Results 1 - 10
of
438
A learning algorithm for Boltzmann machines
- Cognitive Science
, 1985
"... The computotionol power of massively parallel networks of simple processing elements resides in the communication bandwidth provided by the hardware connections between elements. These connections con allow a significant fraction of the knowledge of the system to be applied to an instance of a probl ..."
Abstract
-
Cited by 584 (13 self)
- Add to MetaCart
(Show Context)
The computotionol power of massively parallel networks of simple processing elements resides in the communication bandwidth provided by the hardware connections between elements. These connections con allow a significant fraction of the knowledge of the system to be applied to an instance of a problem in o very short time. One kind of computation for which massively porollel networks appear to be well suited is large constraint satisfaction searches, but to use the connections efficiently two conditions must be met: First, a search technique that is suitable for parallel networks must be found. Second, there must be some way of choosing internal representations which allow the preexisting hardware connections to be used efficiently for encoding the con-straints in the domain being searched. We describe a generol parallel search method, based on statistical mechanics, and we show how it leads to a gen-eral learning rule for modifying the connection strengths so as to incorporate knowledge obout o task domain in on efficient way. We describe some simple examples in which the learning algorithm creates internal representations thot ore demonstrobly the most efficient way of using the preexisting connectivity structure. 1.
Qualitative Simulation
- Artificial Intelligence
, 2001
"... Qualitative simulation predicts the set of possible behaviors... ..."
Abstract
-
Cited by 520 (32 self)
- Add to MetaCart
(Show Context)
Qualitative simulation predicts the set of possible behaviors...
Algorithms for Constraint-Satisfaction Problems: A Survey
, 1992
"... A large number of problems in AI and other areas of computer science can be viewed as special cases of the constraint-satisfaction problem. Some examples are machine vision, belief maintenance, scheduling, temporal reasoning, graph problems, floor plan design, the planning of genetic experiments, an ..."
Abstract
-
Cited by 449 (0 self)
- Add to MetaCart
(Show Context)
A large number of problems in AI and other areas of computer science can be viewed as special cases of the constraint-satisfaction problem. Some examples are machine vision, belief maintenance, scheduling, temporal reasoning, graph problems, floor plan design, the planning of genetic experiments, and the satisfiability problem. A number of different approaches have been developed for solving these problems. Some of them use constraint propagation to simplify the original problem. Others use backtracking to directly search for possible solutions. Some are a combination of these two techniques. This article overviews many of these approaches in a tutorial fashion.
Visual search
- In H. Pashler (Ed.), Attention
, 1998
"... This paper describes a series of visual search experiments for targets defined by their hinocu-lar characteristics. In searches for targets defined by binocular rivalry among fused distractors, or vice versa, the rivalrous items do not "pop out " (reaction time [RT] increases with number o ..."
Abstract
-
Cited by 289 (17 self)
- Add to MetaCart
This paper describes a series of visual search experiments for targets defined by their hinocu-lar characteristics. In searches for targets defined by binocular rivalry among fused distractors, or vice versa, the rivalrous items do not "pop out " (reaction time [RT] increases with number of distractors). Binocular luster, a variety of rivalry, is an exception. Luster, an important property of visible surfaces, behaves like a basic feature or "texton " (RT independent of the number of nonlustrous distractors). Searches for targets defined exclusively by eye-of-origin information are virtually impossible. Subjects respond randomly, suggesting that purely monocular information is not available for visual search. Searches for cyclopean (but nonstereoscopic) features are easy, with RTs independent of set size, suggesting that some purely binocular information is available for visual search. There has been considerable recent interest in our ability to search for one type of item among a number of other items presented simultaneously (e.g., Johnston & Dark, 1986; Julesz, 1984; Treisman & Gelade, 1980). In some cas~s, all the items seem to be examined at once and visual
A sufficient condition for backtrack-free search
, 1982
"... A constraint satisfaction problem revolves finding values for a set of variables subject of a set of constraints (relations) on those variables Backtrack search is often used to solve such problems. A relationship involving the structure of the constraints i described which characterizes tosome deg ..."
