Instance-Based Learning Algorithms
TLDR
This paper describes how storage requirements can be significantly reduced with, at most, minor sacrifices in learning rate and classification accuracy and extends the nearest neighbor algorithm, which has large storage requirements.Abstract:
Storing and using specific instances improves the performance of several supervised learning algorithms. These include algorithms that learn decision trees, classification rules, and distributed networks. However, no investigation has analyzed algorithms that use only specific instances to solve incremental learning tasks. In this paper, we describe a framework and methodology, called instance-based learning, that generates classification predictions using only specific instances. Instance-based learning algorithms do not maintain a set of abstractions derived from specific instances. This approach extends the nearest neighbor algorithm, which has large storage requirements. We describe how storage requirements can be significantly reduced with, at most, minor sacrifices in learning rate and classification accuracy. While the storage-reducing algorithm performs well on several real-world databases, its performance degrades rapidly with the level of attribute noise in training instances. Therefore, we extended it with a significance test to distinguish noisy instances. This extended algorithm's performance degrades gracefully with increasing noise levels and compares favorably with a noise-tolerant decision tree algorithm.read more
Citations
More filters
Journal ArticleDOI
Identifying and Handling Mislabelled Instances
TL;DR: A new approach is offered which deals with improving classification accuracies by using a preliminary filtering procedure which is finally compared to the relaxation relabelling schema.
Proceedings ArticleDOI
Digging Digg: Comment Mining, Popularity Prediction, and Social Network Analysis
Salman Jamali,Huzefa Rangwala +1 more
TL;DR: Using comment information available from Digg, a co-participation network between users is defined, and an entropy measure is inferred to infer that users at Digg are not highly focused and participate across a wide range of topics.
Journal ArticleDOI
Probabilistic feature relevance learining for content-based image retrieval
Jing Peng,Bir Bhanu,Shan Qing +2 more
TL;DR: A novel probabilistic method is presented that enables image retrieval procedures to automatically capture feature relevance based on user's feedback and that is highly adaptive to query locations.
Patent
Document-classification system, method and software
TL;DR: This article presented a graphical user interface that concurrently displays an unclassified headnote, a ranked list of candidate classes, a candidate class in combination with adjacent classes of the classification system, and at least one classified headnote associated with one of the candidate classes.
Proceedings ArticleDOI
Decision tree and instance-based learning for label ranking
TL;DR: New methods for label ranking are introduced that complement and improve upon existing approaches and are extensions of two methods that have been used extensively for classification and regression so far, namely instance-based learning and decision tree induction.
References
More filters
Journal ArticleDOI
Classification and Regression Trees.
Journal ArticleDOI
Induction of Decision Trees
TL;DR: In this paper, an approach to synthesizing decision trees that has been used in a variety of systems, and it describes one such system, ID3, in detail, is described, and a reported shortcoming of the basic algorithm is discussed.
MonographDOI
Parallel Distributed Processing: Explorations in the Microstructure of Cognition: Foundations
Book
Classification and regression trees
TL;DR: The methodology used to construct tree structured rules is the focus of a monograph as mentioned in this paper, covering the use of trees as a data analysis method, and in a more mathematical framework, proving some of their fundamental properties.
Journal ArticleDOI
Nearest neighbor pattern classification
Thomas M. Cover,Peter E. Hart +1 more
TL;DR: The nearest neighbor decision rule assigns to an unclassified sample point the classification of the nearest of a set of previously classified points, so it may be said that half the classification information in an infinite sample set is contained in the nearest neighbor.