Shimon Edelman

Visual objects can be represented by their similarities to a small number of reference shapes or prototypes. This method yields low-dimensional (and therefore computationally tractable) representations, which support both the recognition of familiar shapes and the categorization of novel ones. In this note, we show how such representations can be used in a variety of tasks involving novel objects: viewpoint-invariant recognition, recovery of a canonical view, estimation of pose, and prediction of an arbitrary view. The unifying principle in all these cases is the representation of the view space of the novel object as an interpolation of the view spaces of the reference shapes.

Intelligent systems are faced with the problem of securing a principled (ideally, veridical) relationship between the world and its internal representation. I propose a unified approach to visual representation, addressing both the needs of superordinate and basic-level categorization and of identification of specific instances of familiar categories. According to the proposed theory, a shape is represented by its similarity to a number of reference shapes, measured in a high-dimensional space of elementary features. This amounts to embedding the stimulus in a low-dimensional proximal shape space. That space turns out to support representation of distal shape similarities which is veridical in the sense of Shepard's (1968) notion of second-order isomorphism (i.e., correspondence between distal and proximal similarities among shapes, rather than between distal shapes and their proximal representations). Furthermore, a general expression for similarity between two stimuli, based on comparisons to reference shapes, can be used to derive models of perceived similarity ranging from continuous, symmetric, and hierarchical, as in the multidimensional scaling models (Shepard, 1980), to discrete and non-hierarchical, as in the general contrast models (Tversky, 1977; Shepard and Arabie, 1979)

We tested the hypothesis that more frequent exposure to multiword phrases results in deeper entrenchment of their representations, by examining the performance of subjects of different religiosity in the recognition of briefly presented liturgical and secular phrases drawn from several frequency classes. Three of the sources were prayer texts that religious Jews are required to recite on a daily, weekly, and annual basis, respectively; two others were common and rare expressions encountered in the general secular Israeli culture. As expected, linear dependence of recognition score on frequency was found for the religious subjects (being most pronounced for men, who are usually more observant than women); both religious and secular subjects performed better on common than on rare general culture items. Our results support the notion of graded entrenchment introduced by Langacker and shared by several cognitive linguistic theories of language comprehension and production

Language is a rewarding field if you are in the prediction business. A reader who is fluent in English and who knows how academic papers are typically structured will readily come up with several possible guesses as to where the title of this section could have gone, had it not been cut short by the ellipsis. Indeed, in the more natural setting of spoken language, anticipatory processing is a must: performance of machine systems for speech interpretation depends critically on the availability of a good predictive model of how utterances unfold in time (Baker, 1975; Jelinek, 1990; Goodman, 2001), and there is strong evidence that prospective uncertainty affects human sentence processing too (Jurafsky, 2003; Hale, 2006; Levy, 2008). The human ability to predict where the current utterance is likely to be going is just another adaptation to the general pressure to anticipate the future (Hume, 1748; Dewey, 1910; Craik, 1943), be it in perception, thinking, or action, which is exerted on all cognitive systems by evolution (Dennett, 2003). Look-ahead in language is, however, special in one key respect: language is a medium for communication, and in communication the most interesting (that is, informative) parts of the utterance that the speaker is working through are those that cannot be predicted by the listener ahead of time.

We introduce a set of biologically and computationally motivated design choices for modeling the learning of language, or of other types of sequential, hierarchically structured experience and behavior, and describe an implemented system that conforms to these choices and is capable of unsupervised learning from raw natural-language corpora. Given a stream of linguistic input, our model incrementally learns a grammar that captures its statistical patterns, which can then be used to parse or generate new data. The grammar constructed in this manner takes the form of a directed weighted graph, whose nodes are recursively (hierarchically) defined patterns over the elements of the input stream. We evaluated the model in seventeen experiments, grouped into five studies, which examined, respectively, (a) the generative ability of grammar learned from a corpus of natural language, (b) the characteristics of the learned representation, (c) sequence segmentation and chunking, (d) artificial grammar learning, and (e) certain types of structure dependence. The model's performance largely vindicates our design choices, suggesting that progress in modeling language acquisition can be made on a broad front—ranging from issues of generativity to the replication of human experimental findings—by bringing biological and computational considerations, as well as lessons from prior efforts, to bear on the modeling approach.

By what empirical means can a person determine whether he or she is presently awake or dreaming? Any conceivable test addressing this question, which is a special case of the classical metaphysical doubting of reality, must be statistical (for the same reason that empirical science is, as noted by Hume). Subjecting the experienced reality to any kind of statistical test (for instance, a test for bizarreness) requires, however, that a set of baseline measurements be available. In a dream, or in a simulation, any such baseline data would be vulnerable to tampering by the same processes that give rise to the experienced reality, making the outcome of a reality test impossible to trust. Moreover, standard cryptographic defenses against such tampering cannot be relied upon, because of the potentially unlimited reach of reality modification within a dream, which may range from the integrity of the verification keys to the declared outcome of the entire process. In the face of this double predicament, the rational course of action is to take reality at face value. The predicament also has some intriguing corollaries. In particular, even the most revealing insight that a person may gain into the ultimate nature of reality (for instance, by attaining enlightenment in the Buddhist sense) is ultimately unreliable, for the reasons just mentioned. At the same time, to adhere to this principle, one has to be aware of it, which may not be possible in various states of reduced or altered cognitive function such as dreaming or religious experience. Thus, a subjectively enlightened person may still lack the one truly important piece of the puzzle concerning his or her existence.