Abstract
-
Cited by 288 (14 self)
- Add to MetaCart
A constraint satisfaction problem revolves finding values for a set of variables subject of a set of constraints (relations) on those variables Backtrack search is often used to solve such problems. A relationship involving the structure of the constraints i described which characterizes tosome degree the extreme case of mimmum backtracking (none) The relationship involves a concept called "width," which may provide some guidance in the representation f constraint satisfaction problems and the order m which they are searched The width concept is studied and applied, in particular, to constraints which form tree structures.
Representations of Rigid Solids: Theory, Methods, and Systems
- ACM Computing Surveys
, 1980
"... Computer-based ystems for modehng the geometry ofrigid solid objects are becoming increasingly important inmechanical nd civil engineering, architecture, computer graphics, computer vision, and other fields that deal with spatial phenomena. At the heart of such systems are symbol structures (represe ..."
Abstract
-
Cited by 256 (2 self)
- Add to MetaCart
Computer-based ystems for modehng the geometry ofrigid solid objects are becoming increasingly important inmechanical nd civil engineering, architecture, computer graphics, computer vision, and other fields that deal with spatial phenomena. At the heart of such systems are symbol structures (representations) designating "abstract solids" (subsets of Euclidean space) that model physical solids. Representations arethe sources of data for procedures which compute useful properties ofobjects. The variety and uses of systems embodying representations f olids are growing rapidly, but so are the difficulties in assessing current designs, pecifying the characteristics that future systems should exhibit, and designing systems t9 meet such specifications. This paper esolves many of these difficulties by providing a coherent view, based on sound theoretical principles, of what is presently known about he representation of solids. The paper is divided into three parts. The first introduces a simple mathematical framework for characterizing certain important aspects of representations, for example, their semantic (geometric) ntegrity. The second part uses the framework to describe and compare all of the major knownschemes fo ~ representing solids. The third part briefly surveys extant geometric modeling systems and then applies the concepts developed in the paper to the high-level design of a multiple*representation geometric modeling system which exhibits alevel of reliability and versatility supermr to that of systems currently used in industrial computer-aided design and manufacturing.
Numerical Shape from Shading and Occluding Boundaries
- Artifical Intelligence
, 1981
"... An iterative method for computing shape from shading using occluding boundary information is proposed. Some applications of this method are shown. We employ the stereographic plane to express the orientations of surface patches, rather than the more commonly.used gradient space. Use of the stereogra ..."
Abstract
-
Cited by 254 (20 self)
- Add to MetaCart
An iterative method for computing shape from shading using occluding boundary information is proposed. Some applications of this method are shown. We employ the stereographic plane to express the orientations of surface patches, rather than the more commonly.used gradient space. Use of the stereographic plane makes it possible to incorporate occluding boundary information, but forces us to employ a smoothness constraint different from the one previously proposed. The new constraint follows directly from a particular definition of surface smoothness. We solve the set of equations arising from the smoothness constraints and the image-irradiance equation iteratively, using occluding boundary information to supply boundary conditions. Good initial values are found at certain points to help reduce the number of iterations required to reach a reasonable solution. Numerical experiments show that the method is effective and robust. Finally, we analyze scanning electron microscope (SEM) pictures using this method. Other applications are also proposed. 1.
On the Removal of Shadows from Images
, 2006
"... This paper is concerned with the derivation of a progression of shadow-free image representations. First, we show that adopting certain assumptions about lights and cameras leads to a 1D, gray-scale image representation which is illuminant invariant at each image pixel. We show that as a consequenc ..."
Abstract
-
Cited by 236 (18 self)
- Add to MetaCart
(Show Context)
This paper is concerned with the derivation of a progression of shadow-free image representations. First, we show that adopting certain assumptions about lights and cameras leads to a 1D, gray-scale image representation which is illuminant invariant at each image pixel. We show that as a consequence, images represented in this form are shadow-free. We then extend this 1D representation to an equivalent 2D, chromaticity representation. We show that in this 2D representation, it is possible to relight all the image pixels in the same way, effectively deriving a 2D image representation which is additionally shadow-free. Finally, we show how to recover a 3D, full color shadow-free image representation by first (with the help of the 2D representation) identifying shadow edges. We then remove shadow edges from the edge-map of the original image by edge in-painting and we propose a method to reintegrate this thresholded edge map, thus deriving the sought-after 3D shadow-free image.