Self-organizing MapsSelf-Organizing Maps deals with the most popular artificial neural-network algorithm of the unsupervised-learning category, viz. the Self-Organizing Map (SOM). As this book is the main monograph on the subject, it discusses all the relevant aspects ranging from the history, motivation, fundamentals, theory, variants, advances, and applications, to the hardware of SOMs. An extensive literature survey of over 2000 contemporary studies is included. Thus, answers to the most frequently asked questions relating to this topic can be found in this volume. The subject is presented in a didactive manner and only a general theoretical background is required. The reader will be guided by the many case studies to the very frontier of modern research in this area. |
Other editions - View all
Self Organizing Maps: Applications and Novel Algorithm Design Josphat Igadwa Mwasiagi Limited preview - 2011 |
Common terms and phrases
accuracy adaptive algorithm applications approximation array Artificial Intelligence Artificial Neural Networks ASSOM basic basis vectors cell classification clustering codebook vectors components computing Congress on Neural convergence corresponding cortex defined denoted density function described dimensionality discussed distance dot product dynamic equation Euclidean feature filters Hillsdale IEEE Int IEEE Service Center input vector Joint Conf Kangas Kohonen lattice learning linear linear subspace matrix method Nanterre neighborhood function Netherlands 1991 Networks IEEE Service Neural Networks IEEE neuron nodes nonlinear North-Holland operation optimal orthogonal output parameters pattern recognition phonemes Piscataway probability density function problem Proc reference vectors respectively samples SAN DIEGO scalar Sect self-organizing Self-Organizing Map sequence Signal Processing Simula simulation speech recognition Springer statistical stochastic subspace supervised learning symbols Symp synaptic tion topology transformation two-dimensional unit values vector quantization Voronoi tessellation wavelets whereby winner World Congress