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 289 records · Page 16Linked to original sources
PubMed2001

The neural basis of perceptual learning.

Perceptual learning is a lifelong process. We begin by encoding information about the basic structure of the natural world and continue to assimilate information about specific patterns with which we become familiar. The specificity of the learning suggests that all areas of the cerebral cortex are plastic and can represent various aspects of learned information. The neural substrate of perceptual learning relates to the nature of the neural code itself, including changes in cortical maps, in the temporal characteristics of neuronal responses, and in modulation of contextual influences. Top-down control of these representations suggests that learning involves an interaction between multiple cortical areas.

Action Potentials↗
PubMed1995

Syntactic cues in the acquisition of collective nouns.

One basic finding in the study of word learning is that children tend to construe a word describing an object as referring to the kind of whole object, rather than to a part of the object, one of its properties, or the substance it is made of. This has been taken as evidence that there exist certain special constraints on word meaning that guide children to favor the kind-of-object interpretation when exposed to a new word. There are descriptive problems with this proposal, however, as it cannot explain how children learn other kinds of words, such as names for specific people, substances, parts, events, collections, and periods of time. These problems motivate an alternative theory in which young children possess several distinct conceptual categories--including "individual", which is more abstract than "whole object"--and can use syntactic cues to determine the conceptual category that a new word belongs to. This theory is explored in two experiments in which we attempt to use syntactic cues to teach children and adults novel collective nouns--words that refer to groups of objects. The results indicate that children can use such cues to learn names for kinds of individuals that are not whole objects, although they are less able to do so than adults. Candidate explanations for why this developmental difference exists are discussed and implications are drawn for theories of word learning and conceptual representation.

Adult↗
PubMed2005

Artificial neural networks for document analysis and recognition.

Artificial neural networks have been extensively applied to document analysis and recognition. Most efforts have been devoted to the recognition of isolated handwritten and printed characters with widely recognized successful results. However, many other document processing tasks, like preprocessing, layout analysis, character segmentation, word recognition, and signature verification, have been effectively faced with very promising results. This paper surveys the most significant problems in the area of offline document image processing, where connectionist-based approaches have been applied. Similarities and differences between approaches belonging to different categories are discussed. A particular emphasis is given on the crucial role of prior knowledge for the conception of both appropriate architectures and learning algorithms. Finally, the paper provides a critical analysis on the reviewed approaches and depicts the most promising research guidelines in the field. In particular, a second generation of connectionist-based models are foreseen which are based on appropriate graphical representations of the learning environment.

Algorithms↗
PubMed2001

Implicit learning of sequences of tasks.

Task sets can be configured in advance of performing a new task. However, the degree to which advance information is actually used for advance configuration depends on the nature of the available information. The role of implicit learning was explored in 2 experiments by means of a modified serial reaction time task with repeated sequences of 4 dimensionally organized tasks. Although there was clear evidence for implicit learning of the sequence (of length 8), the learning was not associated with a reduction of shift costs, either with a short (200 ms) or with a long (1,200 ms) response-stimulus interval. In contrast, a reduction of shift costs was observed when external precues were introduced in a 3rd experiment. According to these results, the sequences of stimulus features that serve as cues for the tasks to perform on the stimuli are learned, but the representation of the features is void of their task-associated meanings.

Adult↗
PubMed2006

Roles of egocentric and allocentric spatial representations in locomotion and reorientation.

Four experiments investigated the nature of spatial representations used in locomotion. Participants learned the layout of several objects and then pointed to the objects while blindfolded in 3 conditions: before turning (baseline), after turning to a new heading (updating), and after disorientation (disorientation). The internal consistency of pointing in the disorientation condition was relatively high and equivalent to that in the baseline and updating conditions, when the layout had salient intrinsic axes and the participants learned the locations of the objects on the periphery of the layout. The internal consistency of pointing was disrupted by disorientation when participants learned the locations of objects while standing amid them and the layout did not have salient intrinsic axes. It was also observed that many participants retrieved spatial relations after disorientation from the original learning heading. These results indicate that people form an allocentric representation of object-to-object spatial relations when they learn the layout of a novel environment and use that representation to locate objects around them. Egocentric representations may be used to locate objects when allocentric representations are not of high fidelity.

Confusion↗
PubMed2003

Toxicology analysis by means of the JSM-method.

MOTIVATION: A model for learning potential causes of toxicity from positive and negative examples and predicting toxicity for the dataset used in the Predictive Toxicology Challenge (PTC) is presented. The learning model assumes that the causes of toxicity can be given as substructures common to positive examples that are not substructures of negative examples. This assumption results in the choice of a learning model, called the JSM-method, and a language for representing chemical compounds, called the Fragmentary Code of Substructure Superposition (FCSS). By means of the latter, chemical compounds are represented as sets of substructures which are 'biologically meaningful' from the expert point of view. RESULTS: The chosen learning model and representation language show comparatively good performance for the PTC dataset: for three sex/species groups the predictions were ROC optimal, for one group the prediction was nearly optimal. The predictions tend to be conservative (few predictions and almost no errors), which can be explained by the specific features of the learning model. AVAILABILITY: by request to finn@viniti.ru; serge@viniti.ru, http://ki-www2.intellektik.informatik.tu-darmstadt.de/~jsm/QDA.

