Adaptive filter theory (2nd ed.)
Adaptive filter theory (2nd ed.)
Elements of signal detection and estimation
Elements of signal detection and estimation
Speech recognition using neural networks
Speech recognition using neural networks
Are Multilayer Perceptrons Adequate for Pattern Recognition and Verification?
IEEE Transactions on Pattern Analysis and Machine Intelligence
Neural and Adaptive Systems: Fundamentals through Simulations with CD-ROM
Neural and Adaptive Systems: Fundamentals through Simulations with CD-ROM
Parallel Models of Associative Memory
Parallel Models of Associative Memory
Transient Signal Detection with Neural Networks: The Search for the Desired Signal
Advances in Neural Information Processing Systems 5, [NIPS Conference]
IJCNN '00 Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 2 - Volume 2
Nonlinear extensions to the minimum average correlation energy filter
Nonlinear extensions to the minimum average correlation energy filter
Large vocabulary speech recognition using neural prediction model
ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
Neural Networks: A Comprehensive Foundation (3rd Edition)
Neural Networks: A Comprehensive Foundation (3rd Edition)
Analysis and design of echo state networks
Neural Computation
Recurrence enhances the spatial encoding of static inputs in reservoir networks
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part II
Survey: Reservoir computing approaches to recurrent neural network training
Computer Science Review
| Hi-index | 0.00 |
The use of echo state networks (ESN) to find patterns in time (dynamical pattern recognition) has been limited. This paper argues that ESNs are particularly well suited for dynamical pattern recognition and proposes a linear associative memory (LAM) as a novel readout for ESNs. From the class of LAMs, the minimum average correlation energy (MACE) filter is adopted because of its high rejection characteristics that allow its use as a detector in the automatic pattern recognition literature. In the ESN application, the MACE interprets the states of the ESN as a two-dimensional ''image'', one dimension being time and the other the processing element index (space). An optimal template image for each class, which associates ESN states with the class label, can be analytically computed using training data. During testing, ESN states are correlated with each template image and the class label of the template with the highest correlation is assigned to the input pattern. The ESN-MACE combination leads to a nonlinear template matcher with robust noise performance as needed in non-Gaussian, nonlinear digital communication channels. A real-world data experiment for chemical sensing with an electronic nose is included to demonstrate the validity of this approach. Moreover, the proposed readout can also be used with liquid state machines eliminating the need to convert spike trains into continuous signals by binning or low-pass filtering.