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 1,063 records · Page 59Linked to original sources
PubMed1994

Acquisition of color opponent representation by a three-layered neural network model.

This paper discusses color representation in the visual system by analysis of a three-layered neural network model. The model incorporates physiological knowledge of color representation at the sensor level (broad-band trichromatic representation by cones) and the higher level (narrow-band color representation by color-coded cells in V4). We trained the model to perform a mapping between these color representations by the back propagation algorithm and analyzed the acquired characteristics of the hidden units. It turned out that the hidden units learned characteristics similar to those of the color opponent cells found in the visual system. It was concluded that the R-G and Y-B color opponent representations reflect the efficiency of the color representation in the visual system from investigations on the efficiency of color representation in the hidden layer and on the capability of the color recognition task of the model.

Color Perception↗
PubMed1999

How does the cerebral cortex work? Learning, attention, and grouping by the laminar circuits of visual cortex.

The organization of neocortex into layers is one of its most salient anatomical features. These layers include circuits that form functional columns in cortical maps. A major unsolved problem concerns how bottom-up, top-down, and horizontal interactions are organized within cortical layers to generate adaptive behaviors. This article models how these interactions help visual cortex to realize: (i) the binding process whereby cortex groups distributed data into coherent object representations; (ii) the attentional process whereby cortex selectively processes important events; and (iii) the developmental and learning processes whereby cortex shapes its circuits to match environmental constraints. New computational ideas about feedback systems suggest how neocortex develops and learns in a stable way, and why top-down attention requires converging bottom-up inputs to fully activate cortical cells, whereas perceptual groupings do not.

Attention↗
PubMed1991

Interference and the representation of events in memory.

Most current models of memory predict that the presence of increasingly well-learned, or strong, items in memory will cause increasing interference. This phenomenon, the list-strength effect, occurs as predicted when memory is tested by free recall but not when a recognition test is used. Four experiments use end-of-session testing to demonstrate that redistribution of storage time or effort from strong to weak items on mixed lists does not occur and therefore cannot be masking interference by strong items. Delay between study and test is found to cause memory loss independent of the basic list-strength findings. It is concluded that the presence of strong items in memory does not interfere with recognition performance and that interference is due to failures of retrieval rather than to composition or other forms of destructive interaction during storage.

Analysis of Variance↗
PubMed2026

Machine learning-driven spleen imaging and genomics uncover a splenic connection to coronary artery disease.

Despite advances in managing traditional risk factors, coronary artery disease (CAD) remains the leading cause of mortality. Circulating hematopoietic cells influence risk for CAD separately from traditional risk factors, but the role of a key regulating organ, the spleen, is unknown. The understudied spleen is a representation of the hematopoietic system optimally suited for unbiased radiologic investigations toward mechanistic insights. Here, we leveraged deep learning to extract 107 splenic radiomic features from abdominal magnetic resonance imaging (MRI) scans of 42,059 UK Biobank participants and of 2745 Mass General Brigham Biobank (MGBB) participants. Of these, 10 features from UK Biobank were associated with CAD. Genome-wide association analysis of CAD-associated features identified 219 loci, including 9p21. Variants at 9p21, the strongest yet mechanistically elusive CAD locus, were associated with splenic features such as run-length nonuniformity, reflecting heterogeneity of continuous texture regions. Research MRI findings were consistent internally, but external clinical validation highlighted challenges in translating analyses of abdominal MRI scans to routine clinical practice because of variability in imaging protocols and greater clinical heterogeneity among patients. Our study, combining deep learning with genomics, presents a framework to uncover potential splenic involvement in CAD and emphasizes translational gaps between research and clinical radiomics.

Humans↗
PubMed1984

Learning about school: the development of kindergartners' school scripts.

This research examined the development of a general event representation and the relationship between general and specific event memories. Kindergarten children were interviewed about the school-day routine 4 times during the first 3 months of school. Even on the second day of school, children's reports were general and well organized, and the organization remained stable over time. With increasing experience, children reported more acts and more conditional statements, indicating that the representation became more elaborate and more temporally complex over time. Furthermore, children shared a remarkably common representation of the routine. All children tended to mention those acts that occupied a particular time and place in the classroom, and each of these acts seemed to encompass a list of possible activities in a hierarchic fashion. In contrast to the ease with which children reported the general routine, children had difficulty recalling specific episodes of the day before at all 4 interviews. These results indicate that children represent an event as a general spatial-temporal framework based on the first experience with a new routine; this framework becomes more elaborate and the temporal and the hierarchical organization of the representation becomes more complex with increasing experience with the event.

