- http://experiment.worldcat.org/entity/work/data/1149975527#Topic/uberwachtes_lernen
- http://experiment.worldcat.org/entity/work/data/1149975527#Topic/ingenierie
- http://experiment.worldcat.org/entity/work/data/1149975527#Topic/computational_intelligence
- http://experiment.worldcat.org/entity/work/data/1149975527#Topic/reseaux_neuronaux_informatique
- http://id.loc.gov/authorities/subjects/sh90001937
- http://experiment.worldcat.org/entity/work/data/1149975527#Topic/computers_intelligence_ai_&_semantics
- http://experiment.worldcat.org/entity/work/data/1149975527#Topic/komplexe_zahl
- http://experiment.worldcat.org/entity/work/data/1149975527#Topic/signal_image_and_speech_processing
- http://id.worldcat.org/fast/1036260
- http://id.loc.gov/authorities/subjects/sh94008290
- http://experiment.worldcat.org/entity/work/data/1149975527#Topic/computers_neural_networks
- http://id.worldcat.org/fast/1139041
- http://experiment.worldcat.org/entity/work/data/1149975527#Topic/apprentissage_supervise_intelligence_artificielle
- http://experiment.worldcat.org/entity/work/data/1149975527#Topic/neural_networks_computer_science
- http://id.loc.gov/authorities/subjects/sh85043176
- http://experiment.worldcat.org/entity/work/data/1149975527#Topic/engineering
- http://experiment.worldcat.org/entity/work/data/1149975527#Topic/neuronales_netz
- http://id.worldcat.org/fast/910312

- "Recent advancements in the field of telecommunications, medical imaging and signal processing deal with signals that are inherently time varying, nonlinear and complex-valued. The time varying, nonlinear characteristics of these signals can be effectively analyzed using artificial neural networks. Furthermore, to efficiently preserve the physical characteristics of these complex-valued signals, it is important to develop complex-valued neural networks and derive their learning algorithms to represent these signals at every step of the learning process. This monograph comprises a collection of new supervised learning algorithms along with novel architectures for complex-valued neural networks. The concepts of meta-cognition equipped with a self-regulated learning have been known to be the best human learning strategy. In this monograph, the principles of meta-cognition have been introduced for complex-valued neural networks in both the batch and sequential learning modes. For applications where the computation time of the training process is critical, a fast learning complex-valued neural network called as a fully complex-valued relaxation network along with its learning algorithm has been presented. The presence of orthogonal decision boundaries helps complex-valued neural networks to outperform real-valued networks in performing classification tasks. This aspect has been highlighted. The performances of various complex-valued neural networks are evaluated on a set of benchmark and real-world function approximation and real-valued classification problems."
- "Recent advancements in the field of telecommunications, medical imaging and signal processing deal with signals that are inherently time varying, nonlinear and complex-valued. The time varying, nonlinear characteristics of these signals can be effectively analyzed using artificial neural networks. Furthermore, to efficiently preserve the physical characteristics of these complex-valued signals, it is important to develop complex-valued neural networks and derive their learning algorithms to represent these signals at every step of the learning process. This monograph comprises a collection of new supervised learning algorithms along with novel architectures for complex-valued neural networks. The concepts of meta-cognition equipped with a self-regulated learning have been known to be the best human learning strategy. In this monograph, the principles of meta-cognition have been introduced for complex-valued neural networks in both the batch and sequential learning modes. For applications where the computation time of the training process is critical, a fast learning complex-valued neural network called as a fully complex-valued relaxation network along with its learning algorithm has been presented. The presence of orthogonal decision boundaries helps complex-valued neural networks to outperform real-valued networks in performing classification tasks. This aspect has been highlighted. The performances of various complex-valued neural networks are evaluated on a set of benchmark and real-world function approximation and real-valued classification problems."@en

- "Electronic books"

- http://www.worldcat.org/oclc/888467630
- http://www.worldcat.org/oclc/812056206
- http://www.worldcat.org/oclc/858884704
- http://www.worldcat.org/oclc/906273352
- http://www.worldcat.org/oclc/835896013
- http://www.worldcat.org/oclc/781681923
- http://www.worldcat.org/oclc/820467164
- http://www.worldcat.org/oclc/863912097
- http://www.worldcat.org/oclc/889166371
- http://www.worldcat.org/oclc/805398598
- http://www.worldcat.org/oclc/884597633