Tweet

Santiago

30 May, 8 tweets, 4 min read

Top 5 machine learning stories.

I just reached a couple of milestones:

• 3,000 newsletter subscribers
• 1,000 Medium followers

Just like my Twitter account, all of this is purely centered around machine learning.

Here are the best 5 stories I've published: ↓

Are you ready for machine learning math?

My recommendations to learn the Math you need for machine learning.

You'll learn an approach that will help you succeed without getting overwhelmed.

svpino.medium.com/are-you-ready-…

How do I learn new things?

My—somewhat unconventional—approach for getting new knowledge and staying up to date with everything happening in my field.

You'll learn a list of practical tips to improve your process.

svpino.medium.com/how-do-i-learn…

A model that smokes everyone else

An introduction to one of the most mind-blowing computer vision models and some examples of how you can use it.

The ROI I'm getting from using this model is absolutely insane!

medium.com/mlearning-ai/c…

A long time ago, I fell in love with autoencoders.

I've found autoencoders extremely fascinating and useful in my regular life.

This is an introduction of how they work, and some examples of how you can use them.

svpino.medium.com/autoencoders-a…

Why is your model getting worse?

A fascinating view into what happens with machine learning models as soon as you publish them.

This story will help you understand what happens, why it happens, and how you can fix the problems.

svpino.medium.com/why-is-your-mo…

Every Friday, I post one of these stories at digest.underfitted.io and svpino.medium.com. Consider subscribing/following me there.

The stories are free, and I try really hard not to be boring and teach you something new about machine learning.

@svpino

If you want the core ideas distilled and packed in a format that you can quickly consume, follow me at @svpino, and every week I'll deliver 2 or 3 gems right to your feed.

• • •

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 @svpino

Santiago

@svpino

31 May

A Master's degree in Computer Science can change your life.

I went to Georgia Tech's Master's program. I graduated with a Machine Learning specialization. This is one of the best decisions I've made in my life.

Here is every class I took and how much money I paid.

↓

The list of classes (3 credits each):

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

9. Human-Computer Interaction
10. Advanced Operating Systems
11. Software Analysis and Testing

33 total credits (you only need 30 to graduate.) It took me 4 years to go through all the classes (2015-2019). I was 35 when I started.

I paid $9,020 for the whole thing. That's it!

Read 5 tweets

Santiago

@svpino

26 May

Wanna change your life?

Start learning machine learning.

1,500+ people have gone through this course, and they loved it!

Next 50 people: $5 only. Gratis for those who can't afford it.

→ gum.co/kBjbC/505

If you can't pay, let me know, and I'll give you a free copy.

Update:

• 22 copies sold.
• 28 copies left.

Only 10 spots left.

Read 12 tweets

Santiago

@svpino

26 May

Why is your machine learning model getting worse?

You finished building your model, and you already deployed it.

You ain't done yet, unfortunately. You are arguably only half the way through.

The performance of machine learning models degrades over time.

Let's talk about this.

A quick introduction to a machine learning model:

X → y

• X: Input data
• y: Output prediction
• →: The relationship that the model learned between X and y.

Read 11 tweets

Santiago

@svpino

24 May

Today, Python 🐍is the best language you can learn if you want to get into machine learning.

It has many things going for it, but here are 2 very important:

• It's very flexible.
• It's very popular.

This, however, can change.

I get a lot of questions about Python versus R.

R is great, but it doesn't have the flexibility that Python does.

Learn Python, and you can use it for more than machine learning: you can build your backend, MLOps, DevOps, tooling, etc.

One language. Multiple uses.

If you look at the literature today, it's Python all the way down.

If you look at libraries and frameworks, they are Python-first with a few spinoffs on different languages.

It's hard to go against the current.

Read 6 tweets

Santiago

@svpino

23 May

The best advice I've ever gotten:

"Nobody remembers who came in second place."

I played a lot of sports. I was taught that winning is the only thing that matters. Participation trophies weren't a thing back then.

That's how I'm wired.

↓

Many people prefer to approach their careers with a different, less competitive mentality.

I respect that. I just prefer a different approach.

Complacency is something that terrifies me, and I've found that healthy competition keeps me away from it.

↓

"Never compare yourself to others." ← This may be good advice, but it doesn't work for me.

I've tried to use yesterday's version of myself to try and improve every day. But this is not enough, too little, and not fun.

↓

Read 4 tweets

Santiago

@svpino

22 May

I'll blow your mind with a technique you aren't using yet.

Sometimes, you want your system to do exactly the opposite of what your machine learning model thinks you should do.

Let me convince you. ↓

I'm going to start with a nice problem:

Imagine a model that looks at a picture of an electrical transformer and predicts whether it's about to break or not.

Don't worry about how the model does this. We are going to focus on the results instead.

There are 4 possible results for this model:

1. It predicts a bad unit as bad.
2. It predicts a bad unit as good.
3. It predicts a good unit as bad.
4. It predicts a good unit as good.

#2 and #3 are the mistakes the model makes.

Read 21 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!