1 code implementation • 20 Oct 2023 • Eduardo Soares, Akihiro Kishimoto, Emilio Vital Brazil, Seiji Takeda, Hiroshi Kajino, Renato Cerqueira
Pre-trained Language Models have emerged as promising tools for predicting molecular properties, yet their development is in its early stages, necessitating further research to enhance their efficacy and address challenges such as generalization and sample efficiency.
no code implementations • 22 Jun 2023 • Eduardo Soares, Emilio Vital Brazil, Karen Fiorela Aquino Gutierrez, Renato Cerqueira, Dan Sanders, Kristin Schmidt, Dmitry Zubarev
Our approach opens up promising avenues for future research in molecular property prediction by harnessing the synergistic potential of both chemical language and physicochemical features, leading to enhanced performance and advancements in the field.
no code implementations • 9 Mar 2023 • Emilio Vital Brazil, Eduardo Soares, Lucas Villa Real, Leonardo Azevedo, Vinicius Segura, Luiz Zerkowski, Renato Cerqueira
Moreover, the dataset will be used in most cases as a blueprint of an entity that at any moment can be stored as a table.
no code implementations • 23 Oct 2022 • Ziyang Zhang, Plamen Angelov, Eduardo Soares, Nicolas Longepe, Pierre Philippe Mathieu
Earth observation is fundamental for a range of human activities including flood response as it offers vital information to decision makers.
no code implementations • 2 Feb 2020 • Plamen Angelov, Eduardo Soares
In summary, we propose a new approach specifically advantageous for imbalanced multi-class problems that achieved two world records on well known hard benchmark problems and the best result on another problem in terms of accuracy.
no code implementations • 5 Dec 2019 • Plamen Angelov, Eduardo Soares
In this paper, we propose an elegant solution that is directly addressing the bottlenecks of the traditional deep learning approaches and offers a clearly explainable internal architecture that can outperform the existing methods, requires very little computational resources (no need for GPUs) and short training times (in the order of seconds).
no code implementations • 1 Nov 2019 • Eduardo Soares, Plamen Angelov
In this paper we offer a method and algorithm, which make possible fully autonomous (unsupervised) detection of new classes, and learning following a very parsimonious training priming (few labeled data samples only).
no code implementations • 18 Sep 2019 • Eduardo Soares, Plamen Angelov
Recidivism prediction provides decision makers with an assessment of the likelihood that a criminal defendant will reoffend that can be used in pre-trial decision-making.