Share This Author
Bayesian community-wide culture-independent microbial source tracking
SourceTracker, a Bayesian approach to estimate the proportion of contaminants in a given community that come from possible source environments, is presented, and microbial surveys from neonatal intensive care units, offices and molecular biology laboratories are applied.
The Neural Network House: An Environment that Adapts to its Inhabitants
- M. Mozer
Although the prospect of computerized homes has a long history, ho/ne automation has never become terribly popular because the benefits are seldom seen to outweigh the costs. One significant cost of…
Optimizing Classifier Performance via an Approximation to the Wilcoxon-Mann-Whitney Statistic
This work proposes an objective function that is an approximation to the Wilcoxon-Mann-Whitney statistic, which is equivalent to the AUC, and applies it to real-world customer behavior prediction problems for a wireless service provider and a cable service provider, and achieves reliable improvements in the ROC curve.
Learning Deep Disentangled Embeddings with the F-Statistic Loss
A new paradigm for discovering disentangled representations of class structure is proposed and a novel loss function based on the $F$ statistic is proposed, which describes the separation of two or more distributions.
Skeletonization: A Technique for Trimming the Fat from a Network via Relevance Assessment
The basic idea is to iteratively train the network to a certain performance criterion, compute a measure of relevance that identifies which input or hidden units are most critical to performance, and automatically trim the least relevant units.
Predicting subscriber dissatisfaction and improving retention in the wireless telecommunications industry
- M. Mozer, R. Wolniewicz, D. Grimes, Eric Johnson, Howard Kaushansky
- Computer ScienceIEEE Trans. Neural Networks Learn. Syst.
- 1 May 2000
These experiments show that under a wide variety of assumptions concerning the cost of intervention and the retention rate resulting from intervention, using predictive techniques to identify potential churners and offering incentives can yield significant savings to a carrier.
Optimizing distributed practice: theoretical analysis and practical implications.
- N. Cepeda, Noriko Coburn, D. Rohrer, J. Wixted, M. Mozer, H. Pashler
- PsychologyExperimental psychology
- 13 May 2009
Both studies demonstrated nonmonotonic gap effects: Increases in gap caused test accuracy to initially sharply increase and then gradually decline, which provides new constraints on theories of spacing and confirms the importance of cumulative reviews to promote retention over meaningful time periods.
A Focused Backpropagation Algorithm for Temporal Pattern Recognition
- M. Mozer
- Computer ScienceComplex Syst.
A specialized connectionist architecture and corre sponding specialization of the backpropagation learnin g algori thm th at opera tes efficiently on temporal sequences is introduced and should scale better than conventional recurrent architectures wit h respect to sequenc e length.
Neural Network Music Composition by Prediction: Exploring the Benefits of Psychoacoustic Constraints and Multi-scale Processing
- M. Mozer
- Computer ScienceConnect. Sci.
An extension of this transition-table approach is described, using a recurrent autopredictive connectionist network called CONCERT, which is trained on a set of pieces with the aim of extracting stylistic regularities and incorporation of psychologically grounded representations of pitch, duration and harmonic structure.
Perception of multiple objects - a connectionist approach
- M. Mozer
- PsychologyNeural network modeling and connectionism
- 17 June 1991
The model, called MORSEL, is unique in providing a broad and unified explanation for a wide range of experimental psychological data on visual perception and attention, and draws on existing theoretical perspectives from cognitive psychology.