Algorithms↗
PubMed2000

Computational principles of learning in the neocortex and hippocampus.

We present an overview of our computational approach towards understanding the different contributions of the neocortex and hippocampus in learning and memory. The approach is based on a set of principles derived from converging biological, psychological, and computational constraints. The most central principles are that the neocortex employs a slow learning rate and overlapping distributed representations to extract the general statistical structure of the environment, while the hippocampus learns rapidly, using separated representations to encode the details of specific events while suffering minimal interference. Additional principles concern the nature of learning (error-driven and Hebbian), and recall of information via pattern completion. We summarize the results of applying these principles to a wide range of phenomena in conditioning, habituation, contextual learning, recognition memory, recall, and retrograde amnesia, and we point to directions of current development.

Hippocampus↗
PubMed1999

Automatically deriving readers' knowledge structures from texts.

Latent semantic analysis (LSA) serves as both a theory and a method for representing the meaning of words based on a statistical analysis of their contextual usage (Foltz, 1996; Landauer & Dumais, 1997). In experiments in the domains of psychology and history, we compared the representation of readers' knowledge structures of information learned from texts with the representation generated by LSA. Results indicated that LSA's representation is similar to readers' representations. In addition, the degree to which the reader's representation is similar to LSA's representation is indicative of the amount of knowledge the reader has acquired and of the reader's reading ability. This approach has implications both as a model of learning from text and as a practical tool for performing knowledge assessment.

Humans↗
PubMed1995

Learning mechanisms in the temporal lobe visual cortex.

Neurophysiological experiments are described which show that neurons form ensemble encoded representations of stimuli such as faces which are relatively invariant with respect to size, contrast, spatial frequency, translation, and view. It is shown that new representations of objects can be formed with less than 5 s of visual experience with those objects. Mechanisms by which the brain could perform this invariant recognition, and learn the representations required for recognition, are described. A neural network simulation of these mechanisms for learning invariant representations is then described. The model uses a multistage feed-forward architecture, and is able to learn invariant representations of objects including faces by use of a Hebbian synaptic modification rule which incorporates a short memory trace (0.5 s) of preceding activity. This trace rule enables the network to learn the properties of objects which are spatio-temporally invariant over this time scale.

Animals↗
PubMed1996

Landmark stability: studies exploring whether the perceived stability of the environment influences spatial representation.

To investigate whether spatial learning complies with associative learning theories or with theories of cognitive mapping, rats were trained in three experiments exploring the effect of variations in spatial predictive relationships. In experiment 1, it was found that making one of two landmarks the sole spatial predictor of reward, by varying the spatial relationship between reward and other cues, reduced the control over search exerted by that landmark compared with that observed when the landmark and context cues were both reliable predictors of reward location. This requirement for landmark stability rather than predictive power appears to contradict results obtained in conventional conditioning paradigms. Discrimination learning was unaffected, suggesting a dissociation between discrimination and spatial learning with respect to the influence of geometric stability. Further experiments used arrays of both single and multiple landmarks. Experiment 2 revealed that the stability of a single landmark improved accuracy of search, but also showed that local stability between a pair of landmarks that moved around the arena together was sufficient to support spatial learning. Experiment 3 examined landmark stability using fixed directional cues in the absence of vestibular disorientation. This also revealed a relative advantage of stable landmarks, but animals presented with a landmark that moved from trial to trial did show some evidence of learning. Parametric manipulation of landmark stability offers an intriguing way of influencing the process of spatial representation and thus understanding better the processes through which egocentric representations of perceived space are transformed into allocentric representations of the real world.

Journal Article↗
PubMed2000

Learning cortical topography from spatiotemporal stimuli.

Stimulus representation is a functional interpretation of early sensory cortices. Early sensory cortices are subject to stimulus-induced modifications. Common models for stimulus-induced learning within topographic representations are based on the stimuli's spatial structure and probability distribution. Furthermore, we argue that average temporal stimulus distances reflect the stimuli's relatedness. As topographic representations reflect the stimuli's relatedness, the temporal structure of incoming stimuli is important for the learning in cortical maps. Motivated by recent neurobiological findings, we present an approach of cortical self-organization that additionally takes temporal stimulus aspects into account. The proposed model transforms average interstimulus intervals into representational distances. Thereby, neural topography is related to stimulus dynamics. This offers a new time-based interpretation of cortical maps. Our approach is based on a wave-like spread of cortical activity. Interactions between dynamics and feedforward activations lead to shifts of neural activity. The psychophysical saltation phenomenon may represent an analogue to the shifts proposed here. With regard to cortical plasticity, we offer an explanation for neurobiological findings that other models cannot explain. Moreover, we predict cortical reorganizations under new experimental, spatiotemporal conditions. With regard to psychophysics, we relate the saltation phenomenon to dynamics and interaction in early sensory cortices and predict further effects in the perception of spatiotemporal stimuli.

