Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/138142
Title: ATTENTIVE RECURRENT NEURAL NETWORKS
Authors: LI MINGMING
ORCID iD:   orcid.org/0000-0003-4741-7105
Keywords: Recurrent Neural Networks; Attention; Associative Memories; Saliency;Image Classification;Navigation
Issue Date: 17-Jul-2017
Source: LI MINGMING (2017-07-17). ATTENTIVE RECURRENT NEURAL NETWORKS. ScholarBank@NUS Repository.
Abstract: This thesis investigates attentive recurrent neural networks (RNN) and their applications, which allow distillation of valuable information in a similar way to attentions in humans' cognition. It enables RNNs to selectively process different patches of an input sample (intra-sample attention) or distinguish samples that contain more informative resources for learning (inter-sample attention). Particularly, saliency-driven associative memory (SDAM) and content-driven associative memory (CDAM) are designed with visual saliency encoding for attentive storage and retrieval of image patterns. A stochastic attentive RNN called Glance and Glimpse Network (GGNet) is developed for image classification, whose learning rule can be derived by either reinforcement learning with reward shaping or direct probabilistic inference via importance sampling. Finally, Partially Observable Trust Region Policy Optimization (PO-TRPO) algorithm is developed to learn navigation policies for socially concomitant mobile robot navigation. The learning process is facilitated with the Role Playing Learning (RPL) scheme. Both simulative and experimental results are provided.
URI: http://scholarbank.nus.edu.sg/handle/10635/138142
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
LiM.pdf8.99 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

9
checked on Jan 14, 2018

Download(s)

5
checked on Jan 14, 2018

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.