Unsupervised statistical learning is the standard setting for the development of the only advanced visual system that is both highly sophisticated and versatile, and extensively studied: that of monkeys and humans. In this extended abstract, we invoke philosophical observations, computational arguments, behavioral data and neurobiological findings to explain why computer vision researchers should care about (1) unsupervised learning, (2) statistical inference, and (3) the visual brain. We then outline a neuromorphic approach to structural primitive learning motivated by these considerations, survey a range of neurobiological findings and behavioral data consistent with it, and conclude by mentioning some of the more challenging directions for future research.

What insights does comparative biology provide for furthering scienti¿ c understanding of the evolution of dynamic coordination? Our discussions covered three major themes: (a) the fundamental unity in functional aspects of neurons, neural circuits, and neural computations across the animal kingdom; (b) brain organization –behavior relationships across animal taxa; and (c) the need for broadly comparative studies of the relationship of neural structures, neural functions, and behavioral coordination. Below we present an overview of neural machinery and computations that are shared by all nervous systems across the animal kingdom, and the related fact that there really are no “simple” relationships in coordination between nervous systems and the behavior they produce. The simplest relationships seen in living organisms are already fairly complex by computational standards. These realizations led us to think about ways that brain similarities and differences could be used to produce new insights into complex brain–behavior phenomena (including a critical appraisal of the roles of cortical and noncortical structures in mammalian behavior), and to think brieÀy about how future studies could best exploit comparative methods to elucidate better general principles underlying the neural mechanisms associated with behavioral coordination. In our view, it is unlikely that the intricacies interrelating neural and behavioral coordination are due to one particular manifestation (such as neural oscillation or the possession of a six-layered cortex). Instead of considering the human cortex to be the standard against which all things are measured (and thus something to crow about), both broad and focused comparative studies on behavioral similarities and differences will be necessary to elucidate the fundamental principles underlying dynamic coordination.

We describe a unified framework for the understanding of structure representation in primate vision. A model derived from this framework is shown to be effectively systematic in that it has the ability to interpret and associate together objects that are related through a rearrangement of common “middle-scale” parts, represented as image fragments. The model addresses the same concerns as previous work on compositional representation through the use of what+where receptive fields and attentional gain modulation. It does not require prior exposure to the individual parts, and avoids the need for abstract symbolic binding

Are minds really dynamical or are they really symbolic? Because minds are bundles of computations, and because computation is always a matter of interpretation of one system by another, minds are necessarily symbolic. Because minds, along with everything else in the universe, are physical, and insofar as the laws of physics are dynamical, minds are necessarily dynamical systems. Thus, the short answer to the opening question is “yes.” It makes sense to ask further whether some of the computations that constitute a human mind are constrained by functional, algorithmic, or implementational factors to be essentially of the discrete symbolic variety (even if they supervene on an apparently continuous dynamical substrate). I suggest that here too the answer is “yes” and discuss the need for such discrete, symbolic cognitive computations in communication-related tasks.

The computational program for theoretical neuroscience initiated by Marr and Poggio (1977) calls for a study of biological information processing on several distinct levels of abstraction. At each of these levels — computational (defining the problems and considering possible solutions), algorithmic (specifying the sequence of operations leading to a solution) and implementational — significant progress has been made in the understanding of cognition. In the past three decades, computational principles have been discovered that are common to a wide range of functions in perception (vision, hearing, olfaction) and action (motor control). More recently, these principles have been applied to the analysis of cognitive tasks that require dealing with structured information, such as visual scene understanding and analogical reasoning. Insofar as language relies on cognition-general principles and mechanisms, it should be possible to capitalize on the recent advances in the computational study of cognition by extending its methods to linguistics.

We describe a pattern acquisition algorithm that learns, in an unsupervised fashion, a streamlined representation of linguistic structures from a plain natural-language corpus. This paper addresses the issues of learning structured knowledge from a large-scale natural language data set, and of generalization to unseen text. The implemented algorithm represents sentences as paths on a graph whose vertices are words. Significant patterns, determined by recursive context-sensitive statistical inference, form new vertices. Linguistic constructions are represented by trees composed of significant patterns and their associated equivalence classes. An input module allows the algorithm to be subjected to a standard test of English as a Second Language profi- ciency. The results are encouraging: the model attains a level of performance considered to be “intermediate” for 9th-grade students, despite having been trained on a corpus containing transcribed speech of parents directed to small children

Nearest-neighbor correlation-based similarity computation in the space of outputs of complex-type receptive elds can support robust recognition of 3D objects. Our experiments with four collections of objects resulted in mean recognition rates between 84% and 94%, over a 40 40 range of viewpoints, centered on a stored canonical view and related to it by rotations in depth. This result has interesting implications for the design of a front end to an arti cial object recognition system, and for the understanding of the faculty of object recognition in primate vision

We describe a method for automatic word sense disambiguation using a text corpus and a machine- readable dictionary (MRD). The method is based on word similarity and context similarity measures. Words are considered similar if they appear in similar contexts; contexts are similar if they contain similar words. The circularity of this definition is resolved by an iterative, converging process, in which the system learns from the corpus a set of typical usages for each of the senses of the polysemous word listed in the MRD. A new instance of a polysemous word is assigned the sense associated with the typical usage most similar to its context. Experiments show that this method performs well, and can learn even from very sparse training data.

