Guardado en:
Detalles Bibliográficos
Autores principales: Perry, Altai, Vuong, Luat
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:https://arxiv.org/abs/2304.12172
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911191287201792
author Perry, Altai
Vuong, Luat
author_facet Perry, Altai
Vuong, Luat
contents Hybrid optical neural networks (HONNs) offload some electronic computation to optical preprocessors to achieve low-power and fast training and inference phases in machine learning tasks. Our contribution to the development of HONNs is a spectral-methods paradigm for building synthetic training data for machine-learned models. Here, our synthetic training image data does not resemble the image test data. As a result, the neural network focuses on learning specific features parameterized by the synthetic training data. Within this paradigm, a dataset's singular value decomposition entropy indicates {\it learnability}, i.e., how rapidly a model converges. Subsequently, we train a neural network model to rapidly learn specific features for further downstream analyses.
format Preprint
id arxiv_https___arxiv_org_abs_2304_12172
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Generalized Training for Neural Network Learnability: a Spectral Methods Approach
Perry, Altai
Vuong, Luat
Optics
Hybrid optical neural networks (HONNs) offload some electronic computation to optical preprocessors to achieve low-power and fast training and inference phases in machine learning tasks. Our contribution to the development of HONNs is a spectral-methods paradigm for building synthetic training data for machine-learned models. Here, our synthetic training image data does not resemble the image test data. As a result, the neural network focuses on learning specific features parameterized by the synthetic training data. Within this paradigm, a dataset's singular value decomposition entropy indicates {\it learnability}, i.e., how rapidly a model converges. Subsequently, we train a neural network model to rapidly learn specific features for further downstream analyses.
title Generalized Training for Neural Network Learnability: a Spectral Methods Approach
topic Optics
url https://arxiv.org/abs/2304.12172