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 1,081 records · Page 60Linked to original sources
PubMed1999

Going digital: image preparation for biomedical publishing.

Authors are more often being held responsible for readying their own data figures for digital publication by scanning them at the proper resolution and preparing them for presentation in both print and on-line journals. In this manner, the visuals can be printed at the highest quality the publisher can provide and be ready for rapid electronic distribution on the Internet. Therefore, authors must become knowledgeable in the visual preparation process in order to generate electronic images that will be as true a representation of the original image as possible. Perfecting this procedure can be a learning experience and often requires some experimentation. When accomplished, the author will have more control of exactly how the images will look before they are published. In addition to the scan resolution, the type of digital scanner and software applications used are very important, and instruction manuals should be followed closely so as to understand the full potential of the digitizing equipment. Anat Rec (New Anat): 257:128-136, 1999.

Anatomy↗
PubMed1984

The development of self-recognition: a review.

The development of self-recognition has been studied mainly by examining infants' responses to their reflections in mirrors. The definitive test is whether or not the infant is capable of using the reflection to notice and respond to a mark on the face or head by touching the mark. The mark should be inconspicuous to the infant not looking in a mirror. In general, studies agree that this response appears in some infants around 15 months of age and is shown by a majority of infants by 24 months of age. There is less agreement over the existence of a "withdrawal" component in the second year, or the presence of a "social" phase analogous to the reaction of many animals confronted with a mirror. Infants as young as 3 months are differentially responsive to a self-reflection and a live peer. Various "self-conscious" reactions and self-labelling may also indicate self-recognition in the second year, but their validity is not well established. Studies using videotapes of the self and others show that contingency of movement is a salient cue which is learned early, and that attempts to engage in contingent play and to imitate representations of oneself are useful measures of early self-recognition. The validity of the response of turning to look at an object first seen in a mirror as a sign of self-recognition is questioned. The age at which self-recognition in still pictures first appears is less clear. Verbal comprehension of self-relevant labels appears earlier than active self-labelling. A few studies have addressed the question of cognitive correlates of self-recognition, but a variety of behaviors that imply self-awareness and the corresponding ability to impute mental states to others remains to be studied in relation to self-recognition. Continued research into self-recognition and associated abilities in nonhuman primates enhances the overall understanding of the development of self-awareness.

Audiovisual Aids↗
PubMed1987

A model of handwriting.

The research reported here is concerned with hand trajectory planning for the class of movements involved in handwriting. Previous studies show that the kinematics of human two-joint arm movements in the horizontal plane can be described by a model which is based on dynamic minimization of the square of the third derivative of hand position (jerk), integrated over the entire movement. We extend this approach to both the analysis and the synthesis of the trajectories occurring in the generation of handwritten characters. Several basic strokes are identified and possible stroke concatenation rules are suggested. Given a concise symbolic representation of a stroke shape, a simple algorithm computes the complete kinematic specification of the corresponding trajectory. A handwriting generation model based on a kinematics from shape principle and on dynamic optimization is formulated and tested. Good qualitative and quantitative agreement was found between subject recordings and trajectories generated by the model. The simple symbolic representation of hand motion suggested here may permit the central nervous system to learn, store and modify motor action plans for writing in an efficient manner.

Cybernetics↗
PubMed2004

Hemispheric specialization and independence for word recognition: a comparison of three computational models.

Two findings serve as the hallmark for hemispheric specialization during lateralized lexical decision. First is an overall word advantage, with words being recognized more quickly and accurately than non-words (the effect being stronger in response latency). Second, a right visual field advantage is observed for words, with little or no hemispheric differences in the ability to identify non-words. Several theories have been proposed to account for this difference in word and non-word recognition, some by suggesting dual routes of lexical access and others by incorporating separate, and potentially independent, word and non-word detection mechanisms. We compare three previously proposed cognitive theories of hemispheric interactions (callosal relay, direct access, and cooperative hemispheres) through neural network modeling, with each network incorporating different means of interhemispheric communication. When parameters were varied to simulate left hemisphere specialization for lexical decision, only the cooperative hemispheres model showed both a consistent left hemisphere advantage for word recognition but not non-word recognition, as well as an overall word advantage. These results support the theory that neural representations of words are more strongly established in the left hemisphere through prior learning, despite open communication between the hemispheres during both learning and recall.

Dominance, Cerebral↗
PubMed2001

The declarative/procedural model of lexicon and grammar.

