Showing papers by "Sebastian Thrun published in 1995"
Proceedings Article•
27 Nov 1995TL;DR: It is shown that across the board, lifelong learning approaches generalize consistently more accurately from less training data, by their ability to transfer knowledge across learning tasks.
Abstract: This paper investigates learning in a lifelong context. Lifelong learning addresses situations in which a learner faces a whole stream of learning tasks. Such scenarios provide the opportunity to transfer knowledge across multiple learning tasks, in order to generalize more accurately from less training data. In this paper, several different approaches to lifelong learning are described, and applied in an object recognition domain. It is shown that across the board, lifelong learning approaches generalize consistently more accurately from less training data, by their ability to transfer knowledge across learning tasks.
474 citations
TL;DR: The major components of the RHINO control software as they were exhibited at the AAAI Robot Competition and Exhibition are described and the basic philosophy of theRHINO architecture is sketched.
Abstract: Rhino was the University of Bonn's entry in the 1994 AAAI Robot Competition and Exhibition. rhino is a mobile robot designed for indoor navigation and manipulation tasks. The general scientific goal of the rhino project is the development and the analysis of autonomous and complex learning systems. This article briefly describes the major components of the rhino control software as they were exhibited at the competition. It also sketches the basic philosophy of the rhino architecture and discusses some of the lessons that we learned during the competition.
206 citations
TL;DR: This paper describes an approach to learning an indoor robot navigation task through trial-and-error using the explanation-based neural network learning algorithm EBNN, which allows the robot to learn control using dynamic programming.
83 citations
01 Nov 1995
TL;DR: This paper investigates learning in a lifelong context where a learner faces a stream of learning tasks and proposes and evaluates several approaches to lifelong learning that generalize consistently more accurately from scarce training data than comparable "single-task" approaches.
Abstract: : Machine learning has not yet succeeded in the design of robust learning algorithms that generalize well from very small datasets. In contrast, humans often generalize correctly from only a single training example, even if the number of potentially relevant features is large. To do so, they successfully exploit knowledge acquired in previous learning tasks, to bias subsequent learning. This paper investigates learning in a lifelong context. Lifelong learning addresses situations where a learner faces a stream of learning tasks. Such scenarios provide the opportunity for synergetic effects that arise if knowledge is transferred across multiple learning tasks. To study the utility of transfer, several approaches to lifelong learning are proposed and evaluated in an object recognition domain. It is shown that all these algorithms generalize consistently more accurately from scarce training data than comparable "single-task" approaches.
46 citations