Santiago Profile picture
8 Mar, 6 tweets, 2 min read
This week, I'll be on Twitter Spaces with amazing company!

We'll be talking about some cool machine learning techniques. Each one of us, a different one.

Save the date, and you can join us from your mobile phone right from the Twitter application.
We are planning to record this session, but... But, we will be recording the screen of an iPhone and some other weird stuff to try and get the audio out.

Not the best process, but we will try to get clean audio out of this.
If everything works, @haltakov will make the audio available (likely in the form of a podcast.) Where and how are details that we'll share when we know.

If the audio comes out too crappy, we will probably not bother because it won't be useful for you anyway.
That being said, if you can attend live, don't miss it.

The magic of being there won't be replaced by a podcast player. Plus you will be able to raise your hand and talk!
For my friends in India and any other region where this time is impossible, I see and hear you 👀.

The next session will be at a time where you can attend. I promise.
Android users: you should be able to join a Space from your phone. At least that's what I've heard. Right @AlejandroPiad?

• • •

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

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

9 Mar
Here is an underrated machine learning technique that will give you important information about your data and model.

Let's talk about learning curves.

Grab your ☕️ and let's do this thing!

🧵👇
Start by creating a model. Something simple. You are still exploring what works and what doesn't, so don't get fancy yet.
We are now going to plot the loss (model error) vs. the training dataset size. This will help us answer the following questions:

▫️ Do we need more data?
▫️ Do we have a bias problem?
▫️ Do we have a variance problem?
▫️ What's the ideal picture?
Read 16 tweets
7 Mar
Are you already using the walrus operator in Python 🐍? Image
Yup, I'm dumb and didn't realize this when I wrote it.

The good news is that the example still stands, but you are completely right: both lines inside the first loop should be swapped.

New things are always controversial.

People don't like to use things that change the syntax of their code because "it becomes less readable." I know people that complain vehemently about slicing in Python.

I'd rather try to use the language as it is.

Read 4 tweets
6 Mar
I'm writing one story about machine learning every week.

My goal is to teach you something new. Something that makes you feel smarter. Something that helps you in your career.

The first issue is coming out this Friday, and I'd love to count on you!

👇 Image
You can subscribe here: digest.underfitted.io.

100% free.

And it will be a two-way street: reply to one of the emails, and I'll do my best to answer and package some of them in future issues.

The content that I've always wanted to read but never found.
Give it a try and, after reading a couple of issues, decide whether you feel better by reading them or not.

The good news is that it costs nothing to read them.

If I were you, I'd like it... but I'm also biased 😉

Read 4 tweets
6 Mar
16 questions that I really like to ask during interviews for machine learning candidates.

These will help you practice, but more importantly, they will help you think and find ways to improve!

Let's do this! ☕️👇
1. How do you handle an imbalanced dataset and avoid the majority class completely overtaking the other?

2. How do you deal with out-of-distribution samples in a classification problem?

3. How would you design a system that minimizes Type II errors?
4. Sometimes, the validation loss of your model is consistently lower than your training loss. Why could this be happening, and how can you fix it?

5. Explain what you would expect to see if we use a learning rate that's too large to train a neural network.
Read 13 tweets
4 Mar
Today, a tiny percentage of companies are currently using AI/ML at scale.

Do you imagine the possibilities as this continues to grow?

Who wants to be in the center of it all?
And paying a buttload of money for people that are the right fit.

Read 6 tweets
4 Mar
It depends on what a "large model" means to you.

If we are talking about "ridiculously large," like in ImageNet-type-large, then you probably won't be able to do it for free.

But then, why would you want to train such a massive model?
If we get it down a couple of notches, we get into the realm of "a few days of training" as long as you have a GPU.

You could train this locally, assuming you have a computer with the right hardware. But that computer won't be cheap either.
If we are talking about hours of training, then Google Colab might be all you need, and you can access it for free.

It won't be the best experience, but again, hard to beat free.
Read 4 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!