I love reading, and I’m a big fan of Stephen King. Also, I’m a physicist and a data scientist, and I’m currently taking a break after I got my Master’s Degree. During this pause, I’ve decided to read another Stephen King book, and I really loved it.
I would never, ever, EVER, let a computer write a Stephen King book for one simple reason.
We are not there with the technology yet.
If you look at some NLP experiment (e.g. AI writing jokes here) you can safely say that we are not as good as humans in writing.
Sometimes humans are able to do certain kind of stuff very easily, but they are not able to properly describe how they do it. For example, we are able to clearly distinguish two different voices when they speak, but it is hard to describe the exact features that we use to distinguish them. As the task is hard to describe, it is even harder to teach a computer how to do it. Fortunately, we have data, and we can use the examples to train our machines.
Let’s get started!
As the title say, I’ve used Python. …
One of the most challenging area of Machine Learning is the one that regards the language and it is known as Natural Language Processing (NLP). It is true that all the area of Machine Learning can be complex and challenging at some level, but NLP is particularly difficult as it requires to explore human communication and, somehow, human consciousness. Moreover, while it is relatively easy to encode an image in terms of data (i.e. a bidimensional matrix), or a physics experiment (that is basically a .csv …
Physicists define climate as a “complex system”. While there are a lot of interpretations about it, in this specific case we can consider “complex” to be “unsolvable in analytical ways”.
This may seems discouraging, but it actually paves the way to a wide range of numerical algorithms that aim to solve the climate challenges. With the computational developments of the last years, Machine Learning algorithms are certainly part of them.
The challenge I want to discuss is based on forecasting the average temperature using traditional machine learning algorithms: Auto Regressive Integrated Moving Average models (ARIMA).
While this post doesn’t want…
3.1 Metrics Discussion
4. Practical Example
5. Fast MRI starter pack
The magnetic resonance imaging is an imaging technique that is extremely convenient for several reasons. The power of this imaging technique is its flexibility and sensitivity to a broad range of tissue properties. In this sense MRI is an helpful imaging technique to understand much more about the human body, both about its form and its function. Moreover, this imaging technique is absolutely harmless.
So what’s wrong with MRI? Well, the first thing that is unpleasant is its cost.
The first thing I want to say is that, as a data scientist, I don’t like to talk about “non technical things”.
It gives me the idea that I’m one of the online guru that wants to teach you how to live your life, eat healthy food and meditate when you wake up (and you should wake up at 5 a.m.).
Well, I don’t want to be that guy, but in this special case, I think a non-technical talk is ideal for the topic I want to discuss.
Note: In order to make it even simpler to understand, some technical steps are skipped. You can check the full process here ❤
When we think about “Computer Vision” or we see that the iPhone is able to recognize our face, we freak out.
And there is actually a reason why we do that. In fact, computer vision is actually able to do really complex tasks that have changed (and will change) the way we live.
Nonetheless, in the 21st century, sometimes we are able to make complex things really easy, and there is no need to write tons of…
Note: This is not a political post, and the scientific analysis has been done without any bias.
In its last book, the 44th president of the United States Barack Obama shows the America that he was exploring when he became president. He talks about the difficult times he faced and its way to react to the challenging period he was living. I couldn’t help but notice that its communication strategy was way different from the one of the 2021 politicians.
Of course, social media are game changing in terms of the politicians’ communication. Plus, in the era of “Big Data”…
A very common task in Computer Vision is based on identifying colors.
More generally, a fascinating aspect of learning is that sometimes we know things but we can’t explain them. For example, if I ask you to describe me the “red color” your only option is to show me a red object, like the red orange that is reported above… but you can’t really explain what “red” is.
For this reason a certain effort is necessary to transmit the definition of a color to a computer.
Let’s do it!
The first step is to get an image. …
Note: The notebook is available here. Enjoy ❤
When I was little, in my dreams, I was Gareth Bale. I dreamed to have its speed and its power and to be unstoppable like he appeared to be.
All the Inter Milan fans loved Mourinho so much when they helped them achieve what wasn’t possible to achieve until that very moment. Now, Jose Mourinho, one of the best (maybe the best) coach of all times, is the Tottenham Hotspur manager.
If you talk to a 10 years old football-loving-kid from England he will probably tell you that he wants to become…