Inici
→
Recerca: articles, congressos, llibres
→
Departament de Tecnologies de la Informació i les Comunicacions
→
Visualitza Departament de Tecnologies de la Informació i les Comunicacions per matèria

Visualitza Departament de Tecnologies de la Informació i les Comunicacions per matèria "Adaptation models"

Ara mostrant els elements 1-4 de 4

Autonomous development of turn-taking behaviors in agent populations: a computational study

Moulin-Frier, Clément; Sánchez Fibla, Martí; Verschure, Paul F. M. J. (Institute of Electrical and Electronics Engineers (IEEE), 2015)

We provide an original computational model showing how turn-taking behaviors can self-organize out of sensorimotor/ninteractions between vocalizing agents. These agents are equipped with a cognitive architecture based on ...
Efficient remote photoplethysmography with temporal derivative modules and time-shift invariant loss

Comas, Joaquim; Ruiz Ovejero, Adrià; Sukno, Federico Mateo (Institute of Electrical and Electronics Engineers (IEEE), 2022)

We present a lightweight neural model for remote heart rate estimation focused on the efficient spatio-temporal learning of facial photoplethysmography (PPG) based on i) modelling of PPG dynamics by combinations of multiple ...
Orchestrating networked machine learning applications using Autosteer

Wen, Zhenyu; Hu, Haozhen; Yang, Renyu; Qian, Bian; Sham, Ringo W.H.; Rui, Sun; Xu, Jie; Patel, Pankesh; Rana, Omer; Dustdar, Schahram; Ranjan, Rajiv (Institute of Electrical and Electronics Engineers (IEEE), 2022)

A platform for orchestrating networked machine learning (ML) applications over distributed environments is described. ML applications are transformed into automated pipelines that manage the whole application lifecycle and ...
WGansing: a multi-voice singing voice synthesizer based on the Wasserstein-Gan

Chandna, Pritish; Blaauw, Merlijn; Bonada, Jordi, 1973-; Gómez Gutiérrez, Emilia, 1975- (Institute of Electrical and Electronics Engineers (IEEE), 2019)

We present a deep neural network based singing voice synthesizer, inspired by the Deep Convolutions Generative Adversarial Networks (DCGAN) architecture and optimized using the Wasserstein-GAN algorithm. We use vocoder ...