Learn More
One of the surprising recurring phenomena observed in experiments with boosting is that the test error of the generated classifier usually does not increase as its size becomes very large, and often is observed to decrease even after the training error reaches zero. In this paper, we show that this phenomenon is related to the distribution of margins of the(More)
— Motion planning in uncertain and dynamic environments is an essential capability for autonomous robots. Partially observable Markov decision processes (POMDPs) provide a principled mathematical framework for solving such problems, but they are often avoided in robotics due to high computational complexity. Our goal is to create practical POMDP algorithms(More)
This paper studies the problem of building text classifiers using positive and unlabeled examples. The key feature of this problem is that there is no negative example for learning. Recently, a few techniques for solving this problem were proposed in the literature. These techniques are based on the same idea, which builds a classifier in two steps. Each(More)
We investigate the following problem: Given a set of documents of a particular topic or class È , and a large set Å of mixed documents that contains documents from class È and other types of documents, identify the documents from class È in Å. The key feature of this problem is that there is no labeled non-È document, which makes traditional machine(More)
Partially observable Markov decision processes (POMDPs) provide a principled, general framework for robot motion planning in uncertain and dynamic environments. They have been applied to various robotic tasks. However, solving POMDPs exactly is computationally intractable. A major challenge is to scale up POMDP algorithms for complex robotic tasks. Robotic(More)
We show that the class of two layer neural networks with bounded fan-in is eeciently learn-able in a realistic extension to the Probably Approximately Correct (PAC) learning model. In this model, a joint probability distribution is assumed to exist on the observations and the learner is required to approximate the neural network which minimizes the expected(More)
In this paper, we present an algorithm for learning a generative model of natural language sentences together with their formal meaning representations with hierarchical structures. The model is applied to the task of mapping sentences to hierarchical representations of their underlying meaning. We introduce dynamic programming techniques for efficient(More)
The problem of learning with positive and unla-beled examples arises frequently in retrieval applications. We transform the problem into a problem of learning with noise by labeling all unla-beled examples as negative and use a linear function to learn from the noisy examples. To learn a linear function with noise, we perform logistic regression after(More)