By Sebastian Thrun
Lifelong studying addresses events during which a learner faces a chain of other studying projects delivering the chance for synergy between them. Explanation-based neural community studying (EBNN) is a desktop studying set of rules that transfers wisdom throughout a number of studying initiatives. while confronted with a brand new studying activity, EBNN exploits area wisdom gathered in past studying initiatives to consultant generalization within the new one. consequently, EBNN generalizes extra competently from much less facts than similar tools. Explanation-Based Neural community studying: A Lifelong Learning Approach describes the fundamental EBNN paradigm and investigates it within the context of supervised studying, reinforcement studying, robotics, and chess.
`The paradigm of lifelong studying - utilizing previous realized wisdom to enhance next studying - is a promising course for a brand new iteration of desktop studying algorithms. Given the necessity for extra actual studying equipment, it's tough to visualize a destiny for computer studying that doesn't comprise this paradigm.'
From the Foreword by means of Tom M. Mitchell.
Read or Download Explanation-Based Neural Network Learning: A Lifelong Learning Approach (The Springer International Series in Engineering and Computer Science) PDF
Similar Artificial Intelligence books
This consultant covers the fundamentals of clinical and engineering conversation, together with defining an viewers, operating with collaborators, looking the literature, organizing and drafting files, constructing snap shots, and documenting resources. The records coated contain memos, letters, proposals, growth experiences, different sorts of stories, magazine articles, oral displays, directions, and CVs and resumes.
The current paintings is a continuation of the authors' acclaimed multi-volume APractical good judgment of Cognitive platforms. After having investigated the thought ofrelevance of their earlier quantity, Gabbay and Woods now flip to abduction. Inthis hugely unique strategy, abduction is construed as ignorance-preservinginference, during which conjecture performs a pivotal position.
Jason is an Open resource interpreter for a longer model of AgentSpeak – a logic-based agent-oriented programming language – written in Java™. It permits clients to construct advanced multi-agent structures which are able to working in environments formerly thought of too unpredictable for desktops to address.
The sensible advantages of computational common sense don't need to be restricted to arithmetic and computing. As this booklet indicates, usual humans of their daily lives can cash in on the hot advances which were built for man made intelligence. The booklet attracts upon similar advancements in quite a few fields from philosophy to psychology and legislations.
Additional info for Explanation-Based Neural Network Learning: A Lifelong Learning Approach (The Springer International Series in Engineering and Computer Science)