Por favor, use este identificador para citar o enlazar este ítem:
http://hdl.handle.net/10609/149921
Registro completo de metadatos
Campo DC | Valor | Lengua/Idioma |
---|---|---|
dc.contributor.author | Raigada-García, Ricard-Santiago | - |
dc.date.accessioned | 2024-03-04T14:59:28Z | - |
dc.date.available | 2024-03-04T14:59:28Z | - |
dc.date.issued | 2024-03-01 | - |
dc.identifier.uri | http://hdl.handle.net/10609/149921 | - |
dc.description.abstract | The study proposes an optimization algorithm for machine learning, called Quantum-Inspired Adaptative Learning Rate Optimization (QIALRO), inspired by principles of quantum mechanics. Although the algorithm operates in the classical domain, its conception is based on the ability of quantum systems to simultaneously explore multiple potential states, a property that is sought to be emulated in the optimization of machine learning models. It has been implemented based on softmax regression, cross entropy loss, RMSProp optimizer for learning rate adaptation. The learning rate adjustment mechanism is inspired by the quantum search for optimal solutions by simultaneously exploring multiple possibilities. It adjusts the learning rate by increasing it when the current iteration of the model shows an improvement in loss, leading to an optimal solution space. The technique also permits a decrease in the rate by mimicking the reversion to previous states observed in quantum computing. | en |
dc.format.mimetype | application/pdf | ca |
dc.language.iso | eng | ca |
dc.publisher | Universitat Oberta de Catalunya (UOC) | ca |
dc.rights.uri | http://creativecommons.org/licenses/by/3.0/es/ | - |
dc.subject | Quantumlike learning | en |
dc.subject | Optimization | en |
dc.subject | Machine Learning | en |
dc.subject | Adaptive Learning Rate | en |
dc.subject | Softmax Regression | en |
dc.subject | Cross-Entropy Loss | en |
dc.subject | RMSProp | en |
dc.subject | Algorithm Convergence | en |
dc.subject | Classical Computing | en |
dc.subject | Multiclass Classification Models | en |
dc.title | Quantum-Inspires Adaptive Learning Rate Optimization (QIALRO) | ca |
dc.type | info:eu-repo/semantics/workingPaper | ca |
Aparece en las colecciones: | Treballs finals de carrera, treballs de recerca, etc. |
Ficheros en este ítem:
Fichero | Descripción | Tamaño | Formato | |
---|---|---|---|---|
Quantum-Inspired adaptative learning rate optimization QIALRO.pdf | The study of an optimization algorithm inspired by principles of quantum mechanics. | 660,73 kB | Adobe PDF | Visualizar/Abrir |
Comparte:
Los ítems del Repositorio están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.