Neural Network Structure for Spatio-Temporal Long-Term Memory
- 30 April 2012
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 23 (6), 971-983
- https://doi.org/10.1109/tnnls.2012.2191419
Abstract
This paper proposes a neural network structure for spatio-temporal learning and recognition inspired by the long-term memory (LTM) model of the human cortex. Our structure is able to process real-valued and multidimensional sequences. This capability is attained by addressing three critical problems in sequential learning, namely the error tolerance, the significance of sequence elements and memory forgetting. We demonstrate the potential of the framework with a series of synthetic simulations and the Australian sign language (ASL) dataset. Results show that our LTM model is robust to different types of distortions. Second, our LTM model outperforms other sequential processing models in a classification task for the ASL dataset.Keywords
This publication has 32 references indexed in Scilit:
- Bayesian surprise attracts human attentionVision Research, 2009
- Classifying spatiotemporal object trajectories using unsupervised learning in the coefficient feature spaceMultimedia Systems, 2006
- Cognitive Navigation Based on Nonuniform Gabor Space Sampling, Unsupervised Growing Networks, and Reinforcement LearningIEEE Transactions on Neural Networks, 2004
- Spatiotemporal Connectionist Networks: A Taxonomy and ReviewNeural Computation, 2001
- Multi-associative neural networks and their applications to learning and retrieving complex spatio-temporal sequencesIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 1999
- Learning and retrieving spatio-temporal sequences with any static associative neural networkIEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, 1998
- Anticipation-based temporal pattern generationIEEE Transactions on Systems, Man, and Cybernetics, 1995
- Timing and chunking in processing temporal orderIEEE Transactions on Systems, Man, and Cybernetics, 1993
- Finding structure in timeCognitive Science, 1990
- A massively parallel architecture for a self-organizing neural pattern recognition machineComputer Vision, Graphics, and Image Processing, 1987