Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “representation learning”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 703 records · Page 39Linked to original sources
PubMed2002

Many-layered learning.

We explore incremental assimilation of new knowledge by sequential learning. Of particular interest is how a network of many knowledge layers can be constructed in an on-line manner, such that the learned units represent building blocks of knowledge that serve to compress the overall representation and facilitate transfer. We motivate the need for many layers of knowledge, and we advocate sequential learning as an avenue for promoting the construction of layered knowledge structures. Finally, our novel STL algorithm demonstrates a method for simultaneously acquiring and organizing a collection of concepts and functions as a network from a stream of unstructured information.

Algorithms↗
PubMed2005

Encoding multielement scenes: statistical learning of visual feature hierarchies.

The authors investigated how human adults encode and remember parts of multielement scenes composed of recursively embedded visual shape combinations. The authors found that shape combinations that are parts of larger configurations are less well remembered than shape combinations of the same kind that are not embedded. Combined with basic mechanisms of statistical learning, this embeddedness constraint enables the development of complex new features for acquiring internal representations efficiently without being computationally intractable. The resulting representations also encode parts and wholes by chunking the visual input into components according to the statistical coherence of their constituents. These results suggest that a bootstrapping approach of constrained statistical learning offers a unified framework for investigating the formation of different internal representations in pattern and scene perception.

Adolescent↗
PubMedDate not supplied

Predicting physical-chemical properties of compounds from molecular structures by recursive neural networks.

In this paper, we report on the potential of a recently developed neural network for structures applied to the prediction of physical chemical properties of compounds. The proposed recursive neural network (RecNN) model is able to directly take as input a structured representation of the molecule and to model a direct and adaptive relationship between the molecular structure and target property. Therefore, it combines in a learning system the flexibility and general advantages of a neural network model with the representational power of a structured domain. As a result, a completely new approach to quantitative structure-activity relationship/quantitative structure-property relationship (QSPR/QSAR) analysis is obtained. An original representation of the molecular structures has been developed accounting for both the occurrence of specific atoms/groups and the topological relationships among them. Gibbs free energy of solvation in water, Delta(solv)G degrees , has been chosen as a benchmark for the model. The different approaches proposed in the literature for the prediction of this property have been reconsidered from a general perspective. The advantages of RecNN as a suitable tool for the automatization of fundamental parts of the QSPR/QSAR analysis have been highlighted. The RecNN model has been applied to the analysis of the Delta(solv)G degrees in water of 138 monofunctional acyclic organic compounds and tested on an external data set of 33 compounds. As a result of the statistical analysis, we obtained, for the predictive accuracy estimated on the test set, correlation coefficient R = 0.9985, standard deviation S = 0.68 kJ mol(-1), and mean absolute error MAE = 0.46 kJ mol(-1). The inherent ability of RecNN to abstract chemical knowledge through the adaptive learning process has been investigated by principal components analysis of the internal representations computed by the network. It has been found that the model recognizes the chemical compounds on the basis of a nontrivial combination of their chemical structure and target property.

Journal Article↗
PubMed2002

Representation of memory for order of mental operations in cognitive tasks.

Recent research shows that people learning a cognitive task acquire a memory for the order of operations applied, independent of the data to which those operations were applied. We designed two experiments to show how this sequence memory is represented. Experiment 1 compared predictions based on 3 possible sequence representation methods: composition, dyad transition, and associative chain. Latency and error results from a simple sequential task supported the associative chain representation. The associative links between operations presumably enhance performance by priming subsequent operations but do not operate in an all-or-none fashion. Experiment 2 explored whether transfer items that matched the first 2 rules and first 3 elements of a training item could bias participants toward executing a composed production learned during training. Latency and undetected error results were consistent with an associative chain representation but not with additional predictions made by the composition representation. These two experiments support the representation of operation sequences in memory as an associative chain.

Adult↗
PubMed2006

The representation of information about faces in the temporal and frontal lobes.