Animals↗
PubMed2005

Perceptual learning for speech: Is there a return to normal?

Recent work on perceptual learning shows that listeners' phonemic representations dynamically adjust to reflect the speech they hear (Norris, McQueen, & Cutler, 2003). We investigate how the perceptual system makes such adjustments, and what (if anything) causes the representations to return to their pre-perceptual learning settings. Listeners are exposed to a speaker whose pronunciation of a particular sound (either /s/ or /integral/) is ambiguous (e.g., halfway between /s/ and /integral/). After exposure, participants are tested for perceptual learning on two continua that range from /s/ to /integral/, one in the Same voice they heard during exposure, and one in a Different voice. To assess how representations revert to their prior settings, half of Experiment 1's participants were tested immediately after exposure; the other half performed a 25-min silent intervening task. The perceptual learning effect was actually larger after such a delay, indicating that simply allowing time to pass does not cause learning to fade. The remaining experiments investigate different ways that the system might unlearn a person's pronunciations: listeners hear the Same or a Different speaker for 25 min with either: no relevant (i.e., 'good') /s/ or /integral/ input (Experiment 2), one of the relevant inputs (Experiment 3), or both relevant inputs (Experiment 4). The results support a view of phonemic representations as dynamic and flexible, and suggest that they interact with both higher- (e.g., lexical) and lower-level (e.g., acoustic) information in important ways.

Adaptation, Psychological↗
PubMed1990

Expectancies of reinforcer location and quality as cues for a conditional discrimination in pigeons.

Experiment 1 demonstrated that reliably correlating different reinforcer locations (top vs. bottom) with sample stimuli markedly enhanced the performance of White Carneaux pigeons in a spatial conditional discrimination. This differential outcome effect was more evident at longer retention intervals. In Experiment 2, pigeons were given the opportunity to learn about two redundant reinforcer features--location (top vs. bottom) and quality (grain vs. chow). Which reinforcer feature exerted control over choosing depended on task structure. In the congruent task, where pecks to the top key operated the top feeder and pecks to the bottom key operated the bottom feeder, reinforcer location exerted predominant control. In the incongruent task, where pecks to the top key operated the bottom feeder and vice versa, reinforcer quality exerted exclusive control. These results have implications for the nature of reinforcer representations in instrumental learning.

Animals↗
PubMed2025

ASGCL: Adaptive Sparse Mapping-based graph contrastive learning network for cancer drug response prediction.

Personalized cancer drug treatment is emerging as a frontier issue in modern medical research. Considering the genomic differences among cancer patients, determining the most effective drug treatment plan is a complex and crucial task. In response to these challenges, this study introduces the Adaptive Sparse Graph Contrastive Learning Network (ASGCL), an innovative approach to unraveling latent interactions in the complex context of cancer cell lines and drugs. The core of ASGCL is the GraphMorpher module, an innovative component that enhances the input graph structure via strategic node attribute masking and topological pruning. By contrasting the augmented graph with the original input, the model delineates distinct positive and negative sample sets at both node and graph levels. This dual-level contrastive approach significantly amplifies the model's discriminatory prowess in identifying nuanced drug responses. Leveraging a synergistic combination of supervised and contrastive loss, ASGCL accomplishes end-to-end learning of feature representations, substantially outperforming existing methodologies. Comprehensive ablation studies underscore the efficacy of each component, corroborating the model's robustness. Experimental evaluations further illuminate ASGCL's proficiency in predicting drug responses, offering a potent tool for guiding clinical decision-making in cancer therapy.

Humans↗
PubMed1995

Administration of glutamate following a reminder induces transient memory loss in day-old chicks.

Monosodium glutamate (4.0 mM) administered immediately after a visual reminder presented to day-old chickens between 7.5 min and 24 h following a single trial passive avoidance learning task produced transient losses of memory on retention test, an effect not observed in the absence of a reminder or when the reminder was given 48 h post-learning. The duration of the transient deficit decreased with increasing interval between the training and the reminder trial. The time of onset of memory loss after the reminder trial appeared to increase with increasing interval between the training and the reminder trials. The results suggest that, for a period of at least up to 24 h after passive avoidance training, retrieval of memory may lead to processes which are sensitive to inhibition by glutamate, with the duration of sensitivity post-retrieval decreasing as the period of memory consolidation increases. The results extend previously reported findings with rodents and suggest the possibility that consolidation of a stable memorial representation of a learning experience may take place over several days and may entail the concurrent laying down of a stable retrieval mechanism.

Animals↗