Results 1 -
4 of
4
Learning Locomotion over Rough Terrain using Terrain Templates
"... Abstract — We address the problem of foothold selection in robotic legged locomotion over very rough terrain. The difficulty of the problem we address here is comparable to that of human rock-climbing, where foot/hand-hold selection is one of the most critical aspects. Previous work in this domain t ..."
Abstract
-
Cited by 6 (1 self)
- Add to MetaCart
Abstract — We address the problem of foothold selection in robotic legged locomotion over very rough terrain. The difficulty of the problem we address here is comparable to that of human rock-climbing, where foot/hand-hold selection is one of the most critical aspects. Previous work in this domain typically involves defining a reward function over footholds as a weighted linear combination of terrain features. However, a significant amount of effort needs to be spent in designing these features in order to model more complex decision functions, and hand-tuning their weights is not a trivial task. We propose the use of terrain templates, which are discretized height maps of the terrain under a foothold on different length scales, as an alternative to manually designed features. We describe an algorithm that can simultaneously learn a small set of templates and a foothold ranking function using these templates, from expertdemonstrated footholds. Using the LittleDog quadruped robot, we experimentally show that the use of terrain templates can produce complex ranking functions with higher performance than standard terrain features, and improved generalization to unseen terrain. I.
Sublinear Optimization for Machine Learning
"... Abstract—We give sublinear-time approximation algorithms for some optimization problems arising in machine learning, such as training linear classifiers and finding minimum enclosing balls. Our algorithms can be extended to some kernelized versions of these problems, such as SVDD, hard margin SVM, a ..."
Abstract
-
Cited by 4 (2 self)
- Add to MetaCart
Abstract—We give sublinear-time approximation algorithms for some optimization problems arising in machine learning, such as training linear classifiers and finding minimum enclosing balls. Our algorithms can be extended to some kernelized versions of these problems, such as SVDD, hard margin SVM, and L2-SVM, for which sublinear-time algorithms were not known before. These new algorithms use a combination of a novel sampling techniques and a new multiplicative update algorithm. We give lower bounds which show the running times of many of our algorithms to be nearly best possible in the unitcost RAM model. We also give implementations of our algorithms in the semi-streaming setting, obtaining the first low pass polylogarithmic space and sublinear time algorithms achieving arbitrary approximation factor. I.
LEARNING TO CRAWL: CLASSIFIER-GUIDED TOPICAL CRAWLERS
, 2004
"... Topical or focused crawlers follow the hyperlinked structure of the Web guided by the scent of information to identify and harvest topically relevant pages. For sniff-ing the appropriate scent they mine the content of pages that are already fetched to prioritize the fetching of unvisited pages. Topi ..."
Abstract
- Add to MetaCart
Topical or focused crawlers follow the hyperlinked structure of the Web guided by the scent of information to identify and harvest topically relevant pages. For sniff-ing the appropriate scent they mine the content of pages that are already fetched to prioritize the fetching of unvisited pages. Topical crawling is currently a young and creative area of research that holds the promise of benefiting from several sophisti-cated data mining techniques. Sporadically, the use of classification algorithms to guide topical crawlers has been suggested in the literature. No systematic study, however, has been done on their relative merits. Using the lessons learned from our previous crawler evaluation studies, we experiment with multiple versions of different classification schemes. We also explore the effects of various techniques for deriving contexts of hyperlinks on crawling performance. The crawling process is modeled as a parallel best-first search over a graph defined by the Web. The classifiers pro-vide heuristics to the crawler thus biasing it towards certain portions of the graph (i.e., the Web). We have designed and developed a crawling framework that allows
A NOTE ON A LARGE MARGIN PERCEPTRON ALGORITHM
- INFORMATION TECHNOLOGY AND CONTROL, 2006, VOL.35, NO.3A
, 2006
"... The importance of classification algorithms in the context of risk assessment is briefly explained. As an alternative to the popular support vector machines fault tolerant perceptron learning is suggested. In order to achieve better generalization properties the additional use of an iterative large ..."
Abstract
- Add to MetaCart
The importance of classification algorithms in the context of risk assessment is briefly explained. As an alternative to the popular support vector machines fault tolerant perceptron learning is suggested. In order to achieve better generalization properties the additional use of an iterative large margin perceptron algorithm is investigated. In particular it is shown that care has to be taken when initializing the algorithm. Some preliminary experimental results are briefly discussed.

