Sequence recognition with spatio-temporal long-term memory organization
In this work, we propose a connectionist memory structure for spatio-temporal sequence learning and recognition inspired by the Long-Term Memory structure of human cortex. Besides symbolic data, our framework is able to continuously process real-valued multi-dimensional data stream. This capability...
Saved in:
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2013
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/98284 http://hdl.handle.net/10220/12399 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-98284 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-982842020-05-28T07:19:04Z Sequence recognition with spatio-temporal long-term memory organization Nguyen, Vu Anh Goh, Wooi Boon Starzyk, Janusz A. School of Computer Engineering International Joint Conference on Neural Networks (2012 : Brisbane, Australia) DRNTU::Engineering::Computer science and engineering In this work, we propose a connectionist memory structure for spatio-temporal sequence learning and recognition inspired by the Long-Term Memory structure of human cortex. Besides symbolic data, our framework is able to continuously process real-valued multi-dimensional data stream. This capability is made possible by addressing three critical problems in spatio-temporal learning, namely error tolerance, significance of sequence's elements and memory forgetting mechanism. We demonstrate the potential of the framework with a synthetic example and a real world example, namely the task of hand-sign language interpretation with the Australian Sign Language dataset. 2013-07-26T06:53:20Z 2019-12-06T19:53:10Z 2013-07-26T06:53:20Z 2019-12-06T19:53:10Z 2012 2012 Conference Paper Nguyen, V. A., Starzyk, J. A., & Goh, W. B. (2012). Sequence recognition with spatio-temporal long-term memory organization. The 2012 International Joint Conference on Neural Networks (IJCNN). https://hdl.handle.net/10356/98284 http://hdl.handle.net/10220/12399 10.1109/IJCNN.2012.6252682 en © 2012 IEEE. |
institution |
Nanyang Technological University |
building |
NTU Library |
country |
Singapore |
collection |
DR-NTU |
language |
English |
topic |
DRNTU::Engineering::Computer science and engineering |
spellingShingle |
DRNTU::Engineering::Computer science and engineering Nguyen, Vu Anh Goh, Wooi Boon Starzyk, Janusz A. Sequence recognition with spatio-temporal long-term memory organization |
description |
In this work, we propose a connectionist memory structure for spatio-temporal sequence learning and recognition inspired by the Long-Term Memory structure of human cortex. Besides symbolic data, our framework is able to continuously process real-valued multi-dimensional data stream. This capability is made possible by addressing three critical problems in spatio-temporal learning, namely error tolerance, significance of sequence's elements and memory forgetting mechanism. We demonstrate the potential of the framework with a synthetic example and a real world example, namely the task of hand-sign language interpretation with the Australian Sign Language dataset. |
author2 |
School of Computer Engineering |
author_facet |
School of Computer Engineering Nguyen, Vu Anh Goh, Wooi Boon Starzyk, Janusz A. |
format |
Conference or Workshop Item |
author |
Nguyen, Vu Anh Goh, Wooi Boon Starzyk, Janusz A. |
author_sort |
Nguyen, Vu Anh |
title |
Sequence recognition with spatio-temporal long-term memory organization |
title_short |
Sequence recognition with spatio-temporal long-term memory organization |
title_full |
Sequence recognition with spatio-temporal long-term memory organization |
title_fullStr |
Sequence recognition with spatio-temporal long-term memory organization |
title_full_unstemmed |
Sequence recognition with spatio-temporal long-term memory organization |
title_sort |
sequence recognition with spatio-temporal long-term memory organization |
publishDate |
2013 |
url |
https://hdl.handle.net/10356/98284 http://hdl.handle.net/10220/12399 |
_version_ |
1681056868731977728 |