WorldCat Identities

Edelman, Shimon

Works: 44 works in 129 publications in 1 language and 5,709 library holdings
Genres: Academic theses 
Roles: Author
Classifications: BF311, 153
Publication Timeline
Most widely held works by Shimon Edelman
Computing the mind : how the mind really works by Shimon Edelman( Book )

13 editions published in 2008 in English and held by 631 WorldCat member libraries worldwide

"By analyzing the tasks facing any sentient being that is subject to stimulation and a pressure to act, Shimon Edelman identifies computation as the common denominator in the emerging answers to all these questions. Any system composed of elements that exchange signals with each other and occasionally with the rest of the world can be said to be engaged in computation. A brain composed of neurons is one example of a system that computes, and the computations that the neurons collectively carry out constitute the brain's mind." "Edelman presents a computational account of the entire spectrum of cognitive phenomena that constitute the mind. He begins with sentience, and uses examples from visual perception to demonstrate that it must, at its very core, be a type of computation. Throughout his account, Edelman acknowledges the human mind's biological origins. Along the way, he also demystifies traits such as creativity, language, and individual and collective consciousness, and hints at how naturally evolved minds can transcend some of their limitations by moving to computational substrates other than brains. The book should be read by anyone seeking a comprehensive and current introduction to cognitive psychology."--Jacket
The happiness of pursuit : what neuroscience can teach us about the good life by Shimon Edelman( Book )

5 editions published in 2012 in English and held by 610 WorldCat member libraries worldwide

Draws on philosophy, literature, and brain science to explain why the pursuit of happiness is a more complicated effort than understood by most people, sharing insights into how to apply scientific methods for increasing one's chances of achieving happiness
Representation and recognition in vision by Shimon Edelman( Book )

12 editions published in 1999 in English and held by 392 WorldCat member libraries worldwide

Researchers have long sought to understand what the brain does when we see an object, what two people have in common when they see the same object, and what a "seeing" machine would need to have in common with a human visual system. Recent neurobiological and computational advances in the study of vision have now brought us close to answering these and other questions about representation
Language universals by Morten H Christiansen( Book )

11 editions published in 2009 in English and held by 161 WorldCat member libraries worldwide

Examining language universals from a cross-disciplinary perspective, this book provides insights into questions such as: What exactly defines the human capacity for language? Are there universal properties of human languages and, if so, what are they? Can all language universals be explained in the same way?
Being in time : dynamical models of phenomenal experience( Book )

10 editions published in 2012 in English and held by 73 WorldCat member libraries worldwide

Given that a representational system's phenomenal experience must be intrinsic to it and must therefore arise from its own temporal dynamics, consciousness is best understood -- indeed, can only be understood -- as being in time. Despite that, it is still acceptable for theories of consciousness to be summarily exempted from addressing the temporality of phenomenal experience. The chapters comprising this book represent a collective attempt on the part of their authors to redress this aberration. The diverse treatments of phenomenal consciousness range in their methodology from philosophy, throu
On the representation of object structure in human vision : Evidence from differential priming of shape and location by Scymour Edelman( Book )

2 editions published in 1998 in English and held by 6 WorldCat member libraries worldwide

Synthesis of visual modules from examples : learning hyperacuity by Tomaso Poggio( Book )

4 editions published in 1991 in English and held by 5 WorldCat member libraries worldwide

For any given visual competence, it is tempting to conjecture a specific algorithm and a corresponding neural circuitry. It has been often implicitly assumed that this machinery may be hardwired in the brain. This extreme point of view, if taken seriously, amy quickly lead to absurd consequences. The underlying reason for the spectacular performance of human subjects in these tasks is that the information sampled by the photoreceptors and relayed to the brain does contain the information necessary for precise localization of image features, since the spacing between photoreceptors and the eye's optics satisfy (in the fovea) the constraints of the sampling theorem. More specifically, it has been shown that, in principle, spatial mechanisms that account for grating resolution are sensitive enough to support hyperacuity-level performance. Furthermore, some of the hyperacuity tasks can be solved by detecting 'secondary' cues such as luminance difference (as in the bisection task) or orientation (as in the detection of vertical vernier stimuli). The detailed structure of the neural circuitry that subserves the detection of these cues, or hyperacuity performance in other tasks is, however, unknown
Features of recognition by Shimon Edelman( Book )

