登入選單
返回Google圖書搜尋
Modular Learning in Neural Networks
Tomas Hrycej
其他書名
A Modularized Approach to Neural Network Classification
出版Wiley, 1992-10-09
主題Computers / Artificial Intelligence / GeneralComputers / Data Science / Neural NetworksTechnology & Engineering / Electrical
ISBN04715715479780471571544
URLhttp://books.google.com.hk/books?id=hbNQAAAAMAAJ&hl=&source=gbs_api
註釋This important new work recognizes the advanced nature of today's artificial neural networks, uniquely emphasizing a modular approach to neural network learning. By breaking down the learning task into relatively independent parts of lower complexity, Modular Learning in Neural Networks demonstrates how neural network learning can be made more powerful and efficient. The book's modular approach, unlike the monolithic viewpoint, admits intermediary solution stages whose success can be independently verified, as in other engineering fields. Each stage can be evaluated before moving on to the subsequent one, and the reason for possible failures can be analyzed, ultimately leading to the improved development and engineering of applications. The modular approach also takes into account growing network complexity, reducing the difficulty of such inevitable problems as scaling and convergence. Modular Learning in Neural Networks' modular approach is also fully in step with important psychological and neurobiological research. Studies in developmental psychology demonstrate the incremental nature of human learning, in which the success of each stage is conditioned by the successful accomplishment of the previous stage, while neurobiology has depicted the human brain as a complex structure of cooperating modules. Modular Learning in Neural Networks covers the full range of conceivable approaches to the modularization of learning, including decomposition of learning into modules using supervised and unsupervised learning types; decomposition of the function to be mapped into linear and nonlinear parts; decomposition of the neural network to minimize harmful interferences between a large number ofnetwork parameters during learning; decomposition of the application task into subtasks that are learned separately; decomposition into a knowledge-based part and a learning part. The book attempts to show that modular learning based on these approaches is helpful in improving the learning performance of neural networks. It demonstrates this by applying modular methods to a pair of benchmark cases - a medical classification problem of realistic size, encompassing 7,200 cases of thyroid disorder; and a handwritten digits classification problem, involving several thousand cases. In so doing, the book shows that some of the proposed methods lead to substantial improvements in solution quality and learning speed, as well as enhanced robustness with regard to learning control parameters. A refreshingly unique and highly practical new look at the problem-solving capabilities of neural networks, Modular Learning in Neural Networks will prompt scientific inquiry into the yet undiscovered relationships resulting from the integrative of learning modularization, and provide neural network application engineers with insight on how neural network technology can be made more controllable by the decomposition of application tasks.