• Home
  • Jonathan A. Marshall
Jonathan A. Marshall

Jonathan A. Marshall
Well Rounded Software, Inc.

Ph.D.

About

42
Publications
2,266
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
588
Citations
Additional affiliations
July 1990 - December 1998
University of North Carolina at Chapel Hill
Position
  • Professor (Assistant)

Publications

Publications (42)
Article
Full-text available
The time complexity of data clustering has been viewed as fundamentally quadratic, slowing with the number of data items, as each item is compared for similarity to preceding items. Clustering of large data sets has been infeasible without resorting to probabilistic methods or to capping the number of clusters. Here we introduce MIMOSA, a novel cla...
Article
Existing neural network models are capable of tracking linear trajectories of moving visual objects. This paper describes an additional neural mechanism, disfacilitation, that enhances the ability of a visual system to track curved trajectories. The added mechanism combines information about an object's trajectory with information about changes in...
Article
Intracortical microstimulation (ICMS) of a single site in the somatosensory cortex of rats and monkeys for 2-6 h increases the number of neurons responsive to the skin region corresponding to the ICMS-site receptive field (RF), with very little effect on the position and size of the ICMS-site RF, and the response evoked at the ICMS site by tactile...
Technical Report
Full-text available
Code reuse decreases software development time and cost. Developers integrate existing components, instead of building them repeatedly from scratch. Reuse has succeeded widely for small chunks of code, like application component libraries. However, larger-scale code reuse is perennially hobbled by practical problems. For example: • When code is se...
Article
Full-text available
Intracortical microstimulation (ICMS) of a single site in the somatosensory cortex of rats and monkeys for 2-6 h increases the number of neurons responsive to the skin region corresponding to the ICMS-site receptive field (RF), with very little effect on the position and size of the ICMS-site RF, and the response evoked at the ICMS site by tactile...
Article
There is an intriguing temporal and stochastic relationship between stimulus strength and dominance duration in binocular rivalry (Blake, Psychol. Rev. 96 (1989) 145; Blake, Fox, McIntyre, J. Exp. Psychol. 88 (1971) 327; Levelt, 1965; Muller, Blake, Biol. Cybernet. 61 (1989) 223). Increasing the stimulus strength in the ipsilateral eye decreases th...
Article
Existing neural network models are capable of tracking linear trajectories of moving visual objects. This paper describes an additional neural mechanism, disfacilitation, that enhances the ability of a visual system to track curved trajectories. The added mechanism combines information about an object's trajectory with information about changes in...
Article
Full-text available
Infusion of a GABA agonist (Reiter & Stryker, 1988) and infusion of an NMDA receptor antagonist (Bear et al., 1990), in the primary visual cortex of kittens during monocular deprivation, shifts ocular dominance toward the closed eye, in the cortical region near the infusion site. This reverse ocular dominance shift has been previously modeled by va...
Article
Full-text available
Previous models of visual cortical ocular dominance (OD) plasticity (e.g., Clothiaux et al., 1991; Miller et al., 1989) are based on afferent excitatory synaptic plasticity alone; these models do not consider the role of lateral interactions and synaptic plasticity in lateral pathways in OD plasticity. Recent models of other cortical properties and...
Article
Full-text available
A large variety of synaptic plasticity rules have been used in models of excitatory synaptic plasticity (Brown et al., 1990). These rules are generalizations of the Hebbian rule and have some properties consistent with experimental data on long-term excitatory synaptic plasticity, but they also have some properties inconsistent with experimental da...
Article
Full-text available
Human visual systems maintain a stable internal representation of a scene even though the image on the retina is constantly changing because of eye movements. Such stabilization can theoretically be effected by dynamic shifts in the receptive field (RF) of neurons in the visual system. This paper examines how a neural circuit can learn to generate...
Article
Full-text available
The position, size, and shape of the receptive field (RF) of some cortical neurons change dynamically, in response to artificial scotoma conditioning (Pettet & Gilbert, 1992) and to retinal lesions (Chino et al., 1992; Darian-Smith & Gilbert, 1995) in adult animals. The RF dynamics are of interest because they show how visual systems may adaptively...
Article
Full-text available
. A new way of measuring generalization in unsupervised learning is presented. The measure is based on an exclusive allocation,orcredit assignment, criterion. In a classifier that satisfies the criterion, input patterns are parsed so that the credit for each input feature is assigned exclusively to one of multiple, possibly overlapping, output cate...
Article
Full-text available
A new way of measuring generalization in unsupervised learning is presented. The measure is based on an exclusive allocation, or credit assignment , criterion. In a classifier that satisfies the criterion, input patterns are parsed so that the credit for each input feature is assigned exclusively to one of multiple, possibly overlapping, output cat...
Article
Full-text available
The position, size, and shape of the visual receptive field (RF) of some primary visual cortical neurons change dynamically, in response to artificial scotoma conditioning in cats (Pettet & Gilbert, 1992) and to retinal lesions in cats and monkeys (DarianSmith & Gilbert, 1995). The "EXIN" learning rules (Marshall, 1995) are used to model dynamic RF...
Article
Full-text available
Intracortical microstimulation (ICMS) of a localized site in the somatosensory cortex of rats and monkeys for 2{6 hours produces a large increase in the cortical representation of the skin region represented by the ICMS-site neurons before ICMS, with very little eeect on the ICMS-site neuron's RF location, RF size, and responsiveness (Recanzone et...
Article
Purpose. The ocular dominance (ÖD) of neurons in primary visual cortex is affected by the classical rearing paradigms, such as monocular (MD) and binocular (BD) deprivation, reverse suture (RS), and strabimus (ST). We studied how OD responds to these rearing conditions, as well as to normal rearing (NR), and recovery (RE) after long-term BD and MD....
Article
Purpose. Segmentation of transparently overlaid surfaces requires spatially nonlocal communication between the cortical representation of various image features e.g., between two X-junctions on a single surface. The nonlocal communication is needed to allow the local evidence for the validity or invalidity of transparent segmentations to he checked...