Neurophysiological evidence is described showing that some neurons in the macaque inferior temporal visual cortex have responses that are invariant with respect to the position, size and view of faces and objects, and that these neurons show rapid processing and rapid learning. Which face or object is present is encoded using a distributed representation in which each neuron conveys independent information in its firing rate, with little information evident in the relative time of firing of different neurons. This ensemble encoding has the advantages of maximising the information in the representation useful for discrimination between stimuli using a simple weighted sum of the neuronal firing by the receiving neurons, generalisation and graceful degradation. These invariant representations are ideally suited to provide the inputs to brain regions such as the orbitofrontal cortex and amygdala that learn the reinforcement associations of an individual's face, for then the learning, and the appropriate social and emotional responses, generalise to other views of the same face. A theory is described of how such invariant representations may be produced in a hierarchically organised set of visual cortical areas with convergent connectivity. The theory proposes that neurons in these visual areas use a modified Hebb synaptic modification rule with a short-term memory trace to capture whatever can be captured at each stage that is invariant about objects as the objects change in retinal view, position, size and rotation. Another population of neurons in the cortex in the superior temporal sulcus encodes other aspects of faces such as face expression, eye gaze, face view and whether the head is moving. These neurons thus provide important additional inputs to parts of the brain such as the orbitofrontal cortex and amygdala that are involved in social communication and emotional behaviour. Outputs of these systems reach the amygdala, in which face-selective neurons are found, and also the orbitofrontal cortex, in which some neurons are tuned to face identity and others to face expression. In humans, activation of the orbitofrontal cortex is found when a change of face expression acts as a social signal that behaviour should change; and damage to the orbitofrontal cortex can impair face and voice expression identification, and also the reversal of emotional behaviour that normally occurs when reinforcers are reversed.

Animals↗
PubMed2007

Evaluation of an intelligent tutoring system in pathology: effects of external representation on performance gains, metacognition, and acceptance.

OBJECTIVE: Determine effects of computer-based tutoring on diagnostic performance gains, meta-cognition, and acceptance using two different problem representations. Describe impact of tutoring on spectrum of diagnostic skills required for task performance. Identify key features of student-tutor interaction contributing to learning gains. DESIGN: Prospective, between-subjects study, controlled for participant level of training. Resident physicians in two academic pathology programs spent four hours using one of two interfaces which differed mainly in external problem representation. The case-focused representation provided an open-learning environment in which students were free to explore evidence-hypothesis relationships within a case, but could not visualize the entire diagnostic space. The knowledge-focused representation provided an interactive representation of the entire diagnostic space, which more tightly constrained student actions. MEASUREMENTS: Metrics included results of pretest, post-test and retention-test for multiple choice and case diagnosis tests, ratios of performance to student reported certainty, results of participant survey, learning curves, and interaction behaviors during tutoring. RESULTS: Students had highly significant learning gains after one tutoring session. Learning was retained at one week. There were no differences between the two interfaces in learning gains on post-test or retention test. Only students in the knowledge-focused interface exhibited significant metacognitive gains from pretest to post-test and pretest to retention test. Students rated the knowledge-focused interface significantly higher than the case-focused interface. CONCLUSIONS: Cognitive tutoring is associated with improved diagnostic performance in a complex medical domain. The effect is retained at one-week post-training. Knowledge-focused external problem representation shows an advantage over case-focused representation for metacognitive effects and user acceptance.

Attitude to Computers↗
PubMed2005

Item organization in three-dimensional space and their discriminability in a mouse operant behavioral task.

