Simple Lifelong Learning Machines

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Dey, Jayanta, Vogelstein, Joshua T., Helm, Hayden S., LeVine, Will, Mehta, Ronak D., Tomita, Tyler M., Xu, Haoyin, Geisa, Ali, Wang, Qingyang, van de Ven, Gido M., Gao, Chenyu, Yang, Weiwei, Tower, Bryan, Larson, Jonathan, White, Christopher M., Priebe, Carey E.
Formato: Preprint
Publicado: 2020
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908474044055552
author Dey, Jayanta
Vogelstein, Joshua T.
Helm, Hayden S.
LeVine, Will
Mehta, Ronak D.
Tomita, Tyler M.
Xu, Haoyin
Geisa, Ali
Wang, Qingyang
van de Ven, Gido M.
Gao, Chenyu
Yang, Weiwei
Tower, Bryan
Larson, Jonathan
White, Christopher M.
Priebe, Carey E.
author_facet Dey, Jayanta
Vogelstein, Joshua T.
Helm, Hayden S.
LeVine, Will
Mehta, Ronak D.
Tomita, Tyler M.
Xu, Haoyin
Geisa, Ali
Wang, Qingyang
van de Ven, Gido M.
Gao, Chenyu
Yang, Weiwei
Tower, Bryan
Larson, Jonathan
White, Christopher M.
Priebe, Carey E.
contents In lifelong learning, data are used to improve performance not only on the present task, but also on past and future (unencountered) tasks. While typical transfer learning algorithms can improve performance on future tasks, their performance on prior tasks degrades upon learning new tasks (called forgetting). Many recent approaches for continual or lifelong learning have attempted to maintain performance on old tasks given new tasks. But striving to avoid forgetting sets the goal unnecessarily low. The goal of lifelong learning should be to use data to improve performance on both future tasks (forward transfer) and past tasks (backward transfer). In this paper, we show that a simple approach -- representation ensembling -- demonstrates both forward and backward transfer in a variety of simulated and benchmark data scenarios, including tabular, vision (CIFAR-100, 5-dataset, Split Mini-Imagenet, and Food1k), and speech (spoken digit), in contrast to various reference algorithms, which typically failed to transfer either forward or backward, or both. Moreover, our proposed approach can flexibly operate with or without a computational budget.
format Preprint
id arxiv_https___arxiv_org_abs_2004_12908
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Simple Lifelong Learning Machines
Dey, Jayanta
Vogelstein, Joshua T.
Helm, Hayden S.
LeVine, Will
Mehta, Ronak D.
Tomita, Tyler M.
Xu, Haoyin
Geisa, Ali
Wang, Qingyang
van de Ven, Gido M.
Gao, Chenyu
Yang, Weiwei
Tower, Bryan
Larson, Jonathan
White, Christopher M.
Priebe, Carey E.
Artificial Intelligence
Machine Learning
In lifelong learning, data are used to improve performance not only on the present task, but also on past and future (unencountered) tasks. While typical transfer learning algorithms can improve performance on future tasks, their performance on prior tasks degrades upon learning new tasks (called forgetting). Many recent approaches for continual or lifelong learning have attempted to maintain performance on old tasks given new tasks. But striving to avoid forgetting sets the goal unnecessarily low. The goal of lifelong learning should be to use data to improve performance on both future tasks (forward transfer) and past tasks (backward transfer). In this paper, we show that a simple approach -- representation ensembling -- demonstrates both forward and backward transfer in a variety of simulated and benchmark data scenarios, including tabular, vision (CIFAR-100, 5-dataset, Split Mini-Imagenet, and Food1k), and speech (spoken digit), in contrast to various reference algorithms, which typically failed to transfer either forward or backward, or both. Moreover, our proposed approach can flexibly operate with or without a computational budget.
title Simple Lifelong Learning Machines
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2004.12908