Our use of language depends upon two capacities: a mental lexicon of memorized words and a mental grammar of rules that underlie the sequential and hierarchical composition of lexical forms into predictably structured larger words, phrases, and sentences. The declarative/procedural model posits that the lexicon/grammar distinction in language is tied to the distinction between two well-studied brain memory systems. On this view, the memorization and use of at least simple words (those with noncompositional, that is, arbitrary form-meaning pairings) depends upon an associative memory of distributed representations that is subserved by temporal-lobe circuits previously implicated in the learning and use of fact and event knowledge. This "declarative memory" system appears to be specialized for learning arbitrarily related information (i.e., for associative binding). In contrast, the acquisition and use of grammatical rules that underlie symbol manipulation is subserved by frontal/basal-ganglia circuits previously implicated in the implicit (nonconscious) learning and expression of motor and cognitive "skills" and "habits" (e.g., from simple motor acts to skilled game playing). This "procedural" system may be specialized for computing sequences. This novel view of lexicon and grammar offers an alternative to the two main competing theoretical frameworks. It shares the perspective of traditional dual-mechanism theories in positing that the mental lexicon and a symbol-manipulating mental grammar are subserved by distinct computational components that may be linked to distinct brain structures. However, it diverges from these theories where they assume components dedicated to each of the two language capacities (that is, domain-specific) and in their common assumption that lexical memory is a rote list of items. Conversely, while it shares with single-mechanism theories the perspective that the two capacities are subserved by domain-independent computational mechanisms, it diverges from them where they link both capacities to a single associative memory system with broad anatomic distribution. The declarative/procedural model, but neither traditional dual- nor single-mechanism models, predicts double dissociations between lexicon and grammar, with associations among associative memory properties, memorized words and facts, and temporal-lobe structures, and among symbol-manipulation properties, grammatical rule products, motor skills, and frontal/basal-ganglia structures. In order to contrast lexicon and grammar while holding other factors constant, we have focused our investigations of the declarative/procedural model on morphologically complex word forms. Morphological transformations that are (largely) unproductive (e.g., in go-went, solemn-solemnity) are hypothesized to depend upon declarative memory. These have been contrasted with morphological transformations that are fully productive (e.g., in walk-walked, happy-happiness), whose computation is posited to be solely dependent upon grammatical rules subserved by the procedural system. Here evidence is presented from studies that use a range of psycholinguistic and neurolinguistic approaches with children and adults. It is argued that converging evidence from these studies supports the declarative/procedural model of lexicon and grammar.

Aphasia↗
PubMed2005

Spontaneous recovery from forward and backward blocking.

This article demonstrates and analyzes spontaneous recovery of stimulus control following both forward and backward blocking in a conditioned suppression preparation with rats. Experiment 1 found, in first-order conditioning, robust forward blocking and an attenuation of it following a retention interval. Experiment 2 showed, in sensory preconditioning, recovery of responding following both forward and backward blocking. Also, the results of this experiment indicated that response recovery to the blocked stimulus cannot be explained by an impaired status of the blocking stimulus after a retention interval. Experiment 3, also in sensory preconditioning, suggested that spontaneous recovery following both forward and backward blocking in Experiment 2 was due to impaired associative activation of the blocking stimulus' representation during testing with the blocked stimulus. Although no contemporary model of associative learning can explain these results, a modification of R. R. Miller and L. D. Matzel's (1988) comparator hypothesis is proposed to do so.

Animals↗
PubMed1999

Experience with the Internet release of AIDA v4.0--http://www.diabetic.org.uk.aida.htm--an interactive educational diabetes simulator.

AIDA v4.0 is a freeware computer program that permits the interactive simulation of plasma insulin and blood glucose profiles for demonstration and teaching purposes. It has been made freely available, without charge, on the World Wide Web as a noncommercial contribution to continuing diabetes education. Since its Internet launch in 1996 over 23,000 people have visited the AIDA Web site (http://www.diabetic.org.uk/aida.htm) and over 7,750 copies of the program have been downloaded gratis. This report overviews the Internet release of AIDA v4.0 and provides examples of the simulator in operation. The concept of a "virtual diabetic patient" is introduced. This provides an electronic representation of a patient with diabetes that can be used for self-learning/teaching/demonstration purposes.

Computer Simulation↗
PubMed2004

Statistical modeling of complex backgrounds for foreground object detection.

This paper addresses the problem of background modeling for foreground object detection in complex environments. A Bayesian framework that incorporates spectral, spatial, and temporal features to characterize the background appearance is proposed. Under this framework, the background is represented by the most significant and frequent features, i.e., the principal features, at each pixel. A Bayes decision rule is derived for background and foreground classification based on the statistics of principal features. Principal feature representation for both the static and dynamic background pixels is investigated. A novel learning method is proposed to adapt to both gradual and sudden "once-off" background changes. The convergence of the learning process is analyzed and a formula to select a proper learning rate is derived. Under the proposed framework, a novel algorithm for detecting foreground objects from complex environments is then established. It consists of change detection, change classification, foreground segmentation, and background maintenance. Experiments were conducted on image sequences containing targets of interest in a variety of environments, e.g., offices, public buildings, subway stations, campuses, parking lots, airports, and sidewalks. Good results of foreground detection were obtained. Quantitative evaluation and comparison with the existing method show that the proposed method provides much improved results.