Article
Full-text available
A new way of measuring generalization in unsupervised learning is presented. The measure is based on an exclusive allocation, or credit assignment, criterion. In a classifier that satisfies the criterion, input patterns are parsed so that the credit for each input feature is assigned exclusively to one of multiple, possibly overlapping, output cate...
Article
Full-text available
Stereomatching of oblique and transparent surfaces is described using a model of cortical binocular ‘tuned’ neurons selective for disparities of individual visual features and neurons selective for the position, depth and 3D orientation of local surface patches. The model is based on a simple set of learning rules. In the model, monocular neurons p...
Article
Full-text available
Visual occlusion events constitute a major source of depth information. This paper presents a self-organizing neural network that learns to detect, represent, and predict the visibility and invisibility relationships that arise during occlusion events, after a period of exposure to motion sequences containing occlusion and disocclusion events. The...
Article
Full-text available
We studied whether the blur/sharpness of an occlusion boundary between a sharply focused surface and a blurred surface is used as a relative depth cue. Observers judged relative depth in pairs of images that differed only in the blurriness of the common boundary between two adjoining texture regions, one blurred and one sharply focused. Two experim...
Article
Purpose. The size and shape of the receptive field (RF) of some V1 neurons in monkeys change dynamically, in response to artificial scotoma conditioning (Pettet & Gilbert, 1992) and to retinal lesions (Darian-Smith & Gilbert, 1995). We have formulated and tested a neural network model that exhibits similar dynamic RF changes. The model, which uses...
Article
Purpose. The strength with which moving visual stimulus elements are perceptually grouped together depends on several contextual factors, including the motion coherence of the elements and the local motion contrast between the elements. We studied the development of neural circuits for perceptual grouping. We also studied the effects of motion cohe...
Article
Full-text available
A new context-sensitive neural network, called an EXIN (excitatory + inhibitory) network, is described. EXIN networks self-organize in complex perceptual environments, in the presence of multiple superimposed patterns, multiple scales, and uncertainty. The networks use a new inhibitory learning rule, in addition to an excitatory learning rule, to a...
Article
Full-text available
. Visual occlusion events constitute a major source of depth information. We have developed a neural network model that learns to detect and represent depth relations, after a period of exposure to motion sequences containing occlusion and disocclusion events. The network's learning is governed by a new set of learning and activation rules. The net...
Article
A simple self-organizing neural network model, called an EXIN network, that learns to process sensory information in a context-sensitive manner, is described. EXIN networks develop efficient representation structures for higher-level visual tasks such as segmentation, grouping, transparency, depth perception, and size perception. Exposure to a perc...
Conference Paper
A simple self-organizing neural network model, called an EXIN network, that learns to process sensory information in a context-sensitive manner is described. Exposure to a perceptual environment during a developmental period configures the network to perform appropriate organization of sensory data. An anti-Hebbian learning rule causes some lateral...
Article
Full-text available
Human vision systems integrate information nonlocally, across long spatial ranges. For example, a moving stimulus appears smeared when viewed briefly (30 ms), yet sharp when viewed for a longer exposure (100 ms) (Burr, 1980). This suggests that visual systems combine information along a trajectory that matches the motion of the stimulus. Our self-o...
Article
Psychophysical studies on motion perception suggest that human visual systems perform certain nonlocal operations. In some cases, data about one part of an image can influence the processing or perception of data about another part of the image, across a long spatial range. In others, data about nearby parts of an image can fail to influence one an...
Article
Edge linearization operators are often used in computer vision and in neural network models of vision to reconstruct noisy or incomplete edges. Such operators gather evidence for the presence of an edge at various orientations across all image locations and then choose the orientation that best fits the data at each point. One disadvantage of such...
Article
Full-text available
The human visual system overcomes ambiguities, collectively known as the aperture problem, in its local measurements of the direction in which visual objects are moving, producing unambiguous percepts of motion. A new approach to the aperture problem is presented, using an adaptive neural network model. The neural network is exposed to moving image...
Conference Paper
Full-text available
Three adaptive rules are combined in a neural network simulation: an anti-Hebbian inhibitory learning rule, a variant of a Hebbian excitatory learning rule, and a Weber law neuron-growth rule. The neuron-growth rule permits the network to learn and classify input patterns despite variations in their spatial scale. The inhibitory learning rule permi...
Chapter
The ability to represent multiple hypotheses about the classification of an ambiguous input pattern is an extremely useful network property. Yet typically, self-organizing neural networks are designed to make only winner-take-all pattern classification decisions. The winner-take-all decisions may often turn out to be wrong when they are based on in...
Article
Full-text available
A neural network model of multiple-scale binocular fusion and rivalry in visual cortex is described and simulated on the computer. The model consists of three parts: a distributed spatial representation of binocular input patterns among simple cells that are organized into ocular dominance columns; an adaptive filter from simple cells to complex ce...
Conference Paper
The analysis describes some of the issues involved in constructing a self-organizing neural network that can learn to perform a high-level vision task, depth perception from motion parallax, without guidance from an external teacher. An examination is made of how motion parallax conveys depth information. A network structure is presented for detect...
Article
Thesis (Ph. D.)--Boston University, 1989. Vita. Includes bibliographical references (leaves 171-185).

Network

Cited By