Showing papers by "Thomas G. Dietterich published in 1993"

Locally Adaptive Nearest Neighbor Algorithms

Abstract: Four versions of a k-nearest neighbor algorithm with locally adaptive k are introduced and compared to the basic k-nearest neighbor algorithm (kNN). Locally adaptive kNN algorithms choose the value of k that should be used to classify a query by consulting the results of cross-validation computations in the local neighborhood of the query. Local kNN methods are shown to perform similar to kNN in experiments with twelve commonly used data sets. Encouraging results in three constructed tasks show that local methods can significantly outperform kNN in specific applications. Local methods can be recommended for on-line learning and for applications where different regions of the input space are covered by patterns solving different sub-tasks.

A Comparison of Dynamic Reposing and Tangent Distance for Drug Activity Prediction

Abstract: In drug activity prediction (as in handwritten character recognition), the features extracted to describe a training example depend on the pose (location, orientation, etc.) of the example. In handwritten character recognition, one of the best techniques for addressing this problem is the tangent distance method of Simard, LeCun and Denker (1993). Jain, et al. (1993a; 1993b) introduce a new technique-dynamic reposing--that also addresses this problem. Dynamic reposing iteratively learns a neural network and then reposes the examples in an effort to maximize the predicted output values. New models are trained and new poses computed until models and poses converge. This paper compares dynamic reposing to the tangent distance method on the task of predicting the biological activity of musk compounds. In a 20-fold cross-validation, dynamic reposing attains 91% correct compared to 79% for the tangent distance method, 75% for a neural network with standard poses, and 75% for the nearest neighbor method.

Memory-Based Methods for Regression and Classification

Abstract: Memory-based learning methods operate by storing all (or most) of the training data and deferring analysis of that data until "run time" (i.e., when a query is presented and a decision or prediction must be made). When a query is received, these methods generally answer the query by retrieving and analyzing a small subset of the training data--namely, data in the immediate neighborhood of the query point. In short, memory-based methods are "lazy" (they wait until the query) and "local" (they use only a local neighborhood). The purpose of this workshop was to review the state-of-the-art in memory-based methods and to understand their relationship to "eager" and "global" learning algorithms such as batch backpropagation.