3 editions published in 1991 in English and held by 5 WorldCat member libraries worldwide

Abstract: "The notion of features of recognition, of varying complexities and possessing different degrees of spatial localization, offers a unified approach to the understanding of object recognition in human vision. According to this approach, the visual system synthesizes a feature-based recognition module for a given object when it is first encountered. (cf. [22,35]; the feasibility of such synthesis in 3D object recognition was demonstrated in [34,17]). The details of the synthesized module, such as the types of features it relies upon and the computations applied to the features, depend on the kind of the [sic] object and on the required level of recognition
Beginnings by Shimon Edelman( Book )

1 edition published in 2014 in English and held by 5 WorldCat member libraries worldwide

Jorge Luis Borges, Philip K. Dick, and Edward Abbey walk into a bar on a small desert planet. ""Is this really me?"", murmurs Borges, staring at the mirror behind the counter. ""Is this really a bar?"", asks Dick. ""Oh forget it, let's just go for a hike, "" says Abbey and heads back to the door
On learning to recognize 3D objects from examples by Shimon Edelman( Book )

3 editions published in 1991 in English and held by 5 WorldCat member libraries worldwide

Abstract: "Previous analyses of visual concept acquisition in the context of computational learning theory tended to rely on the unrealistic assumption that concepts are represented and learned as sets of pixels [1]. In comparison, two recently proposed algorithms that learn to recognize three-dimensional objects from examples [2, 3] employ receptive fields for coarse features as the basic unit of representation. This report uses an approach developed by Haussler [4] to show that, under a feature-based definition of complexity, recognition is PAC-learnable from a feasible number of examples in a distribution-free manner."
Bringing the Grandmother Back into the Picture: A Memory-Based View of Object Recognition by Shimon Edelman( Book )

8 editions published in 1990 in English and Undetermined and held by 5 WorldCat member libraries worldwide

Experiments are described with a versatile pictorial prototype based learning scheme for 3D object recognition. The GRBF scheme seems to be amenable to realization in biophysical hardware because the only kind of computation it involves can be effectively carried out by combining receptive fields. Furthermore, the scheme is computationally attractive because it brings together the old notion of a grandmother cell and the rigorous approximation methods of regularization and splines. Keywords: Object recognition, Representation, Nonlinear interpolation. (JHD)
Viewpoint-specific representations in three-dimensional object recognition by Shimon Edelman( Book )

4 editions published in 1990 in English and held by 4 WorldCat member libraries worldwide

We report a series of psychological experiments that explore different aspects of the problem of object representation and recognition in human vision. Contrary to the paradigmatic view which holds that the representations are three dimensional and object centered, the results consistently support the notion of view specific representations that include at most partial depth information. In simulated experiments that involved the same stimuli shown to the human subjects, computational models built around two dimensional multiple-view representations replicated our main psychological results, including patterns of generalization errors and the time course of perceptual learning
Learning to recognize faces from examples by Shimon Edelman( Book )

2 editions published in 1991 in English and held by 4 WorldCat member libraries worldwide

Abstract: "We describe an implemented system that learns to recognize human faces under varying pose and illumination conditions. The system relies on symmetry operations to detect the eyes and the mouth in a face image, uses the locations of these features to normalize the appearance of the face, performs simple but effective dimensionality reduction by a convolution with a set of Gaussian receptive fields, and subjects the vector of activities of the receptive fields to a Radial Basis Function interpolating classifier. The performance of the system compares favorably with the state of the art in machine recognition of faces."
Stimulus familiarity determines recognition strategy for novel 3D objects by Shimon Edelman( Book )

3 editions published in 1989 in English and held by 4 WorldCat member libraries worldwide

Everyday objects are more readily recognized when seen from certain representative, or canonical, viewpoints than from other, random, viewpoints. We investigated the canonical views phenomenon for novel 3D objects. In particular, we looked for the effects of object complexity and familiarity on the variation of response times and error rates over different views of the object. Our main findings indicate that the responses times for different views become more uniform with practice, even though the subjects in our experiments received no feedback as to the correctness of their responses. In addition, the orderly dependency of the response time on the distance to a good view, characteristic of the canonical views phenomenon, disappears with practice. One possible interpretation of our results is in terms of a tradeoff between memory needed for storing specific-view representations of objects and time spent in recognizing the objects. Keywords: Visual perception; Image processing. (SDW)
Class similarity and viewpoint invariance in the recognition of 3D objects by Shimon Edelman( Book )

