S
Stephen I. Gallant
Researcher at Northeastern University
Publications - 45
Citations - 3401
Stephen I. Gallant is an academic researcher from Northeastern University. The author has contributed to research in topics: Expert system & Artificial neural network. The author has an hindex of 17, co-authored 44 publications receiving 3298 citations. Previous affiliations of Stephen I. Gallant include Pitney Bowes.
Papers
More filters
Book
Neural network learning and expert systems
TL;DR: This text and reference provides a systematic development of neural network learning algorithms from a computational perspective, coupled with an extensive exploration of Neural Network expert systems which shows how the power of neuralnetwork learning can be harnessed to generate expert systems automatically.
Journal ArticleDOI
Connectionist expert systems
TL;DR: Connectionist networks can be used as expert system knowledge bases and can be constructed from training examples by machine learning techniques, giving a way to automate the generation of expert systems for classification problems.
Journal ArticleDOI
Perceptron-based learning algorithms
TL;DR: The heart of these algorithms is the pocket algorithm, a modification of perceptron learning that makes perceptronLearning well-behaved with nonseparable training data, even if the data are noisy and contradictory.
Patent
Methods for generating or revising context vectors for a plurality of word stems
TL;DR: In this article, a method for generating context vectors for use in a document storage and retrieval system is presented, where a context vector is a fixed length list of component values generated to approximate conceptual relationships.
Patent
Method for document retrieval and for word sense disambiguation using neural networks
TL;DR: In this article, a dictionary of context vectors provides a context vector for each word stem in the dictionary, and a normalized summary vector is stored for each document by combining the context vectors of the words remaining in the document after uninteresting words are removed.