In order to study spatial cognition as well as operant/instrumental conditioning or attention processes in the same experimental context in mice, we have designed and constructed an operant chamber that contains a large number of nose poke holes distributed over its inner walls. The nose poke holes were placed three in a horizontal row on one left wall, five in a form of an X on the front wall, and three in a vertical column on one right wall in a hexagonal shaped chamber. This organization of nose poke holes was intended to provide mice with spatially structured environmental cues. Here, we report on an experiment in which providing additional structuring to the standard condition, favoring either further spatial grouping or perceptual/visual clustering of subsets of holes, tremendously facilitated nose poke discrimination learning in normal C57BL/6 mice. More interestingly, mice were able to use their (spatial or mental) representation of holes organization elaborated under spatially or visually structured environment, to improve their learning of a new discrimination under the standard less-structured environment. These findings support the idea that mice are sensitive to subtle visual background information, in addition to spatial information, to organize nose poke items, process similar to both pattern separation and chunking process, in order to minimize interference and to increase items discriminability and their capacity for (long-term) memory.

Analysis of Variance↗
PubMed2002

No evidence for overshadowing or facilitation of spatial pattern learning by visual cues.

Two experiments were conducted to examine the effects of redundant and relevant visual cues on spatial pattern learning. Rats searched for hidden food items on the tops of poles that formed a square (Experiment 1) or a checkerboard (Experiment 2) pattern. The experimental groups were trained with visual cues that specified the locations of the baited poles. All groups were tested without visual cues so that any overshadowing or facilitation of spatial pattern learning by visual cues could be detected. Spatial choices were controlled by the spatial pattern and by the visual cues in both experiments. However, there was no evidence of overshadowing or facilitation of spatial pattern learning by visual cues in either experiment. The results are consistent with the idea that the representation of the spatial pattern that guides choices is not controlled by the same learning processes as those that produce associations between visual cues and food locations.

Animals↗
PubMed1977

Nonverbal visual short-term memory as a function of age and dimensionality in learning-disabled children.

A serial recognition task was used to compare performance of 2 learning disability age groups with 2- and 3-dimensional representations of nonlabeled 8-point random shapes. Age-related increases in short-term memory (STM) performance for both dimensions were found. No significant differences were found between 2- or 3-dimensional stimuli. Contrary to reports of STM performance with normal children, learning-disabled children showed no primacy effect for the 2-dimensional treatment, and second choices were not consistently correct when the first choice was incorrect, These findings were interpreted according to Flavell's notions of mediational inefficiencies.

Age Factors↗
PubMed2003

Motor learning processes in a movement-scaling task in olivopontocerebellar atrophy and Parkinson's disease.

Nine Parkinson's disease (PD), seven olivopontocerebellar atrophy (OPCA) patients and two age-matched control groups learned a linear arm movement-scaling task over 2 days, requiring movements proportional in length to visually presented target-bars. Scaling was acquired through knowledge of results (KR concerning the direction and magnitude of errors) following every second acquisition trial. Initial acquisition of both groups was significantly worse than their respective controls (poorer movement scaling), but rapidly improved to nearly identical levels. Retention for the PD group's movement scaling was as good as controls initially, but markedly poorer after 24 h. The OPCA group did not show this deficit. Both patient groups extrapolated accurately to longer, previously unpracticed target distances (no KR provided), suggesting an unimpaired capacity to generate and use an internal representation of the movement scaling. They also rapidly learned a new scaling relationship when the gain was changed. Overall, the learning of this movement-scaling task was not adversely affected in OPCA, and the impairment was restricted primarily to longer-term retention in PD. The study suggests that: (1) the ability to acquire movement scaling in a task that requires conscious use of error feedback and no new coordination may depend little on the cerebellum, and (2) the basal ganglia may participate in longer-term storage of scaling information.

Adult↗
PubMed2000

Minimizing binding errors using learned conjunctive features.

