L
Lawrence K. Saul
Researcher at University of California, San Diego
Publications - 138
Citations - 40154
Lawrence K. Saul is an academic researcher from University of California, San Diego. The author has contributed to research in topics: Hidden Markov model & Nonlinear dimensionality reduction. The author has an hindex of 49, co-authored 133 publications receiving 37255 citations. Previous affiliations of Lawrence K. Saul include Massachusetts Institute of Technology & University of Pennsylvania.
Papers
More filters
The Shrinkage-Delinkage Trade-off: An Analysis of Factorized Gaussian Approximations for Variational Inference
TL;DR: In this article , the authors consider the trade-off between the componentwise variance and the entropy of a factorized approximation of a Gaussian and a non-Gaussian distribution.
Journal Article
A geometrical connection between sparse and low-rank matrices and its application to manifold learning
TL;DR: In this article , a generalized low-rank decomposition of sparse matrices is proposed, which can be encoded by a neural network with one layer of rectified linear units and can be viewed as a layerwise primitive for deep learning.
Journal ArticleDOI
An EM Algorithm for Capsule Regression.
TL;DR: This letter studies the problem of capsule regression—a higher-dimensional analog of logistic, probit, and softmax regression in which class probabilities are derived from vectors of competing magnitude, and proposes a simple capsule architecture for multinomial classification.
Proceedings Article
Modeling the rate of speech by Markov processes on curves.
Lawrence K. Saul,Mazin G. Rahim +1 more
TL;DR: A statistical model for automatic speech recognition that relates variations in speaking rate to nonlinear warpings of time is proposed and it is shown that Markov processes on curves yield lower word error rates than comparably trained hid-ers.
Patent
Automatic speech recognition using multi-dimensional curve-linear representations
TL;DR: In this paper, a method and apparatus for speech recognition using Markov processes on curves is presented, which operate such that input speech utterances are received and represented as multidimensional curves.