database Systems Concepts and Design
7. Software Development Process
8. Software Architecture and Design

๐Ÿ‘‡
9. Human-Computer Interaction
10. Advanced Operating Systems
11. Software Analysis and Testing

You only need 30 credits to graduate. I completed 33.

It took me 4 years to go through all the classes (2015-2019). I was 35 when I started.

๐Ÿ‘‡
I paid $510 for 3 credits, and I completed 33 of them, so I ended up paying $5,610 for the classes.

I also paid $310 in term fees. It took me 11 terms to finish (I never took two classes simultaneously), so I paid $3,410.

$5,610 + $3,410 = $9,020 was my total cost.

๐Ÿ‘‡
If you take more than one class per semester, you will pay less money (it can cost as low as ~$7k.)

I was working full-time the whole time, and I didn't want to rush it.

I'm glad I took my time: I finished with a 4.0 GPA (the maximum possible score.)

๐Ÿ‘‡
I loved the program. It taught me a lot. It was the reason I started focusing on machine learning professionally.

If you are interested, check out @GTOMSCS.

If you feel unprepared, stay tuned, and let's start building up your confidence and knowledge step by step.

โ€ข โ€ข โ€ข

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

Keep Current with Santiago

Santiago 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 @svpino

19 Jan
What are the differences between a multi-class classification problem and a multi-label classification problem?

(This is the answer to the second question from the attached thread.)



๐Ÿงต๐Ÿ‘‡
Let's assume we are classifying images into 3 different classes.

We will process each image and assign them to the class corresponding to the animal they show.

For example, we will classify the attached images as CAT, DOG, and CHICK.

๐Ÿ‘‡ ImageImageImage
Because we are classifying images into three or more classes, this is a multi-class classification problem.

The main characteristic of these problems is that the classes are mutually exclusive: we either classify an image as a CAT, DOG, or CHICK.

๐Ÿ‘‡
Read 8 tweets
18 Jan
100,000 followers!
Here is a rant about followers, some "you-can-do-it" encouragement, and a little bit about my account's story.

๐Ÿ‘‡
Of course, this tweet was a way for me to hack the number of people who go and look at my profile.

You know, one of those silly experiments I've been doing.

But here is the thing: although 100,000 is still out there, it will happen at some point this year!

๐Ÿ‘‡
Read 12 tweets
18 Jan
Why is it important to introduce non-linearities in a neural network?

The short answer: So we can solve more interesting problems.

The left image shows a classification problem that can be solved using a single dividing line. The image on the right is much more complex.

๐Ÿงต๐Ÿ‘‡
Here is a neural network with 2 hidden layers of 4 neurons. The activation is set to "Linear."

In just a few epochs, the network finds the correct solution.

Notice how the network uses a single dividing line in the output. That's all it can do with linear activations.

๐Ÿ‘‡
If we try the same network on the more complex problem, it will struggle to classify the data correctly.

We haven't introduced non-linearities in this network, so it won't find the proper solution for this type of problem.

๐Ÿ‘‡
Read 7 tweets
17 Jan
20 machine learning questions that will make you think.

(Cool questions. Not the regular, introductory stuff that you find everywhere.)

๐Ÿงต๐Ÿ‘‡
1. Why is it important to introduce non-linearities in a neural network?

2. What are the differences between a multi-class classification problem and a multi-label classification problem?

3. Why does the use of Dropout work as a regularizer?

๐Ÿ‘‡
4. Why you shouldn't use a softmax output activation function in a multi-label classification problem when using a one-hot-encoded target?

5. Does the use of Dropout in your model slow down or speed up the training process? Why?

๐Ÿ‘‡
Read 12 tweets
16 Jan
Ready to take your machine learning models into production?

@awscloud offers SageMaker, a fully managed machine learning service that acts as a one-stop-shop for everything you need.

The list of services is impressive:

๐Ÿงต๐Ÿ‘‡
1. Studio
2. Projects
3. Studio Notebooks
4. Experiments
5. Debugger
6. Model Registry
7. Model Building Pipelines
8. Model Monitor
9. Lineage Tracking
10. Feature Store
11. Data Wrangler
12. Preprocessing
13. Batch Transform
14. Ground Truth
15. Augmented AI
16. Edge Manager

๐Ÿ‘‡
17. Autopilot
18. Neo
19. Elastic Inference
20. Reinforcement Learning
21. JumpStart
22. Clarify

I've been working for years with SageMaker, and the services are incredibly comprehensive. Whatever I need to do, I can find.

(Plus, you can combine them with the rest of AWS!)

๐Ÿ‘‡
Read 4 tweets
14 Jan
10 machine learning YouTube videos.

On libraries, algorithms, and tools.

(If you want to start with machine learning, having a comprehensive set of hands-on tutorials you can always refer to is fundamental.)

๐Ÿงต๐Ÿ‘‡
1โƒฃ Notebooks are a fantastic way to code, experiment, and communicate your results.

Take a look at @CoreyMSchafer's fantastic 30-minute tutorial on Jupyter Notebooks.

2โƒฃ The Pandas library is the gold-standard to manipulate structured data.

Check out @joejamesusa's "Pandas Tutorial. Intro to DataFrames."

Read 12 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!