Recent Posts
The holidays have just passed. And yes, I know it is February, but the writing of this article started on January 5, so nothing, the holidays have just passed. All of us have had lunches, dinners, and little dinners, and I am sure you have been harassed by the usual …
In the previous article, I talked about two nice things: modular arithmetic and Galois fields. I introduced them in anticipation of this day. Yes, because today I will talk about a cryptographic algorithm. An algorithm that is not only really cool, but also has an emotional value, since I first …
Who knows me knows that one of the topics I am most passionate about is cryptography. For this reason it was not a matter of if but of when, I would have written an article about it. Since forever however you cannot start abruptly, and this article serves exactly this …
This article of mine is different from all those I’ve written so far. You won’t find formulas, algorithms, or other mind-blowing wizardry. Instead, I want to talk about a topic I care about: metaheuristics. That art of searching in a non-intuitive way for good enough solutions, when the …
Here we are. We've reached the fifth and final part of the NODE series. Though take that statement with a grain of salt, if I run out of space, you might get a sixth one too. In any case, in this (hopefully) final part, we'll look at some code and …
Yes, I know, post-holiday slumps hit everyone hard. But hey, someone has to do the dirty work, right? So let's pick up, after a few weeks' break, our delightful little chat about Neural ODEs, or NODEs. If you missed the earlier parts, don't worry, they're linked at the end of …
There comes a time in the life of every mathematician, engineer, and mythological figure alike when
You like analytics, huh!? Then take this ODE.
And it smacks you with a nonlinear, coupled, implicit one, with coefficients changing like the Hogwarts staircases. The only thing you can do is not solve …
Here we are again with the second part of the series dedicated to Neural ODEs. If the first article was a mental beating this one will be a bit less so. But don’t get your hopes up: it’s still no walk in the park. We’ve already sunk …
Once upon a time, there was a neural network that didn’t want to work layer by layer like all her friends. No, she wanted to be continuous, fluid, dynamic. She wanted to be a differential equation. This is not the usual nightmare for mathematicians. There's no Freddy Krueger waking …
Do you ever wake up in the morning thinking:
Damn, today I really feel like backpropagating some error... but I should probably watch my weight!
No? Weird, but hey, good for you. Either way, even if nobody asked, I’ve got the perfect solution: the right compromise between indulgence and …