Author name cluster

Clay Spence

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.

8 papers

1 author row

NeurIPS Conference 2000 Conference Paper

Higher-Order Statistical Properties Arising from the Non-Stationarity of Natural Signals

Lucas Parra
Clay Spence
Paul Sajda

We present evidence that several higher-order statistical proper(cid: 173) ties of natural images and signals can be explained by a stochastic model which simply varies scale of an otherwise stationary Gaus(cid: 173) sian process. We discuss two interesting consequences. The first is that a variety of natural signals can be related through a com(cid: 173) mon model of spherically invariant random processes, which have the attractive property that the joint densities can be constructed from the one dimensional marginal. The second is that in some cas(cid: 173) es the non-stationarity assumption and only second order methods can be explicitly exploited to find a linear basis that is equivalent to independent components obtained with higher-order methods. This is demonstrated on spectro-temporal components of speech.

PDF Details

NeurIPS Conference 1999 Conference Paper

Hierarchical Image Probability (H1P) Models

Clay Spence
Lucas Parra

We formulate a model for probability distributions on image spaces. We show that any distribution of images can be factored exactly into condi(cid: 173) tional distributions of feature vectors at one resolution (pyramid level) conditioned on the image information at lower resolutions. We would like to factor this over positions in the pyramid levels to make it tractable, but such factoring may miss long-range dependencies. To fix this, we in(cid: 173) troduce hidden class labels at each pixel in the pyramid. The result is a hierarchical mixture of conditional probabilities, similar to a hidden Markov model on a tree. The model parameters can be found with max(cid: 173) imum likelihood estimation using the EM algorithm. We have obtained encouraging preliminary results on the problems of detecting various ob(cid: 173) jects in SAR images and target recognition in optical aerial images.

PDF Details

NeurIPS Conference 1999 Conference Paper

Unmixing Hyperspectral Data

Lucas Parra
Clay Spence
Paul Sajda
Andreas Ziehe
Klaus-Robert Müller

In hyperspectral imagery one pixel typically consists of a mixture of the reflectance spectra of several materials, where the mixture coefficients correspond to the abundances of the constituting ma(cid: 173) terials. We assume linear combinations of reflectance spectra with some additive normal sensor noise and derive a probabilistic MAP framework for analyzing hyperspectral data. As the material re(cid: 173) flectance characteristics are not know a priori, we face the problem of unsupervised linear unmixing. The incorporation of different prior information (e. g. positivity and normalization of the abun(cid: 173) dances) naturally leads to a family of interesting algorithms, for example in the noise-free case yielding an algorithm that can be understood as constrained independent component analysis (ICA). Simulations underline the usefulness of our theory.

PDF Details

NeurIPS Conference 1998 Conference Paper

Applications of Multi-Resolution Neural Networks to Mammography

Clay Spence
Paul Sajda

We have previously presented a coarse-to-fine hierarchical pyra(cid: 173) mid/neural network (HPNN) architecture which combines multi(cid: 173) scale image processing techniques with neural networks. In this paper we present applications of this general architecture to two problems in mammographic Computer-Aided Diagnosis (CAD). The first application is the detection of microcalcifications. The <: oarse-to-fine HPNN was designed to learn large-scale context in(cid: 173) formation for detecting small objects like microcalcifications. Re(cid: 173) ceiver operating characteristic (ROC) analysis suggests that the hierarchical architecture improves detection performance of a well established CAD system by roughly 50 %. The second application is to detect mammographic masses directly. Since masses are large, extended objects, the coarse-to-fine HPNN architecture is not suit(cid: 173) able for this problem. Instead we construct a fine-to-coarse HPNN architecture which is designed to learn small-scale detail structure associated with the extended objects. Our initial results applying the fine-to-coarse HPNN to mass detection are encouraging, with detection performance improvements of about 36 %. We conclude that the ability of the HPNN architecture to integrate information across scales, both coarse-to-fine and fine-to-coarse, makes it well suited for detecting objects which may have contextual clues or detail structure occurring at scales other than the natural scale of the object.

PDF Details

NeurIPS Conference 1994 Conference Paper

Coarse-to-Fine Image Search Using Neural Networks

Clay Spence
John Pearson
Jim Bergen

The efficiency of image search can be greatly improved by using a coarse-to-fine search strategy with a multi-resolution image representa(cid: 173) tion. However, if the resolution is so low that the objects have few dis(cid: 173) tinguishing features, search becomes difficult. We show that the performance of search at such low resolutions can be improved by using context information, i. e. , objects visible at low-resolution which are not the objects of interest but are associated with them. The networks can be given explicit context information as inputs, or they can learn to detect the context objects, in which case the user does not have to be aware of their existence. We also use Integrated Feature Pyramids, which repre(cid: 173) sent high-frequency information at low resolutions. The use of multi(cid: 173) resolution search techniques allows us to combine information about the appearance of the objects on many scales in an efficient way. A natural fOlm of exemplar selection also arises from these techniques. We illus(cid: 173) trate these ideas by training hierarchical systems of neural networks to find clusters of buildings in aerial photographs of farmland.

PDF Details

NeurIPS Conference 1990 Conference Paper

Applications of Neural Networks in Video Signal Processing

John Pearson
Clay Spence
Ronald Sverdlove

Although color TV is an established technology, there are a number of longstanding problems for which neural networks may be suited. Impulse noise is such a problem, and a modular neural network approach is pre(cid: 173) sented in this paper. The training and analysis was done on conventional computers, while real-time simulations were performed on a massively par(cid: 173) allel computer called the Princeton Engine. The network approach was compared to a conventional alternative, a median filter. Real-time simula(cid: 173) tions and quantitative analysis demonstrated the technical superiority of the neural system. Ongoing work is investigating the complexity and cost of implementing this system in hardware. 1 THE POTENTIAL FOR NEURAL NETWORKS IN CONSUMER ELECTRONICS Neural networks are most often considered for application in emerging new tech(cid: 173) nologies, such as speech recognition, machine vision, and robotics. The fundamental ideas behind these technologies are still being developed, and it will be some time before products containing neural networks are manufactured. As a result, research in these areas will not drive the development of inexpensive neural network hard(cid: 173) ware which could serve as a catalyst for the field of neural networks in general. In contrast, neural networks are rarely considered for application in mature tech(cid: 173) nologies, such as consumer electronics. These technologies are based on established principles of information processing and communication, and they are used in mil(cid: 173) lions of products per year. The embedding of neural networks within such mass-

PDF Details

NeurIPS Conference 1989 Conference Paper

The Computation of Sound Source Elevation in the Barn Owl

Clay Spence
John Pearson

The midbrain of the barn owl contains a map-like representation of sound source direction which is used to precisely orient the head to(cid: 173) ward targets of interest. Elevation is computed from the interaural difference in sound level. We present models and computer simula(cid: 173) tions of two stages of level difference processing which qualitatively agree with known anatomy and physiology, and make several strik(cid: 173) ing predictions.

PDF Details

NeurIPS Conference 1988 Conference Paper

Neuronal Maps for Sensory-Motor Control in the Barn Owl

Clay Spence
John Pearson
J. Gelfand
R. Peterson
W. Sullivan

The bam owl has fused visual/auditory/motor representations of space in its midbrain which are used to orient the head so that visu(cid: 173) al or auditory stimuli are centered in the visual field of view. We present models and computer simulations of these structures which address various problems, inclu<lln~ the construction of a map of space from auditory sensory information, and the problem of driv(cid: 173) ing the motor system from these maps. We compare the results with biological data.

PDF Details