We have studied some of the design trade-offs governing visual representations based on spatially invariant conjunctive feature detectors, with an emphasis on the susceptibility of such systems to false-positive recognition errors-Malsburg's classical binding problem. We begin by deriving an analytical model that makes explicit how recognition performance is affected by the number of objects that must be distinguished, the number of features included in the representation, the complexity of individual objects, and the clutter load, that is, the amount of visual material in the field of view in which multiple objects must be simultaneously recognized, independent of pose, and without explicit segmentation. Using the domain of text to model object recognition in cluttered scenes, we show that with corrections for the nonuniform probability and nonindependence of text features, the analytical model achieves good fits to measured recognition rates in simulations involving a wide range of clutter loads, word size, and feature counts. We then introduce a greedy algorithm for feature learning, derived from the analytical model, which grows a representation by choosing those conjunctive features that are most likely to distinguish objects from the cluttered backgrounds in which they are embedded. We show that the representations produced by this algorithm are compact, decorrelated, and heavily weighted toward features of low conjunctive order. Our results provide a more quantitative basis for understanding when spatially invariant conjunctive features can support unambiguous perception in multiobject scenes, and lead to several insights regarding the properties of visual representations optimized for specific recognition tasks.

Artificial Intelligence↗
PubMed1982

The role of visual monitoring in observational learning of action patterns: making the unobservable observable.

The present experiment tested the hypothesis that concurrent visual feedback enhances observational learning of a novel action pattern that normally would be unobservable. Subjects repeatedly enacted a modeled action pattern with visual monitoring of their reproductions throughout enactments, during only early or late phases of enactment, or not at all. At periodic intervals the adequacy of their conception of the modeled pattern was also measured. Visual feedback during ongoing performance enhanced accurate reproduction of the modeled pattern; the facilitative effect was most pronounced for reproduction of complex response components. The superiority of subjects who had enacted these difficult response components with visual feedback was maintained even when both the model and feedback were withdrawn. Visual feedback did not facilitate accurate enactment of the modeled pattern before development of an adequate cognitive representation of it. The results support the social learning view that observationally-learned behaviors are cognitively represented and that visual monitoring serves to decrease discrepancies between conception and action.

Journal Article↗
PubMed1985

Psychophysical evidence for a shared representational medium for mental images and percepts.

The intuition that imagery is similar to perception has led many psychologists to assume that imaging an object consists of activating some of the same representational structures that are activated during the perception of that object. This assumption was tested by measuring the effects of visual imagery on concurrent visual perception. The experimental task consisted of a two-interval forced-choice detection task (no stimulus identification required) during which the subject imaged a particular stimulus. In Experiment 1, a matching image led to better detection than a nonmatching image. Interactions between imagery and perception imply a common locus of activity, and the content-specific interactions obtained here imply that the common locus consists of representational structures. In Experiment 2, a matching image facilitated perception only when the image and the stimulus were in the same position. This was taken to imply that the shared representational structures occur at an analog level of perceptual representation.

Discrimination Learning↗
PubMed1999

Phonology, reading acquisition, and dyslexia: insights from connectionist models.

The development of reading skill and bases of developmental dyslexia were explored using connectionist models. Four issues were examined: the acquisition of phonological knowledge prior to reading, how this knowledge facilitates learning to read, phonological and nonphonological bases of dyslexia, and effects of literacy on phonological representation. Compared with simple feedforward networks, representing phonological knowledge in an attractor network yielded improved learning and generalization. Phonological and surface forms of developmental dyslexia, which are usually attributed to impairments in distinct lexical and nonlexical processing "routes," were derived from different types of damage to the network. The results provide a computationally explicit account of many aspects of reading acquisition using connectionist principles.

Child↗
PubMed1992

Cognitive mechanisms of face processing.

Evidence from natural and induced errors of face recognition, from the effects of different cues on resolving errors, and from the latencies to make different decisions about seen faces, all suggest that familiar face recognition involves a fixed, invariant sequence of stages. To recognize a familiar face, a perceptual description of a seen face must first activate a long-standing representation of the appearance of the face of the familiar person. 'Semantic' knowledge about such things as the person's occupation and personality are accessed next, followed, in the final stage, by the name. Certain factors affect the ease of familiar face recognition. Faces seen in the recent past are recognized more readily (repetition priming), as are distinctive faces, and faces preceded by those of related individuals (associative priming). Our knowledge of these phenomena is reviewed for the light it can shed upon the mechanisms of face recognition. Four aspects of face recognition--graded similarity effects and part-to-whole completion in repetition priming, prototype extraction with simultaneous retention of information about individual exemplars, and distinctiveness effects in classification and identification--are proposed as being compatible with distributed memory accounts of cognitive representations.