Child Development↗
PubMed2004

Behavioral studies of the olivocochlear efferent system: learning to listen in noise.

BACKGROUND: Olivocochlear (OC) neurons make up an efferent, descending auditory system that returns sound representations to the inner ear soon after they have entered the brain. Efferent inputs into the cochlea modulate outer hair cell activity to improve the neural encoding of auditory signals in background noise. Based on this physiological evidence, loss of efferent feedback is expected to degrade perception in noise. Attempts to confirm this prediction with long-term audiological assessments have met with mixed results. OBJECTIVE: To isolate procedural factors that may diminish the demonstration of long-term OC deficits in listening tasks. DESIGN: Operant conditioning procedures were used to train domestic cats to signal a change in the location of an auditory stimulus by responding on a lever. The smallest detectable change in location was measured by manipulating the distance between speakers under quiet conditions and in the presence of background noise. Functional consequences of efferent feedback were evaluated by comparing the sound localization thresholds of OC-lesioned cats with normal controls. RESULTS: As predicted by the hypothesized function of OC feedback systems, the lesioned cats exhibited significantly elevated thresholds only when tested in background noise. This initially poor performance returned to normal values after long-term exposure to the testing procedure. CONCLUSIONS: The results of our animal studies support the OC enhancement of sound localization behavior in background noise. Also, our behavioral observations suggest the acquisition of alternate listening strategies that allowed lesioned cats to minimize the functional consequences of their auditory deficits by attending more closely to remaining directional cues. These learned compensatory behaviors were encouraged by our present experimental design, which incorporated long-term training under consistent stimulus conditions. These findings point out the potential limitations of the highly routine audiological procedures that have been used to assess the impact of OC feedback on human hearing.

Animals↗
PubMed2005

Learning-induced plasticity in animal and human auditory cortex.

Recent data on learning-related changes in animal and human auditory cortex indicate functions beyond mere stimulus representation and simple recognition memory for stimuli. Rather, auditory cortex seems to process and represent stimuli in a task-dependent fashion. This implies plasticity in neural processing, which can be observed at the level of single neuron firing and the level of spatiotemporal activity patterns in cortical areas. Auditory cortex is a structure in which behaviorally relevant aspects of stimulus processing are highly developed because of the fugitive nature of auditory stimuli.

Acoustic Stimulation↗
PubMed2001

Abstract coherent categories.

Many studies have demonstrated the importance of the knowledge that interrelates features in people's mental representation of categories and that makes our conception of categories coherent. This article focuses on abstract coherent categories, coherent categories that are also abstract because they are defined by relations independently of any features. Four experiments demonstrate that abstract coherent categories are learned more easily than control categories with identical features and statistical structure, and also that participants induced an abstract representation of the category by granting category membership to exemplars with completely novel features. The authors argue that the human conceptual system is heavily populated with abstract coherent concepts, including conceptions of social groups, societal institutions, legal, political, and military scenarios, and many superordinate categories, such as classes of natural kinds.

Adult↗
PubMed2003

TV guide: two-year-old children learn to use video as a source of information.

Learning to use symbols is a challenge for young children even when the symbol in question (e.g., a live video image) is iconic and seems transparent to adults. This research examined the effect of experience on children's use of video-presented information. Two-year-old children saw themselves "live" on their family television for 2 weeks and then participated in an object-retrieval task. The children reliably used a live video presentation of an adult hiding a toy in an adjoining room to find the toy. Most also transferred what they learned to a task involving another symbol (pictures) that typically is very difficult for this age group. The results reveal flexibility in 2-year-olds' symbol use that follows from successful representation of a symbolic relation.

Child Development↗
PubMed2003

Bounding the effect of noise in multiobjective learning classifier systems.

This paper analyzes the impact of using noisy data sets in Pittsburgh-style learning classifier systems. This study was done using a particular kind of learning classifier system based on multiobjective selection. Our goal was to characterize the behavior of this kind of algorithms when dealing with noisy domains. For this reason, we developed a theoretical model for predicting the minimal achievable error in noisy domains. Combining this theoretical model for crisp learners with graphical representations of the evolved hypotheses through multiobjective techniques, we are able to bound the behavior of a learning classifier system. This kind of modeling lets us identify relevant characteristics of the evolved hypotheses, such as overfitting conditions that lead to hypotheses that poorly generalize the concept to be learned.

