{"product_id":"learning-and-generalisation-with-applications-to-neural-networks-von-mathukumalli-vidyasagar","title":"Learning and Generalisation","description":"\n                                \n                \u003cp\u003e\n                                        \n                    \u003cem\u003eLearning and Generalization\u003c\/em\u003e\n                                         provides a formal mathematical theory addressing intuitive questions of the type: \n                \n                \u003c\/p\u003e\n                                \n                \n                \u003cp\u003e• How does a machine learn a concept on the basis of examples?\u003c\/p\u003e\n                                \n                \n                \u003cp\u003e• How can a neural network, after training, correctly predict the outcome of a previously unseen input?\u003c\/p\u003e\n                                \n                \n                \u003cp\u003e• How much training is required to achieve a given level of accuracy in the prediction?\u003c\/p\u003e\n                                \n                \n                \u003cp\u003e• How can one identify the dynamical behaviour of a nonlinear control system by observing its input-output behaviour over a finite time?\u003c\/p\u003e\n                                \n                \n                \u003cp\u003eThe second edition covers new areas including:\u003c\/p\u003e\n                                \n                \n                \u003cp\u003e• support vector machines;\u003c\/p\u003e\n                                \n                \n                \u003cp\u003e• fat-shattering dimensions and applications to neural network learning;\u003c\/p\u003e\n                                \n                \n                \u003cp\u003e• learning with dependent samples generated by a beta-mixing process;\u003c\/p\u003e\n                                \n                \n                \u003cp\u003e• connections between system identification and learning theory;\u003c\/p\u003e\n                                \n                \n                \u003cp\u003e• probabilistic solution of 'intractable problems' in robust control and matrix theory using randomized algorithms.\u003c\/p\u003e\n                                \n                \n                \u003cp\u003eIt also contains solutions to some of the open problems posed in the first edition, while adding new open problems. \u003c\/p\u003e\n                            \n            \u003cdiv class=\"aw-variant-hidden-subtitle-div\" id=\"aw-variant-subtitle-9781849968676\"\u003e\u003ch3\u003eWith Applications to Neural Networks\u003c\/h3\u003e\u003c\/div\u003e\u003cdiv class=\"aw-variant-hidden-subtitle-div\" id=\"aw-variant-subtitle-9781852333737\"\u003e\u003ch3\u003eWith Applications to Neural Networks\u003c\/h3\u003e\u003c\/div\u003e","brand":"Libri","offers":[{"title":"Softcover - 9781849968676","offer_id":39418406666333,"sku":"9781849968676","price":192.59,"currency_code":"EUR","in_stock":true},{"title":"Hardcover - 9781852333737","offer_id":51349936838,"sku":"9781852333737","price":192.59,"currency_code":"EUR","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0940\/0622\/files\/3b48da78-c5d1-4a43-b17b-84607a6832be.jpg?v=1778645216","url":"https:\/\/shop.autorenwelt.de\/en\/products\/learning-and-generalisation-with-applications-to-neural-networks-von-mathukumalli-vidyasagar","provider":"Autorenwelt Shop","version":"1.0","type":"link"}