Brain and Nature-Inspired Learning, Computation and Recognition presents a systematic analysis of neural networks, natural computing, machine learning and compression, algorithms and applications inspired by the brain and biological mechanisms found in nature. Sections cover new developments and main applications, algorithms and simulations. Developments in brain and nature-inspired learning have promoted interest in image processing, clustering problems, change detection, control theory and other disciplines. The book discusses the main problems and applications pertaining to bio-inspired computation and recognition, introducing algorithm implementation, model simulation, and practical application of parameter setting.
Readers will find solutions to problems in computation and recognition, particularly neural networks, natural computing, machine learning and compressed sensing. This volume offers a comprehensive and well-structured introduction to brain and nature-inspired learning, computation, and recognition.
1. Chapter 1. Introduction - p. 1 2. Chapter 2. The models and structure of neural networks - p. 47 3. Chapter 3. Theoretical basis of natural computation - p. 81 4. Chapter 4. Theoretical basis of machine learning - p. 97 5. Chapter 5. Theoretical basis of compressive sensing - p. 109 6. Chapter 6. Multiobjective evolutionary algorithm (MOEA)-based sparse clustering - p. 127 7. 6.1. Introduction - p. 128 8. 6.2. Modified function and feasible-guiding strategy-based constrained MOPs - p. 131 9. 6.3. Learning simultaneous adaptive clustering and classification learning via MOEA - p. 137 10. 6.4. A sparse spectral clustering framework via MOEA - p. 143 11. 6.5. Experiments - p. 151 12. 6.6. Summary - p. 190 13. Chapter 7. MOEA-based community detection - p. 197 14. Chapter 8. Evolutionary computation-based multiobjective capacitated arc routing optimizations - p. 233 15. 8.1. Introduction - p. 234 16. 8.2. Multipopulation cooperative coevolutionary algorithm - p. 237 17. 8.3. Immune clonal algorithm via directed evolution - p. 249 18. 8.4. Improved memetic algorithm via route distance grouping - p. 258 19. 8.5. Experiments - p. 264 20. 8.6. Summary - p. 297 21. Chapter 9. Multiobjective optimization algorithm-based image segmentation - p. 301 22. 9.1. Introduction - p. 301 23. 9.2. Multiobjective evolutionary fuzzy clustering with MOEA/D - p. 303 24. 9.3. Multiobjective immune algorithm for SAR image segmentation - p. 310 25. 9.4. Experiments - p. 317 26. 9.5. Summary - p. 346 27. Chapter 10. Graph-regularized feature selection based on spectral learning and subspace learning - p. 351 28. 10.1. Nonnegative spectral learning and subspace learning-based graph-regularized feature selection - p. 352 29. 10.2. Experiments of spectral learning and subspace learning methods for feature selection - p. 362 30. Chapter 11. Semisupervised learning based on nuclear norm regularization - p. 387 31. Chapter 12. Fast clustering methods based on learning spectral embedding - p. 407 32. Chapter 13. Fast clustering methods based on affinity propagation and density weighting - p. 437 33. Chapter 14. SAR image processing based on similarity measures and discriminant feature learning - p. 477 34. 14.1. SAR image retrieval based on similarity measures - p. 478 35. 14.2. SAR image change detection based on spatial coding and similarity - p. 528 36. Chapter 15. Hyperspectral image processing based on sparse learning and sparse graph - p. 559 37. 15.1. Hyperspectral image denoising based on hierarchical sparse learning - p. 560 38. 15.2. Hyperspectral image restoration based on hierarchical sparse Bayesian learning - p. 581 39. 15.3. Hyperspectral image dimensionality reduction using a sparse graph - p. 595 40. Chapter 16. Nonconvex compressed sensing framework based on block strategy and overcomplete dictionary - p. 617 41. Chapter 17. Sparse representation combined with fuzzy C-means (FCM) in compressed sensing - p. 629 42. Chapter 18. Compressed sensing by collaborative reconstruction - p. 669 43. Chapter 19. Hyperspectral image classification based on spectral information divergence and sparse representation - p. 693 44. Chapter 20. Neural network-based synthetic aperture radar image processing - p. 709 45. Chapter 21. Neural networks-based polarimetric SAR image classification - p. 723 46. Chapter 22. Deep neural network models for hyperspectral images - p. 735 47. Index - p. 749
Brain and Nature-Inspired Learning, Computation and Recognition presents a systematic analysis of neural networks, natural computing, machine learning and compression, algorithms and applications inspired by the brain and biological mechanisms found in nature. Sections cover new developments and main applications, algorithms and simulations. Developments in brain and nature-inspired learning have promoted interest in image processing, clustering problems, change detection, control theory and other disciplines. The book discusses the main problems and applications pertaining to bio-inspired computation and recognition, introducing algorithm implementation, model simulation, and practical application of parameter setting.
