Výsledky vyhledávání - "Médina, José"

Report

Pretraining Graph Transformers with Atom-in-a-Molecule Quantum Properties for Improved ADMET Modeling

Autor: Fallani, Alessio, Nugmanov, Ramil, Arjona-Medina, Jose, Wegner, Jörg Kurt, Tkatchenko, Alexandre, Chernichenko, Kostiantyn

We evaluate the impact of pretraining Graph Transformer architectures on atom-level quantum-mechanical features for the modeling of absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties of drug-like compounds. We compare th

Externí odkaz: http://arxiv.org/abs/2410.08024

Zobrazit plný text záznamu

Report

Analysis of Atom-level pretraining with Quantum Mechanics (QM) data for Graph Neural Networks Molecular property models

Autor: Arjona-Medina, Jose, Nugmanov, Ramil

Despite the rapid and significant advancements in deep learning for Quantitative Structure-Activity Relationship (QSAR) models, the challenge of learning robust molecular representations that effectively generalize in real-world scenarios to novel co

Externí odkaz: http://arxiv.org/abs/2405.14837

Zobrazit plný text záznamu

Report

The rational (non-)formality of the non-3-equal manifolds

Autor: González, Jesús, León-Medina, José Luis

Let $M^{(k)}_{d}(n)$ be the manifold of $n$-tuples $(x_1,\ldots,x_n)\in(\mathbb{R}^d)^n$ having non-$k$-equal coordinates. We show that, for $d\geq2$, $M^{(3)}_{d}(n)$ is rationally formal if and only if $n\leq 6$. This stands in sharp contrast with

Externí odkaz: http://arxiv.org/abs/2401.01449

Zobrazit plný text záznamu

Report

MEET: A Monte Carlo Exploration-Exploitation Trade-off for Buffer Sampling

Autor: Ott, Julius, Servadei, Lorenzo, Arjona-Medina, Jose, Rinaldi, Enrico, Mauro, Gianfranco, Lopera, Daniela Sánchez, Stephan, Michael, Stadelmayer, Thomas, Santra, Avik, Wille, Robert

Data selection is essential for any data-based optimization technique, such as Reinforcement Learning. State-of-the-art sampling strategies for the experience replay buffer improve the performance of the Reinforcement Learning agent. However, they do

Externí odkaz: http://arxiv.org/abs/2210.13545

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání