Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory
Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory
Development of Quadratic Neural Unit with Applications to Pattern Classification
ISUMA '03 Proceedings of the 4th International Symposium on Uncertainty Modelling and Analysis
ISUMA '03 Proceedings of the 4th International Symposium on Uncertainty Modelling and Analysis
Cubic Neural Unit for Control Applications
ISUMA '03 Proceedings of the 4th International Symposium on Uncertainty Modelling and Analysis
Neural Units with Higher-Order Synaptic Operations for Robotic Image Processing Applications
Soft Computing - A Fusion of Foundations, Methodologies and Applications - Fuzzy-neural computation and robotics
Modeling and prediction with a class of time delay dynamic neural networks
Applied Soft Computing
Foundation of Notation and Classification of Nonconventional Static and Dynamic Neural Units
COGINF '07 Proceedings of the 6th IEEE International Conference on Cognitive Informatics
Learning polynomial feedforward neural networks by genetic programming and backpropagation
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
This paper reviews the background as well as the most contemporary developments and applications of nonconventional neural architectures (NNA) at the Department of Instrumentation and Control Engineering, at the Czech Technical University in Prague (CTU) with respect to continuous cooperation with our international collaborators [1] [2] [3]. First, the onset of the need for development of nonconventional neural units is introduced on the background of original research of evaluation and prediction of complex time series using neural networks and modeling and evaluation of complex dynamic systems - particularly focusing heart rate variability. Second, the classification of the recently developed new neural architectures is reviewed; mathematical structure of the NNA is discussed in comparison to a biological neuron involving parallels of nonsynaptic neural processing and thus revealing the need for extension of our general understanding to mathematical notation of artificial neurons. Then, founding principles of adaptive evaluation of complex high-dimensional dynamic systems using low-dimensional dynamic NNA are reviewed and achievements for both theoretical as well as real-world data are discussed.