Algorithms↗
PubMed1997

A confirmatory factor analysis of the structure of tacit knowledge in nursing.

The purpose of this study was to examine the structure of tacit knowledge in the nursing profession. Using research in implicit learning and practical intelligence as a theoretical framework, a paper-and-pencil measure of tacit knowledge for nurses was developed and refined. Five models, each representing an established theory of traditional intelligence, were compared in terms of fit to the data. The results of the confirmatory factor analysis suggest that Model 3, a hierarchical model of intelligence, was the most plausible representation of tacit knowledge in nursing. The results indicate that the portion of managerial decision making learned implicitly on the job is mainly accounted for by managing tasks and others. Suggestions for nursing education include teaching effective strategies for managing tasks, such as handling increased workloads, establishing priorities, and delegating responsibility.

Decision Making↗
PubMed1990

Conditions for versatile learning, Helmholtz's unconscious inference, and the task of perception.

It is a mistake to consider perception and learning separately because what one learns is strongly constrained by what one perceives, and what one perceives depends on what one has experienced. I shall propose the hypothesis that perception is the computation of a representation that enables us to make reliable and versatile inferences about associations occurring in the world around us--that is, perception prepares the ground for learning. The statistical problem in learning is to determine whether a compound event such as "C followed by U" is a random co-occurrence or a significant association, for if it is the former it would be a mistake to pay any particular attention to C, whereas if it is the latter C is a conditional stimulus for U and a useful predictor for it. Now you cannot decide whether the association is random or not without knowledge of the prior probabilities of C and U: hence on my hypothesis when you perceive an object or event the representation must not only signal "it's there" or "it's happened", but must also make evident (or rapidly accessible) the prior probability of what has been signalled. Furthermore it must do this for all the objects or events that can act as conditional stimuli, and this implies that the representative elements should be statistically independent (or approximately so) in the normal environment. Forms of coding that would do this, and the relationship with Helmholtz's unconscious inference, will be discussed. These considerations imply that the task performed in perception has been overlooked both by learning theorists and by connectionists working on associative and adaptive networks. Coding for independence may be particularly important in understanding the developmental processes during the sensitive period: it may be the operation that leads ontogenetically-timed, activity-dependent, connections to imprint appropriate codes if the animal has experience, but inappropriate codes without experience.

Adaptation, Physiological↗
PubMed2001

Formal schooling influences two- but not three-dimensional naming skills.

The modulatory influence of literacy on the cognitive system of the human brain has been indicated in behavioral, neuroanatomic, and functional neuroimaging studies. In this study we explored the functional consequences of formal education and the acquisition of an alphabetic written language on two- and three-dimensional visual naming. The results show that illiterate subjects perform significantly worse on immediate naming of two-dimensional representations of common everyday objects compared to literate subjects, both in terms of accuracy and reaction times. In contrast, there was no significant difference when the subjects named the corresponding real objects. The results suggest that formal education and learning to read and to write modulate the cognitive process involved in processing two- but not three-dimensional representations of common everyday objects. Both the results of the reaction time and the error pattern analyses can be interpreted as indicating that the major influence of literacy affects the visual system or the interaction between the visual and the language systems. We suggest that the visual system in a wide sense and/or the interface between the visual and the language system are differently formatted in literate and illiterate subjects. In other words, we hypothesize that the pattern of interactions in the functional-anatomical networks subserving visual naming, that is, the interactions within and between the visual and language processing networks, differ in literate and illiterate subjects.

Aged↗
PubMed1979

Aspects of the reinforcer learned in second-order Pavlovian conditioning.

Four experiments used an autoshaping procedure in pigeons to explore learning about the reinforcer in a second-order conditioning paradigm. Experiment 1 conditioned two visual second-order stimuli (S2), using as reinforcers two visual first-order stimuli (S1), each of which had previously been paired with food. Animals for which the S2 stimuli were each consistently paired with one particular S1 developed second-order responding more rapidly than did animals for which the identity of S1 varied from trial to trial. Moreover, following consistent pairings, extinction of an S1 had a depressive effect upon second-order responding which was peculiar to the S2 with which it had been paired. Both results suggest that in this preparation the organism identifies a particular S1 as the reinforcer for each S2. The remaining experiments examined the details of that identification. A compound S1, itself composed of two separable elements, was used to reinforce an S2. Subsequent extinction of either element of S1 led to a depression in the responding to S2, which indicates that both elements were involved in the second-order conditioning. Moreover, the use of several complex discriminations, which produced different behavior to S1 and to its elements, suggested that the organism had associated the S2 with the compound S1 rather than with its separate elements. However, even complete extinction of the response to S1 left some residual behavior to S2, which indicates that a portion of the second-order conditioning is independent of the current state of the reinforcer. These results demonstrate that in some situations the organism associates a conditioned stimulus with a rich representation of the reinforcer.

