Author name cluster

David Rumelhart

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

NeurIPS Conference 1993 Conference Paper

A Connectionist Model of the Owl's Sound Localization System

Daniel Rosen
David Rumelhart
Eric Knudsen

, ,"'e do not have a good understanding of how theoretical principles of learning are realized in neural systems. To address this problem we built a computational model of development in the owl's sound localization system. The structure of the model is drawn from known experimental data while the learning principles come from recent work in the field of brain style computation. The model accounts for numerous properties of the owl's sound localization system, makes specific and testable predictions for future experi(cid: 173) ments, and provides a theory of the developmental process.

PDF Details

NeurIPS Conference 1992 Conference Paper

Context-Dependent Multiple Distribution Phonetic Modeling with MLPs

Michael Cohen
Horacio Franco
Nelson Morgan
David Rumelhart
Victor Abrash

A number of hybrid multilayer perceptron (MLP)/hidden Markov model (HMM: ) speech recognition systems have been developed in recent years (Morgan and Bourlard. 1990). In this paper. we present a new MLP architecture and training algorithm which allows the modeling of context-dependent phonetic classes in a hybrid MLP/HMM: framework. The new training procedure smooths MLPs trained at different degrees of context dependence in order to obtain a robust estimate of the cootext-dependent probabilities. Tests with the DARPA Resomce Management database have shown substantial advantages of the context-dependent MLPs over earlier cootext(cid: 173) independent MLPs. and have shown substantial advantages of this hybrid approach over a pure HMM approach.

PDF Details

NeurIPS Conference 1991 Conference Paper

A Self-Organizing Integrated Segmentation and Recognition Neural Net

Jim Keeler
David Rumelhart

We present a neural network algorithm that simultaneously performs seg(cid: 173) mentation and recognition of input patterns that self-organizes to detect input pattern locations and pattern boundaries. We demonstrate this neu(cid: 173) ral network architecture on character recognition using the NIST database and report on results herein. The resulting system simultaneously seg(cid: 173) ments and recognizes touching or overlapping characters, broken charac(cid: 173) ters, and noisy images with high accuracy.

PDF Details

NeurIPS Conference 1990 Conference Paper

Generalization by Weight-Elimination with Application to Forecasting

Andreas Weigend
David Rumelhart
Bernardo Huberman

Inspired by the information theoretic idea of minimum description length, we add a term to the back propagation cost function that penalizes network complexity. We give the details of the procedure, called weight-elimination, describe its dynamics, and clarify the meaning of the parameters involved. From a Bayesian perspective, the complexity term can be usefully interpreted as an assumption about prior distribution of the weights. We use this procedure to predict the sunspot time series and the notoriously noisy series of currency exchange rates.

PDF Details

NeurIPS Conference 1990 Conference Paper

Integrated Segmentation and Recognition of Hand-Printed Numerals

James Keeler
David Rumelhart
Wee Leow

Neural network algorithms have proven useful for recognition of individ(cid: 173) ual, segmented characters. However, their recognition accuracy has been limited by the accuracy of the underlying segmentation algorithm. Con(cid: 173) ventional, rule-based segmentation algorithms encounter difficulty if the characters are touching, broken, or noisy. The problem in these situations is that often one cannot properly segment a character until it is recog(cid: 173) nized yet one cannot properly recognize a character until it is segmented. We present here a neural network algorithm that simultaneously segments and recognizes in an integrated system. This algorithm has several novel features: it uses a supervised learning algorithm (backpropagation), but is able to take position-independent information as targets and self-organize the activities of the units in a competitive fashion to infer the positional information. We demonstrate this ability with overlapping hand-printed numerals.

PDF Details