Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group

Training an improved recurrent attention model using an alternative reward function

Not Accessible

Your library or personal account may give you access

Abstract

A recurrent attention model is considered for application to image classification tasks. Modifications to the approach to improve its accuracy are described. Utilization of the reward in the form of negative cross entropy, which increases the informative value of the reinforcement signal, is proposed for neural network training. A deeper architecture of the attention control subnetwork and an asynchronous actor–critic algorithm are also used. Experiments based on the MNIST and CIFAR datasets are conducted, which confirm the effectiveness of the proposed modifications. Experiments using learned classifiers are also conducted, which demonstrate the complexity of the simultaneous attention control and selection of an embedded classifier for analysis of the chosen patch.

© 2021 Optical Society of America

PDF Article
More Like This
Ensemble model with cascade attention mechanism for high-resolution remote sensing image scene classification

Fengpeng Li, Ruyi Feng, Wei Han, and Lizhe Wang
Opt. Express 28(15) 22358-22387 (2020)

PCCA-Model: an attention module for medical image segmentation

Linjie Liu, Guanglei Wang, Yanlin Wu, Hongrui Wang, and Yan Li
Biomed. Opt. Express 14(4) 1428-1444 (2023)

Automatic segmentation of OCT retinal boundaries using recurrent neural networks and graph search

Jason Kugelman, David Alonso-Caneiro, Scott A. Read, Stephen J. Vincent, and Michael J. Collins
Biomed. Opt. Express 9(11) 5759-5777 (2018)

Cited By

You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Select as filters


Select Topics Cancel
© Copyright 2024 | Optica Publishing Group. All rights reserved, including rights for text and data mining and training of artificial technologies or similar technologies.