Readers will find solutions to problems in computation and recognition, particularly neural networks, natural computing, machine learning and compressed sensing. This volume offers a comprehensive and well-structured introduction to brain and nature-inspired learning, computation, and recognition.
1. Chapter 1. Introduction - p. 1 2. Chapter 2. The models and structure of neural networks - p. 47 3. Chapter 3. Theoretical basis of natural computation - p. 81 4. Chapter 4. Theoretical basis of machine learning - p. 97 5. Chapter 5. Theoretical basis of compressive sensing - p. 109 6. Chapter 6. Multiobjective evolutionary algorithm (MOEA)-based sparse clustering - p. 127 7. 6.1. Introduction - p. 128 8. 6.2. Modified function and feasible-guiding strategy-based constrained MOPs - p. 131 9. 6.3. Learning simultaneous adaptive clustering and classification learning via MOEA - p. 137 10. 6.4. A sparse spectral clustering framework via MOEA - p. 143 11. 6.5. Experiments - p. 151 12. 6.6. Summary - p. 190 13. Chapter 7. MOEA-based community detection - p. 197 14. Chapter 8. Evolutionary computation-based multiobjective capacitated arc routing optimizations - p. 233 15. 8.1. Introduction - p. 234 16. 8.2. Multipopulation cooperative coevolutionary algorithm - p. 237 17. 8.3. Immune clonal algorithm via directed evolution - p. 249 18. 8.4. Improved memetic algorithm via route distance grouping - p. 258 19. 8.5. Experiments - p. 264 20. 8.6. Summary - p. 297 21. Chapter 9. Multiobjective optimization algorithm-based image segmentation - p. 301 22. 9.1. Introduction - p. 301 23. 9.2. Multiobjective evolutionary fuzzy clustering with MOEA/D - p. 303 24. 9.3. Multiobjective immune algorithm for SAR image segmentation - p. 310 25. 9.4. Experiments - p. 317 26. 9.5. Summary - p. 346 27. Chapter 10. Graph-regularized feature selection based on spectral learning and subspace learning - p. 351 28. 10.1. Nonnegative spectral learning and subspace learning-based graph-regularized feature selection - p. 352 29. 10.2. Experiments of spectral learning and subspace learning methods for feature selection - p. 362 30. Chapter 11. Semisupervised learning based on nuclear norm regularization - p. 387 31. Chapter 12. Fast clustering methods based on learning spectral embedding - p. 407 32. Chapter 13. Fast clustering methods based on affinity propagation and density weighting - p. 437 33. Chapter 14. SAR image processing based on similarity measures and discriminant feature learning - p. 477 34. 14.1. SAR image retrieval based on similarity measures - p. 478 35. 14.2. SAR image change detection based on spatial coding and similarity - p. 528 36. Chapter 15. Hyperspectral image processing based on sparse learning and sparse graph - p. 559 37. 15.1. Hyperspectral image denoising based on hierarchical sparse learning - p. 560 38. 15.2. Hyperspectral image restoration based on hierarchical sparse Bayesian learning - p. 581 39. 15.3. Hyperspectral image dimensionality reduction using a sparse graph - p. 595 40. Chapter 16. Nonconvex compressed sensing framework based on block strategy and overcomplete dictionary - p. 617 41. Chapter 17. Sparse representation combined with fuzzy C-means (FCM) in compressed sensing - p. 629 42. Chapter 18. Compressed sensing by collaborative reconstruction - p. 669 43. Chapter 19. Hyperspectral image classification based on spectral information divergence and sparse representation - p. 693 44. Chapter 20. Neural network-based synthetic aperture radar image processing - p. 709 45. Chapter 21. Neural networks-based polarimetric SAR image classification - p. 723 46. Chapter 22. Deep neural network models for hyperspectral images - p. 735 47. Index - p. 749