2 editions published in 1992 in English and held by 4 WorldCat member libraries worldwide

Abstract: "In human vision, the processes and the representations involved in identifying specific individuals are frequently postulated to be different from those used for basic-level classification, because classification is largely viewpoint-invariant, but identification is not. The validity of the dual-process assumption was assessd in psychophysical experiments, in which objective similarity between stimuli (and, consequently, the level of their distinction) varied in a controlled fashion. Increasing the similarity led to stronger dependence of the subjects' performance on viewpoint (as well as to higher mean error rate)
Viewpoint-dependence of response time in object recognition by Florin Cutzu( Book )

3 editions published in 1992 in English and held by 4 WorldCat member libraries worldwide

Rather, the RTs were significantly correlated with the summed image-plane feature-by-feature distances between the presented view and the first 1-3 best (shortest-RT) views. Our results suggest that nonlinear deformations in the image plane are a better model than mental rotation for the mechanism used by the human visual system to recognize objects across changes in their 3D orientation."
Generation of natural-looking 3D shapes by simulated evolution by F Manolache( Book )

2 editions published in 1993 in English and held by 4 WorldCat member libraries worldwide

Abstract: "Diverse complex simulated objects are widely used in psychophysical study of visual recognition, in computer graphics, and in animation. This paper describes a method to generate artificially objects belonging to a given subjectively characterized class. The method uses artificial evolution and is based on the observation that humans may classify objects by comparing them with previously encountered structural prototypes. An efficient artificial evolution algorithm was obtained using a thermodynamical point of view of the object universe, which regarded objects as populations of generic parts characterized by an entropy-like function used as fitness
On similarity to prototypes in 3D object recognition by S Duvdevani-Bar( Book )

2 editions published in 1995 in English and held by 3 WorldCat member libraries worldwide

Abstract: "A representational scheme under which the ranking between represented dissimilarities is isomorphic to the ranking between the corresponding shape dissimilarities can support perfect shape classification, because it preserves the clustering of shapes according to the natural kinds prevailing in the external world. We discuss the computational requirements of rank-preserving representation, and examine its plausibility within a protocol-based framework of shape vision."
Receptive fields for vision : from hyperacuity to object recognition by Shimon Edelman( Book )

2 editions published in 1995 in English and held by 3 WorldCat member libraries worldwide

Abstract: "Many of the lower-level areas in the mammalian visual system are organized retinotopically, that is, as maps which preserve to a certain degree the topography of the retina. A unit that is a part of such a retinotopic map normally responds selectively to stimulation in a well- delimited part of the visual field, referred to as its receptive field (RF). Receptive fields are probably the most prominent and ubiquitous computational mechanism employed by biological information processing systems. This paper surveys some of the possible computational reasons behind the ubiquity of RFs, by discussing examples of RF-based solutions to problems in vision, from spatial acuity, through sensory coding, to object recognition."
Generalization from a single view in face recognition by M Lando( Book )

2 editions published in 1995 in English and held by 3 WorldCat member libraries worldwide

Abstract: "We describe a computational model of face recognition, which generalizes from single views of faces by taking advantage of prior experience with other faces, seen under a wider range of viewing conditions. The model represents face images by vectors of activities of graded overlapping receptive fields (RFs). It relies on high spatial frequency information to estimate the viewing conditions, which are then used to normalize (via a transformation specific for faces), and identify, the low spatial frequency representation of the input. The class-specific transformation approach allows the model to replicate a series of psychophysical findings on face recognition, and constitutes an advance over current face recognition methods, which are incapable of generalization from a single example."
moreShow More Titles
fewerShow Fewer Titles
Audience Level
Audience Level
  Kids General Special  
Audience level: 0.20 (from 0.08 for Representa ... to 0.86 for Bringing t ...)

Computing the mind : how the mind really works
Alternative Names
delʹman, Šimon Aleksandr

ʾEdelman Šimʿwn

Эдельман Шимон Александр

אדלמן שמעון

English (93)

Representation and recognition in visionLanguage universals