Geometric deep learning is an emerging area of research in machine learning focusing on exploiting symmetries in problems to improve models. Its goal is to understand how transformations to the input should affect the output and design neural networks around the corresponding inductive bias. We present a message passing neural network architecture designed to be equivariant to column and row permutations of a matrix. We illustrate its advantages over traditional architectures like multi-layer perceptrons (MLPs), convolutional neural networks (CNNs) and even Transformers, on the combinatorial optimization task of recovering a set of deleted entries of a Hadamard matrix. We argue that this is a powerful application of the principles of Geometric Deep Learning to fundamental mathematics, and a potential stepping stone toward more insights on the Hadamard conjecture using Machine Learning techniques.
The perspective of the language in multimodal conversational AI for high-end fashion marketplaces
April 19, 2022
6:38 pm
Ricardo Sousa
Ricardo Sousa is Principal Data Scientist at FARFETCH. Driven to quickly trial novel Machine Learning approaches to disrupt different business areas, Ricardo was one key contributor in the “Search and Discovery” cluster. As a manager of Data Science, he co-lead four multidisciplinary product development teams composed of product, engineers, and scientists. Ricardo is currently leading the conversational commerce initiatives at FARFETCH to disrupt the high-end fashion commerce industry and contribute to novel solutions with Conversational AI Agents. With research interest in fields related to Information Retrieval leverage by modern Machine Learning, Computer Vision and Natural Language Processing he continues to contribute to the scientific community with articles in journals, conferences about his work at FARFETCH and co-organizing international events such as Multimodal Conversational AI Agents at ACM Multimedia.FARFETCHSeminários
Últimos seminários
Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decoding
June 17, 2025Large language models (LLMs) have emerged as strong contenders in machine translation. Yet, they often fall behind specialized neural machine…
Speech as a Biomarker for Disease Detection
May 20, 2025Today’s overburdened health systems face numerous challenges, exacerbated by an aging population. Speech emerges as a ubiquitous biomarker with strong…
Enhancing Uncertainty Estimation in Neural Networks
May 6, 2025Neural networks are often overconfident about their predictions, which undermines their reliability and trustworthiness. In this presentation, I will present…
Improving Evaluation Metrics for Vision-and-Language Models
April 22, 2025Evaluating image captions is essential for ensuring both linguistic fluency and accurate semantic alignment with visual content. While reference-free metrics…