David A. Cohn

Learn More
Active learning differs from “learning from examples” in that the learning algorithm assumes at least some control over what part of the input domain it receives information about. In some situations, active learning is provably more powerful than learning from examples alone, giving better generalization for a fixed number of training examples. In this(More)
We describe a joint probabilistic model for modeling the contents and inter-connectivity of document collections such as sets of web pages or research paper archives. The model is based on a probabilistic factor decomposition and allows identifying principal topics of the collection as well as authoritative documents within those topics. Furthermore, the(More)
Consider the problem of learning input/output mappings through exploration, e.g. learning the kinematics or dynamics of a robotic manipulator. If actions are expensive and computation is cheap, then we should explore by selecting a trajectory through the input space which gives us the most amount of information in the fewest number of steps. I discuss how(More)
"Selective sampling" is a form of directed search that can greatly increase the ability of a connectionist network to generalize accurately. Based on information from previous batches of samples, a network may be trained on data selectively sampled from regions in the domain that are unknown. This is realizable in cases when the distribution is known, or(More)
I describe a querying criterion that attempts to minimize the error of a learner by minimizing its estimated squared bias. I describe experiments with locally-weighted regression on two simple problems, and observe that this "bias-only" approach outperforms the more common "variance-only" exploration approach, even in the presence of noise.
Gerald Tesauro IBM Watson Research Center P.O. Box 704 Yorktown Heights, NY 10598 \Ve describe a series of careful llumerical experiments which measure the average generalization capability of neural networks trained on a variety of simple functions. These experiments are designed to test whether average generalization performance can surpass the worst-case(More)
Antibody responses to two structurally different pneumococcal polysaccharides, type 3 (SIII) and type 14 (SXIV), were examined in intact and splenectomized (Sx) A/J mice to determine whether the role of the spleen in immune responses to these antigens varies with respect to the dosage, the antigenic structure, or the interval between immunization and assay.(More)
The barriers to oral delivery of the hydrophilic zwitterion L-767, 679 (I) and its carboxyl ester prodrug L-775,318 (II) were examined. In the Caco-2 cell model, transport of II, but not I, was strongly oriented in the secretory direction. The basal-to-apical transport of II displayed saturable kinetics and was markedly inhibited by verapamil and quinidine,(More)