Santiago Profile picture
24 Mar, 4 tweets, 1 min read
🐍 Python 3 features that you might not be using yet:

▫️ Type hints
▫️ Data classes
▫️ Pathlib
▫️ Enumerations
▫️ F-strings
▫️ Iterable unpacking
▫️ Walrus operator
▫️ Async IO
▫️ Assignment expressions
▫️ Positional-only parameters

Pick one and see how it can help you.
I like to spend some time every week looking into something new from Python 🐍.

2 out of 3 times, I can't use it right away. I don't find a good way to make it work for me.

I usually talk about what I learned here on Twitter and then put it in the backburner.
Sometimes, I find a good place right away for what I just learned, and there's no better feeling than that!

I think people need more Python 🐍 in their lives:

- Simple
- Popular
- Powerful
- Versatile

Follow me and I'll make sure we learn this thing together until it hurts.
I added "Assignment expressions" to the list but left "Walrus operator" by mistake.

They are both the same.

• • •

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

25 Mar
A summary of the setup I use for work and how I use each one of these:

▫️ Google Colab PRO
▫️ @awscloud's SageMaker
▫️ Mac Pro running @code

Here are the details: 🧵👇
I always start new things with Google Colab.

Opening Colab is fast, and I can go from an idea to a running script in no time.

I can share the notebook and open it anywhere without worrying about version control systems.

2/9
Any new experiments go into Colab. Whenever I need to test something, I do it in Colab.

Paying for the PRO version is a no-brainer for me:

▫️ Faster GPUs
▫️ More RAM
▫️ More Disk
▫️ Longer runtime

3/9
Read 9 tweets
25 Mar
If you are starting out with machine learning, these algorithms will give you the best bang for your money:

▫️ Decision Trees
▫️ Linear Regression
▫️ Logistic Regression
▫️ Random Forest
▫️ AdaBoost
▫️ Naive Bayes
▫️ KNN
▫️ Neural Networks
▫️ K-means
▫️ PCA
If you are looking to make things a little bit more practical, XGBoost will solve a lot of your problems.

I didn’t include it in the previous list because it’s a combination of Decision Trees with Bagging and Boosting, but it’s definitely one of algorithms that I use the most.
Information overload is a real problem. If you do a Google search, there are literally thousands of machine learning algorithms.

This list will keep you focused on the list that will give you the most benefits when you are starting.

Read 6 tweets
22 Mar
Do you wanna know why do we use ReLU when doing deep learning?

When starting out with neural networks, it's common to work with examples using the sigmoid activation function.

The sigmoid function squeezes any input value to a value between 0 and 1.

This is a 🧵👇
There's a problem with the sigmoid function: it saturates quickly.

This means that smaller and larger values will get concentrated around 0 and 1, respectively.

The function is only sensitive to values around the midpoint.

(2 of 5)
Once saturated, the weights will stop changing, and the network will not learn anything useful.

If your network is not too deep, this will not be an issue. But if you have a buttload of layers, you'll likely run into the problem.

This sucks.

(3 of 5)
Read 6 tweets
19 Mar
Thoughts about starting with machine learning.

☕️🧵👇
Three unnegotiable prerequisites:

1. Software development
2. Algorithms and data structures
3. Communication

If you build a strong foundation on these, you'll be unstoppable.
Learn to build software.

It's hard to make progress with machine learning if you struggle with programming.
Read 23 tweets
18 Mar
I can't shut up about neural networks.

What questions do you have?
They aren't necessarily opposite concepts.

Fully connected refer to networks composed of layers where every node is connected to every node of the next layer.

Deep networks refer to networks with many layers. They could be fully connected or not.

Especially with deep learning, where you have many layers full of nodes, it's hard to understand the "thinking" of a network because you'll have to reverse-engineer million of float values and try to make sense of them.

Hard to do.

Read 13 tweets
18 Mar
The ability to reuse the knowledge of one model and adapt it to solve a different problem is one of the most consequential breakthroughs in machine learning.

Grab your ☕️ and let's talk about this.

🧵👇
A deep learning model is like a Lego set, with many pieces connected, forming a long structure.

These pieces are layers, and each layer has a responsibility.
Although we don't know exactly the role of every layer, we know that the closer they get to the output, the more specific they get.

The best way to understand what I mean is through an example: a model that will process car images.
Read 13 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!