Variational Adaptive Noise and Dropout towards Stable Recurrent Neural Networks

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kobayashi, Taisuke, Murata, Shingo
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914345411149824
author Kobayashi, Taisuke
Murata, Shingo
author_facet Kobayashi, Taisuke
Murata, Shingo
contents This paper proposes a novel stable learning theory for recurrent neural networks (RNNs), so-called variational adaptive noise and dropout (VAND). As stabilizing factors for RNNs, noise and dropout on the internal state of RNNs have been separately confirmed in previous studies. We reinterpret the optimization problem of RNNs as variational inference, showing that noise and dropout can be derived simultaneously by transforming the explicit regularization term arising in the optimization problem into implicit regularization. Their scale and ratio can also be adjusted appropriately to optimize the main objective of RNNs, respectively. In an imitation learning scenario with a mobile manipulator, only VAND is able to imitate sequential and periodic behaviors as instructed. https://youtu.be/UOho3Xr6A2w
format Preprint
id arxiv_https___arxiv_org_abs_2506_01350
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Variational Adaptive Noise and Dropout towards Stable Recurrent Neural Networks
Kobayashi, Taisuke
Murata, Shingo
Machine Learning
Robotics
This paper proposes a novel stable learning theory for recurrent neural networks (RNNs), so-called variational adaptive noise and dropout (VAND). As stabilizing factors for RNNs, noise and dropout on the internal state of RNNs have been separately confirmed in previous studies. We reinterpret the optimization problem of RNNs as variational inference, showing that noise and dropout can be derived simultaneously by transforming the explicit regularization term arising in the optimization problem into implicit regularization. Their scale and ratio can also be adjusted appropriately to optimize the main objective of RNNs, respectively. In an imitation learning scenario with a mobile manipulator, only VAND is able to imitate sequential and periodic behaviors as instructed. https://youtu.be/UOho3Xr6A2w
title Variational Adaptive Noise and Dropout towards Stable Recurrent Neural Networks
topic Machine Learning
Robotics
url https://arxiv.org/abs/2506.01350