Computers can't sustain themselves

The situation where an unskilled user can enjoy a well-working computer does only last so long.1 Either the user becomes good at maintaining the computer, or it will stop working correctly. That’s because computers are not reliable. If not used carefully, at some point, they will behave unexpectedly or stop working. Therefore, one will have to get their hands dirty and most likely learn something along the way. Some operating systems are more prone to gathering cruft, though.
Read More

On Biometric Authentication

Biometric systems such as fingerprint readers or facial recognition may be appealing, but they have drawbacks worth mentioning. Their attack surfaces are larger than commonly believed, they make it hard to enforce good security rules and are not guaranteed to work all the time. These flaws should be considered when assessing the value of biometric authentication.

Read More

How to install the original Doom on Fedora 31

If you want to distance yourself from the craziness of the world around and happen to be a computer geek, only a few things are more satisfying than blasting hordes of demons on Doom. Here is how to install GZDoom - an OpenGL port of Doom released under the GPLv3 license - and a mod called Brutal Doom on Fedora 31.

Read More

AI transparency: how the Local Interpretable Model-agnostic Explanation Framework works?

As Artificial Intelligence is solving increasingly hard problems, it’s becoming more and more complex. This complexity leads to an often overlooked issue: the lack of transparency. This is problematic, because by taking answers at face value from an uninterpretable model (a black box), we’re trading accuracy for transparency. This is bad for a couple of reasons:

Read More

A PyTorch RNN with variable sequence lengths

A Recurrent Neural Network (RNN) often uses ordered sequences as inputs. Real-world sequences have different lengths, especially in Natural Language Processing (NLP) because all words don’t have the same number of characters and all sentences don’t have the same number of words. In PyTorch, the inputs of a neural network are often managed by a DataLoader. A DataLoader groups the input in batches. This is better for training a neural network because it’s faster and more efficient than sending the inputs one by one to the neural network.
Read More

Algorithms fairness

Software being more and more used to get metrics and insights for critical areas of our societies such as our healthcare system, crime recidivism risk assessment, job application review or loan approval, the question of algorithms fairness is becoming more important than ever. As algorithms learn from human-generated data, they often magnify human bias in decision making, making them prone to judging something in an unfair way. For example, the Amazon CV review program was found to be unfair to women.
Read More