Association Learning↗
PubMed2005

Learning places from views: variation in scene processing as a function of experience and navigational ability.

Humans and animals use information obtained from different viewpoints to form representations of the spatial structure of the world. We used functional magnetic resonance imaging (fMRI) adaptation to investigate the neural basis of this learning process and to show how the concomitant representations vary across individuals as a function of navigational ability. In particular, we examined the effect of repeating viewpoint and/ or place information over both short (within-trial) and long (across-scan) intervals on the neural response in scene processing regions. Short-term fMRI adaptation effects in the parahippocampal cortex were initially highly viewpoint-specific but became less so over time. Long-term fMRI repetition effects included a significant viewpoint-invariant component. When individual differences in navigational ability were considered, a significant correlation between the strength of these effects and self-reported navigational competence was observed. In particular, good navigators encoded representations that differed between new and old views and new and old places, whereas bad navigators did not. These results suggest that cortical scene representations evolve over time to become more viewpoint-invariant and that the quality of these representations directly impacts navigational ability.

Adult↗
PubMed2006

Generalization in perceptual learning for speech.

Lexical context strongly influences listeners' identification of ambiguous sounds. For example, a sound midway between /f/ and /s/ is reported as /f/ in "sheri_," but as /s/ in "Pari_." Norris, McQueen, and Cutler (2003) have demonstrated that after hearing such lexically determined phonemes, listeners expand their phonemic categories to include more ambiguous tokens than before. We tested whether listeners adjust their phonemic categories for a specific speaker. Do listeners learn a particular speaker's "accent"? Similarly, we examined whether perceptual learning is specific to the particular ambiguous phonemes that listeners hear, or whether the adjustments generalize to related sounds. Participants heard ambiguous /d/ or /t/ phonemes during a lexical decision task. They then categorized sounds on /d/-/t/ and /b/-/p/ continua, either in the same voice that they had heard for lexical decision, or in a different voice. Perceptual learning generalized across both speaker and test continua: Changes in perceptual representations are robust and broadly tuned.

Decision Making↗
PubMed1998

Induction of relational schemas: common processes in reasoning and complex learning.

Five experiments were performed to test whether participants induced a coherent representation of the structure of a task, called a relational schema, from specific instances. Properties of a relational schema include: An explicit symbol for a relation, a binding that preserves the truth of a relation, potential for higher-order relations, omnidirectional access, potential for transfer between isomorphs, and ability to predict unseen items in isomorphic problems. However relational schemas are not necessarily coded in abstract form. Predictions from relational schema theory were contrasted with predictions from configural learning and other nonstructural theories in five experiments in which participants were taught a structure comprised of a set of initial-state,operator-->end-state instances. The initial-state,operator pairs were presented and participants had to predict the correct end-state. Induction of a relational schema was achieved efficiently by adult participants as indicated by ability to predict items of a new isomorphic problem. The relational schemas induced showed the omnidirectional access property, there was efficient transfer to isomorphs, and structural coherence had a powerful effect on learning. The "learning to learn" effect traditionally associated with the learning set literature was observed, and the long-standing enigma of learning set acquisition is explained by a model composed of relational schema induction and structure mapping. Performance was better after reversal of operators than after shift to an alternate structure, even though the latter entailed more overlap with previously learned tasks in terms of the number of configural associations that were preserved. An explanation for the reversal shift phenomenon in terms of induction and mapping of a relational schema is proposed. The five experiments provided evidence supporting predictions from relational schema theory, and no evidence was found for configural or nonstructural learning theories.

Adult↗