Last Thursday, I participated in the Data 4 Good Challenge of Emergent in Leuven, along with three teammates. Hasse and Ennio are Computer Science students as well, while Sven is pursuing a Masters in Information Systems Engineering. The Data 4 Good Challenge is a data-based hackathon, surrounded by talks and…

In this series, I will cover the main findings of my thesis that I’m doing at the Computer Science department of KU Leuven. …

RxJS is the best known library for reactive programming in JavaScript. Reactive programming is mainly concerned about handling asynchronous data streams. If you have never worked with reactive programming before, it is going to be though, since you have to think in a completely different way as you are used…

Metaheuristics can find near-optimal solutions for NP-complete problems — Last year, I took the ‘Genetic Algorithms and Evolutionary Computing’ course at KU Leuven. The evaluation of the course is based entirely on a programming project in Python, where the task is to find near-optimal solutions for the travelling salesman problem. Conceptually, several matrices are given that represent the distances…

Redux is a state management pattern, mainly used for complex web applications built with React, Angular, or Vue. Instead of having the state of an app being spread over multiple components, with Redux, the state is centralized. This way, your application’s state will be much more debuggable. The centralized object…

Comparing neuro-symbolic AI against a purely neural network-based approach on visual question-answering — This article focuses on Visual Question Answering, where a neuro-symbolic AI approach with a knowledge base is compared with a purely neural network-based approach. From the experiments, it follows that DeepProbLog, the framework used for the neuro-symbolic AI approach, is able to achieve the same accuracy as the pure neural…

Next.js is a web development framework used for React applications. Its main advantages are the built-in support for server-side rendering and automatic code splitting, without any configuration. Traditional pure React: disadvantages A typical React application is rendered on the client side. There are two main disadvantages to this approach: Browsers have to render a…

Neural networks converge much faster if the input data is normalized. Learn how you can calculate the mean and standard deviation of your own dataset. — Why normalization allows faster convergence The normalization of a dataset is mostly seen as a rather mundane task, although it strongly influences the performance of a neural network. With unnormalized data, numerical ranges of features may vary strongly. Take for example a machine learning application where housing prices are predicted from several inputs (surface area…