David E. Rumelhart’s research while affiliated with Stanford University and other places

Fourteen rhesus monkeys and two human Os were trained to discriminate between identical blocks of wood placed 13 in apart, using cues that were provided by a pointer that was placed at random in positions spaced 1.0 in apart between the manipulanda. Monkeys made increasingly more errors as a function of increasing distance between the manipulandum and discriminandum, and extensive practice did not alter this relationship. The human Os, however, made no errors at positions of the pointer other than the center.

multiple simultaneous constraints parallel distributed processing [PDP] / examples of PDP models representation and learning in PDP models origins of parallel distributed processing (PsycINFO Database Record (c) 2012 APA, all rights reserved)

Computational modeling plays a central role in cognitive science. This book provides a comprehensive introduction to computational models of human cognition. It covers major approaches and architectures, both neural network and symbolic; major theoretical issues; and specific computational models of a variety of cognitive processes, ranging from low-level (e.g., attention and memory) to higher-level (e.g., language and reasoning). The articles included in the book provide original descriptions of developments in the field. The emphasis is on implemented computational models rather than on mathematical or nonformal approaches, and on modeling empirical data from human subjects. Bradford Books imprint

We discuss the development of a neural network for facial expression recognition. It aims at recognizing and interpreting facial expressions in terms of signaled emotions and level of expressiveness. We use the backpropagation algorithm to train the system to differentiate between facial expressions. We show how the network generalizes to new faces and we analyze the results. In our approach, we acknowledge that facial expressions can be very subtle, and propose strategies to deal with the complexity of various levels of expressiveness. Our database includes a variety of different faces, including individuals of different gender, race, and including different features such as glasses, mustache, and beard. Even given the variety of the database, the network learns fairly succesfully to distinguish various levels of expressiveness, and generalizes on new faces as well. Introduction Within the field of computer vision, there has recently been an increasing interest to rec...

e present a speaker-independent, continuous-speech recog- ( nition system based on a hybrid multilayer perceptron MLP)/hidden Markov model (HMM). The system come bines the advantages of both approaches by using MLPs to stimate the state-dependent observation probabilities of an e p HMM. New MLP architectures and training procedures ar resented that allow the modeling of multiple distributions . C for phonetic classes and context-dependent phonetic classes omparisons with a pure HMM system illustrate advantages n of the hybrid approach both in recognition accuracy and in umber of parameters required. N H 1. INTRODUCTIO idden Markov models (HMMs) are used in most state-ofa the-art continuous-speech recognition systems. This pproach is limited by the need for strong statistical assumpu tions that are unlikely to be valid for speech. Techniques sing multilayer perceptrons (MLPs) for probability estimaa tion have recently been introduced [1], which reduce the ssumption of independen...

arlier hybrid multilayer perceptron (MLP)/hidden Markov model (HMM) continuous speech recognition sysr g tems have not modeled context-dependent phonetic effects, sequences of distributions for phonetic models, o ender-based speech consistencies. In this paper we present a new MLP architecture and training procedure for t " modeling context-dependent phonetic classes with a sequence of distributions. A new training procedure tha smooths" networks with different degrees of context-dependence is proposed in order to obtain a robust estip mate of the context-dependent probabilities. We have used this new architecture to model generalized biphone honetic contexts. Tests with the speaker-independent DARPA Resource Management database have shown d w average reductions in word error rates of 20% in both the word-pair grammar and no-grammar cases, compare ith our earlier context-independent MLP/HMM hybrid. P 1. Introduction revious work by Morgan, Bourlard, et al. [1, 2] has shown both the...

n M In this paper we present a hybrid multilayer perceptron (MLP)/hidde arkov model (HMM) speaker-independent continuous-speech recognib tion system, in which the advantages of both approaches are combined y using MLPs to estimate the state-dependent observation probabilities p of an HMM. New MLP architectures and training procedures are resented which allow the modeling of multiple distributions for phonetic a p classes and context-dependent phonetic classes. Comparisons with ure HMM system illustrate advantages of the hybrid approach both in terms of recognition accuracy and number of parameters required. 1. INTRODUCTION - o Hidden Markov models (HMMs) are used in most current state f-the-art continuous-speech recognition systems. This approach is u limited by the need for strong statistical assumptions that are nlikely to be valid for speech. Techniques using multilayer peri ceptrons (MLPs) for probability estimation have recently been ntroduced [1] which reduce the assumption o...

In this paper we present a training method and a network architecture for estimating contextdependent observation probabilities in the framework of a hybrid hidden Markov model (HMM) / multi layer perceptron (MLP) speaker-independent continuous speech recognition system. The context-dependent modeling approach we present here computes the HMM context-dependent observation probabilities using a Bayesian factorization in terms of context-conditioned posterior phone probabilities which are computed with a set of MLPs, one for every relevant context. The proposed network architecture shares the input-to-hidden layer among the set of context-dependent MLPs in order to reduce the number of independent parameters. Multiple states for phone models with different context dependence for each state are used to model the different context effects at the beginning and end of phonetic segments. A new training procedure that "smooths" networks with different degrees of context-dependence is proposed ...