Animals↗
PubMed2003

Neural plasticity following auditory training in children with learning problems.

OBJECTIVE: This study examined the plasticity of the central auditory pathway and accompanying cognitive changes in children with learning problems. METHODS: Children diagnosed with a learning disability and/or attention deficit disorder worked with commercial auditory processing training software for 8 weeks; control groups consisted of normal-learning and learning-impaired children who did not participate in any remedial programs. Auditory brainstem function was evaluated in response to click and speech stimuli in quiet; cortical responses to speech stimuli were obtained in quiet and noise. Academic achievement and cognitive abilities were assessed with standardized measures. RESULTS: Compared to controls, the trained group improved on measures of auditory processing and exhibited changes in cortical responses in quiet and in noise. In quiet, cortical responses reflected an accelerated maturational pattern; in background noise, cortical responses became more resistant to degradation. Brainstem responses did not change with training. CONCLUSIONS: Children with learning problems who practiced with auditory training software exhibited plasticity of neural encoding of speech sounds at the cortical, but not subcortical, level of the auditory pathway. This plasticity was accompanied by improvement in behavioral performance. SIGNIFICANCE: This study demonstrates that in learning-impaired children working with commercial auditory processing training programs affects both the perception and the cortical representation of sound.

Achievement↗
PubMed2004

Sleep inspires insight.

Insight denotes a mental restructuring that leads to a sudden gain of explicit knowledge allowing qualitatively changed behaviour. Anecdotal reports on scientific discovery suggest that pivotal insights can be gained through sleep. Sleep consolidates recent memories and, concomitantly, could allow insight by changing their representational structure. Here we show a facilitating role of sleep in a process of insight. Subjects performed a cognitive task requiring the learning of stimulus-response sequences, in which they improved gradually by increasing response speed across task blocks. However, they could also improve abruptly after gaining insight into a hidden abstract rule underlying all sequences. Initial training establishing a task representation was followed by 8 h of nocturnal sleep, nocturnal wakefulness, or daytime wakefulness. At subsequent retesting, more than twice as many subjects gained insight into the hidden rule after sleep as after wakefulness, regardless of time of day. Sleep did not enhance insight in the absence of initial training. A characteristic antecedent of sleep-related insight was revealed in a slowing of reaction times across sleep. We conclude that sleep, by restructuring new memory representations, facilitates extraction of explicit knowledge and insightful behaviour.

Adolescent↗
PubMed1993

Training Japanese listeners to identify English /r/ and /l/. II: The role of phonetic environment and talker variability in learning new perceptual categories.

Two experiments were carried out to extend Logan et al.'s recent study [J. S. Logan, S. E. Lively, and D. B. Pisoni, J. Acoust. Soc. Am. 89, 874-886 (1991)] on training Japanese listeners to identify English /r/ and /l/. Subjects in experiment 1 were trained in an identification task with multiple talkers who produced English words containing the /r/-/l/ contrast in initial singleton, initial consonant clusters, and intervocalic positions. Moderate, but significant, increases in accuracy and decreases in response latency were observed between pretest and posttest and during training sessions. Subjects also generalized to new words produced by a familiar talker and novel words produced by an unfamiliar talker. In experiment 2, a new group of subjects was trained with tokens from a single talker who produced words containing the /r/-/l/ contrast in five phonetic environments. Although subjects improved during training and showed increases in pretest-posttest performance, they failed to generalize to tokens produced by a new talker. The results of the present experiments suggest that variability plays an important role in perceptual learning and robust category formation. During training, listeners develop talker-specific, context-dependent representations for new phonetic categories by selectively shifting attention toward the contrastive dimensions of the non-native phonetic categories. Phonotactic constraints in the native language, similarity of the new contrast to distinctions in the native language, and the distinctiveness of contrastive cues all appear to mediate category acquisition.

Acoustic Stimulation↗