Article

AI City Intelligence

Imagine being able to make better decisions about where to live, where to establish a new business, or how to understand the changing dynamics of urban neighborhoods. Access to detailed, up-to-date information about city environments allows us to answer these questions with greater confidence, but the challenge lies in accessing and analyzing the right data. […]

Read More
Article
Turning classes into inputs

Let’s face it, we all have worked on an ML project where we had to predict a ridiculously high number of classes. Large enough to make the number of observations per class into an embarrassingly small subset. Most people model these tasks as a multiclass classification problem where, for each input observation, we must predict […]

Read More
Article
NILG.AI in the AI community

Connecting and being connected greatly impact how we positively interact with others. At NILG.AI, we are not only focused on helping businesses unlock their capabilities, but we also make our mission sharing with the world how to leverage the power of Artificial Intelligence (AI). This knowledge-centered culture is one of our greatest pride and a […]

Read More
Article
A new era has arrived for NILG.AI

Happy birthday! Today is NILG.AI’s fourth anniversary. Happy birthday to us! For most humans, birthdays are a synonym for getting older and leaving the good days of the youth behind. For companies, they are a moment to reflect on everything we achieved, recognize how far we have come, and envision how far we will go. […]

Read More
Article
Privacy Preserving Machine Learning

This article reports my work at NILG.AI during a curricular internship on privacy-preserving Machine Learning. Trip data is any type of data that connects the origin and destination of a person’s travel and is generated in countless ways as we move about our day and interact with systems connected to the internet. But why is […]

Read More
Article
Local vs. global optimization

Is the fastest route always the best? This article may give you a different perspective if your answer is yes. Normally there are multiple ways to tackle a given problem or task, and the optimization field is no different, as there are different approaches we can take to find an optimal solution. The choice of […]

Read More
Article
Achieving diverse product recommendations

In this blog post, you’ll learn about some examples of decision processes you can use in recommender systems: do you see any usage for recommending less popular products as a way to improve your business? You will see it now! The Use Case Let’s imagine a use case where you are building a MOOC platform […]

Read More
Article
New internships in AI: Privacy-preserving ML and Similarity Learning

We are proud to share that NILG.AI has partnered with the Faculty of Engineering of the University of Porto (FEUP) through internships in AI as part of curricular units! We have received two new interns, Margarida Vieira and Beatriz Lopes; both enrolled in the Bachelor in Informatics and Computing, tackling two very distinct challenges with […]

Read More
Article
We will be at VISUM Summer School

For the third time in a row, we are proud sponsors of VISUM summer school. VISUM is a worldwide reference summer school in Computer Vision and Machine Intelligence, attracting both experts and students to exchange experiences and knowledge in the field. VISUM has counted on the honor of receiving students from all corners of the […]

Read More
Article
Self-Supervised Learning workshop at the XIII Symposium on Bioengineering

We are delighted to announce our forthcoming workshop on Self-Supervised Learning, a pivotal event slated to take place during the XIII Symposium on Bioengineering, the largest Portugurese Bioengineering congress! The Symposium on Bioengineering is a beacon of collaboration, organized by the Bioengineering Students’ Association, and caters to students and researchers alike. It stands firmly on […]

Read More
Article
Teaching Models With Free Data

“The more I see, the less I know” might be a saying, but it does not apply to AI models. It’s well known that the performance of an artificial neural network is highly dependent on the volume and on the diversity of the data that was shown to the model. This happens because exposing the […]

Read More