Titlebook: Explanation-Based Neural Network Learning; A Lifelong Learning Sebastian Thrun Book 1996 Kluwer Academic Publishers 1996 algorithms.artifi

CREST

https://doi.org/10.1007/978-3-662-07703-0s over its entire lifetime. If these tasks are appropriately related, knowledge learned in the first . - 1 tasks can be transferred to the .-th task to boost the generalization accuracy. Two special cases of lifelong learning problems have been investigated in this book: lifelong supervised learning

BRIBE

揉杂

A. Gottstein,A. Schlossmann,R. Volkns. EBNN analyzes training examples using the invariance network, in order to guide generalization when learning a new function. As will be illustrated, knowing the invariances of the domain can be most instrumental for successful learning if training data is scarce.

ARM

The Invariance Approach,ns. EBNN analyzes training examples using the invariance network, in order to guide generalization when learning a new function. As will be illustrated, knowing the invariances of the domain can be most instrumental for successful learning if training data is scarce.

增长

苦恼

indifferent

climax

Foolproof

Discussion, and lifelong control learning. In both cases, lifelong learning involves learning at a meta-level, in which whole spaces of appropriate base-level hypotheses are considered. Consequently, learning at the meta-level requires different representations than base-level learning.

航海太平洋