Tweet

Santiago 🎃

Follow @svpino

20 Oct, 9 tweets, 2 min read

I'm a full-on AI proponent.

But I really don't like the idea of facial recognition software.

This is why.

🧵👇

▫️It violates our right to privacy

Do you really want thousands of photos with your face stored in hundreds of databases all over the place?

Photos that will be automatically tagged with your personal information.

And you won't have any control over this.

👇

▫️Lack of regulations makes this scary.

Who will be able to use this? Do we have to give consent? Can we trust this? How is this information going to be used? With what purposes?

Are we gonna get tracked every time, everywhere?

👇

▫️It interferes with our liberty and rights.

Check this UN resolution about unnecessary surveillance: article19.org/resources/un-r…

👇

▫️It discourages participation in protests or public events.

2020 showed us how bad this is during the #BlackLivesMatter protests in the U.S.

👇

▫️It exposes us to biases with awful implications.

We have all seen how these facial algorithms work and how they horribly fail (a quick Google search will give you plenty of terrifying examples.)

👇

▫️It could be used to selectively target specific groups.

Facial recognition will join a list of tools that today are disproportionally used to target vulnerable communities and do racial profiling.

👇

▫️It will never be perfect.

I know how this works. I know it can get really good, but never perfect.

What will happen when "you are seen" over there doing something, but you were really over here doing nothing?

👇

A long time ago, we decided that science can't be unbounded, and there should be limits to what we can and should do.

Unrestricted, massively-used facial recognition should join the list of "too much."

• • •

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

21 Oct

I always get Normalization and Standardization mixed up.

But they are different.

Notes about them and why do we care.

🧵👇

Feature scaling is key for a lot of Machine Learning algorithms to work well.

We always want all of our data on the same scale.

👇

Imagine we are working with a dataset of workers.

"Age" will range between 16 and 90.
"Salary" will range between 15,000 and 150,000.

Huge disparity!

Salary will dominate any comparisons because of its magnitude.

We can fix that by scaling both features.
👇

Read 7 tweets

Santiago 🎃

@svpino

19 Oct

Overfitting sucks.

Here are 7 ways you can deal with overfitting in Deep Learning neural networks.

🧵👇

A quick reminder:

When your model makes good predictions on the same data that was used to train it but shows poor results with data that hasn't seen before, we say that the model is overfitting.

The model in the picture is overfitting.

👇

1⃣ Train your model on more data

The more data you feed the model, the more likely it will start generalizing (instead of memorizing the training set.)

Look at the relationship between dataset size and error.

(Unfortunately, sometimes there's no more data.)

👇

Read 10 tweets

Santiago 🎃

@svpino

18 Oct

Bias vs. variance in 13 charts.

🧵👇

Here is a sample 2-dimensional dataset.

(We are just representing here the training data.)

👇

The red line represents a model.

Let's call it "Model A."

A very simple model. Just a straight line.

👇

Read 15 tweets

Santiago 🎃

@svpino

17 Oct

Wanna maximize the potential reward of every hour you spend?

Here is a tangible way to do this when building real-life Machine Learning solutions.

🧵👇

Complex systems usually depend on multiple components working together to produce a solution.

Imagine a pipeline like this, where the input goes through 4 different components before getting to the appropriate output.

👇

After everything is said and done, let's imagine this system is correct 60% of the time.

That sucks. We need to improve it.

Unfortunately, we tend to prioritize work in those areas where we *think* there's value. Even worse, areas that are easy or fun to change.

👇

Read 9 tweets

Santiago 🎃

@svpino

14 Oct

Machine Learning 101:

▫️ Overfitting sucks ▫️

Here is what you need to know.

🧵👇

Overfitting is probably the most common problem when training a Machine Learning model (followed very close by underfitting.)

Overfitting means that your model didn't learn much, and instead, it's just memorizing stuff.

👇

Overfitting may be misleading: during training, it looks like your model learned awesomely well.

Look at the attached picture. It shows how the accuracy of a sample model increases as it's being trained.

The accuracy reaches close to 100%! That's awesome!

Or, is it?

👇

Read 9 tweets

Santiago 🎃

@svpino

13 Oct

Transfer Learning.

It sounds fancy because it is.

This is a thread about one of the most powerful tools that make possible that knuckleheads like me achieve state-of-the-art Deep Learning results on our laptops.

🧵👇

Deep Learning is all about "Deep" Neural Networks.

"Deep" means a lot of complexity. You can translate this to "We Need Very Complex Neural Networks." See the attached example.

The more complex a network is, the slower it is to train, and the more data we need to train it.

👇

To get state-of-the-art results when classifying images, we can use a network like ResNet50, for example.

It takes around 14 days to train this network with the "imagenet" dataset (1,300,000+ images.)

14 days!

That's assuming that you have a decent (very expensive) GPU.

👇

Read 10 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!