It is proposed to conceive of representation as an emergent phenomenon that is supervenient on patterns of activity of coarsely tuned and highly redundant feature detectors. The computational underpinnings of the outlined concept of representation are (1) the properties of collections of overlapping graded receptive fields, as in the biological perceptual systems that exhibit hyperacuity-level performance, and (2) the sufficiency of a set of proximal distances between stimulus representations for the recovery of the corresponding distal contrasts between stimuli, as in multidimensional scaling. The present preliminary study appears to indicate that this concept of representation is computationally viable, and is compatible with psychological and neurobiological data

The distributional principle according to which morphemes that occur in identical contexts belong, in some sense, to the same category [1] has been advanced as a means for extracting syntactic structures from corpus data. We extend this principle by applying it recursively, and by using mutual information for estimating category coherence. The resulting model learns, in an unsupervised fashion, highly structured, distributed representations of syntactic knowledge from corpora. It also exhibits promising behavior in tasks usually thought to require representations anchored in a grammar, such as systematicity.

differentiaily rated pairwise similarity when confronted with two pairs of objects, each revolving in a separate window on a computer screen. Subject data were pooled using individually weighted MDS (ref. 11; in all the experiments, the solutions were consistent among subjects). In each trial, the subject had to select among two pairs of shapes the one consisting of the most similar shapes. The subjects were allowed to respond at will; most responded within 10 sec. Proximity (that is, perceived similarity) tables derived from the judgments were processed to verify their degree of transitivity (4% of all triplets were found intransitive) and then submitted to MDS. In the long-term memory (LTM) variant of this experiment, the subjects were first trained to associate a label (a three-letter nonsensical string, such as "BON" or "POM") with each object and then carried out the pairs of pairs comparison task from memory, prompted by the object labels rather than by the objects themselves. Six subjects participated in each of the two LTM experiments (Star and Triangle). The subjects were taught each shape in a separate session and had to discriminate between that shape and six similar nontargets from various viewpoints. Training continued until the recognition rate reached 90%, over a period of several days. The subjects were never exposed to more than one target in one session and were not told the ultimate purpose of the experiment. After 2 to 3 days of rest, they were tested with questions such as: "is the BON more similar to POM than TOC to ROX?", for all pairs of pairs of stimuli. In the LTM experiments, 8% of the..

Construction-based approaches to syntax (Croft, 2001; Goldberg, 2003) posit a lexicon populated by units of various sizes, as envisaged by (Langacker, 1987). Constructions may be specified completely, as in the case of simple morphemes or idioms such as take it to the bank, or partially, as in the expression what’s X doing Y?, where X and Y are slots that admit fillers of particular types (Kay and Fillmore, 1999). Constructions offer an intriguing alternative to traditional rule-based syntax by hinting at the extent to which the complexity of language can stem from a rich repertoire of stored, more or less entrenched (Harris, 1998) representations that address both syntactic and semantic issues, and encompass, in addition to general rules, “totally idiosyncratic forms and patterns of all intermediate degrees of generality” (Langacker, 1987, p.46). Because constructions are by their very nature language-specific, the question of acquisition in Construction Grammar is especially poignant. We address this issue by offering an unsupervised algorithm that learns constructions from raw corpora.

The statistical structure of a class of objects such as human faces can be exploited to recognize familiar faces from novel viewpoints and under variable illumination conditions. We present computational and psychophysical data concerning the extent to which class-based learning transfers or generalizes within the class of faces. We rst examine the computational prerequisite for generalization across views of novel faces, namely, the similarity of di erent faces to each other. We next describe two computational models which exploit the similarity structure of the class of faces. The performance of these models constrains hypotheses about the nature of face representation in human vision, and supports the notion that human face processing operates in a class-based fashion. Finally, we relate the computational data to well-established ndings in the human memory literature concerning the relationship between the typicality and recognizability of faces.

We examined the role of fitness, commonly assumed without proof to be conferred by the mastery of language, in shaping the dynamics of language evolution. To that end, we introduced island migration (a concept borrowed from population genetics) into the shared lexicon model of communication (Nowak et al., 1999). The effect of fitness linear in language coherence was compared to a control condition of neutral drift. We found that in the neutral condition (no coherence-dependent fitness) even a small migration rate – less than 1% – suffices for one language to become dominant, albeit after a long time. In comparison, when fitness-based selection is introduced, the subpopulations stabilize quite rapidly to form several distinct languages. Our findings support the notion that language confers increased fitness. The possibility that a shared language evolved as a result of neutral drift appears less likely, unless migration rates over evolutionary times were extremely small.