This thesis studies the role of differential geometry in optimization and classification. The objective of this research is to develop machine learning models that can perform better than existing works under various metrics and diverse datasets. One work is on constrained large-scale non-convex optimization where the constraint set implies a manif...
This composition extends my research, with the continuous objective of creating a sense of autonomy and presence on stage by focusing on actions that aim to provoke an inner intention in the player and subsequently produce sound. The approach involves treating sound holarchically, considering factors such as physical actions, dynamic energy, strain...
Published in Theranostics
Background: Neurons in the ventral tegmental area (VTA) are sensitive to stress and their maladaptation have been implicated in the psychiatric disorders such as anxiety and addiction, etc. The cellular properties of the VTA neurons in response to different stressors related to different emotional processing remain to be investigated. Methods: By c...
The practical interest of using ensemble methods has been highlighted in several works. Aggregating predictors leads very often to improve the performance of a single one. A fruitful recipe is to generate several predictors from a single one by perturbing the learning set and, instead of selecting the best one, to aggregate them. Bagging, boosting ...
Accurate and reliable cancer categorization is crucial for informing medical decisions and improving patient care. Deep learning algorithms have emerged as a promising approach due to their ability to extract intricate patterns and correlations from large clinical datasets. In this paper, we propose a novel ensemble technique based on the Levy Stab...
This thesis aims at enhancing the generalization abilities of deep neural networks, a critical step towards fair and reliable artificial intelligence. Specifically, we address the drop in performance when models are evaluated on test samples with a distribution shift with respect to the train samples. To this end, we focus on ensembling strategies:...
[ES] La genómica es la disciplina que estudia el genoma humano. Uno de los principales desafíos es: la detección de variables genéticas relevantes que determinen un genotipo o enfermedad. En este ámbito de estudio nos encontramos con una peculiaridad en los datos: la cantidad de muestras es limitada debido a los costos y la variabilidad de cada obs...
[ES] La densidad mamaria es uno de los factores de riesgo del cáncer de mama, y depende directamente de la cantidad de tejido fibroglandular en proporción al tejido adiposo existente en la mama. En algunos casos, el historial familiar juega un papel importante en el desarrollo del tejido denso, por lo que, estudiar los biomarcadores que intervienen...
Neural Radiance Field (NeRF) is a popular method for synthesizing novel views of a scene from a set of input images. While NeRF has demonstrated state-of-the-art performance in several applications, it suffers from high computational requirements. Recent works have attempted to address these issues by including explicit volumetric information, whic...
Published in bioRxiv : the preprint server for biology
AlphaFold2's ability to accurately predict protein structures from a multiple sequence alignment (MSA) has raised many questions about the utility of the models generated in downstream structural analysis. Two outstanding questions are the prediction of the consequences of point mutations and the completeness of the landscape of protein conformatio...