Algorithms↗
PubMed2002

Intentional maps in posterior parietal cortex.

The posterior parietal cortex (PPC), historically believed to be a sensory structure, is now viewed as an area important for sensory-motor integration. Among its functions is the forming of intentions, that is, high-level cognitive plans for movement. There is a map of intentions within the PPC, with different subregions dedicated to the planning of eye movements, reaching movements, and grasping movements. These areas appear to be specialized for the multisensory integration and coordinate transformations required to convert sensory input to motor output. In several subregions of the PPC, these operations are facilitated by the use of a common distributed space representation that is independent of both sensory input and motor output. Attention and learning effects are also evident in the PPC. However, these effects may be general to cortex and operate in the PPC in the context of sensory-motor transformations.

Animals↗
PubMed2006

A probabilistic Classifier System and its application in data mining.

The article is about a new Classifier System framework for classification tasks called BYP-CS (for BaYesian Predictive Classifier System). The proposed CS approach abandons the focus on high accuracy and addresses a well-posed Data Mining goal, namely, that of uncovering the low-uncertainty patterns of dependence that manifest often in the data. To attain this goal, BYP-CS uses a fair amount of probabilistic machinery, which brings its representation language closer to other related methods of interest in statistics and machine learning. On the practical side, the new algorithm is seen to yield stable learning of compact populations, and these still maintain a respectable amount of predictive power. Furthermore, the emerging rules self-organize in interesting ways, sometimes providing unexpected solutions to certain benchmark problems.

Algorithms↗
PubMed2006

Soft mixer assignment in a hierarchical generative model of natural scene statistics.

Gaussian scale mixture models offer a top-down description of signal generation that captures key bottom-up statistical characteristics of filter responses to images. However, the pattern of dependence among the filters for this class of models is prespecified. We propose a novel extension to the gaussian scale mixture model that learns the pattern of dependence from observed inputs and thereby induces a hierarchical representation of these inputs. Specifically, we propose that inputs are generated by gaussian variables (modeling local filter structure), multiplied by a mixer variable that is assigned probabilistically to each input from a set of possible mixers. We demonstrate inference of both components of the generative model, for synthesized data and for different classes of natural images, such as a generic ensemble and faces. For natural images, the mixer variable assignments show invariances resembling those of complex cells in visual cortex; the statistics of the gaussian components of the model are in accord with the outputs of divisive normalization models. We also show how our model helps interrelate a wide range of models of image statistics and cortical processing.

Animals↗
PubMed2002

Computational explorations of the influence of structured knowledge on age-related cognitive decline.

Experience in a domain can sometimes offset cognitive declines that occur with aging. Using a series of neural network simulations of learning chess opening positions, the authors investigated how structured knowledge in a distributed representation may influence age-related declines. Aging manipulations implemented as modulations of neural noise showed increased knowledge as being protective of performance on a chess memory span task, whereas changes in neural plasticity and neural loss lead to main effects without interactions and steeper declines for the initially more able. The models could also simulate the increase in variability in older groups.

Aged↗
PubMed1985

Improving nutrition components in medical and dental school curriculums.

This article has presented an alternative approach to the traditional, freestanding, concentrated course in nutrition. The integration of nutrition into other courses, with continuous reinforcement throughout the 4-year curriculum, may result in better learning and retention by the student. However, the lack of an accurate curriculum representation presents a problem in selecting topics that integrate with other courses. The unobtrusive approach to nutrition curriculum improvement involves three key points: development of the Nutrition Curriculum Guide, which provides detailed information on what is currently being taught, comparison of what is actually being taught with a set of ideal objectives in order to identify redundancies or omissions, and orchestrating the efforts of faculty in courses throughout the 4-year curriculum to help students integrate nutrition-related topics from the various disciplines. When one makes practical application of the unobtrusive approach, the most difficult problem is defining which interdisciplinary topics are currently being taught. An education specialist and the Tracer Method are important resources for one who is seeking to ameliorate the problem.

Curriculum↗
PubMed1999

Responses of macaque perirhinal neurons during and after visual stimulus association learning.

Recent lesion studies have implicated the perirhinal cortex in learning that two objects are associated, i.e., visual association learning. In this experiment we tested whether neuronal responses to associated stimuli in perirhinal cortex are altered over the course of learning. Neurons were recorded from monkeys during performance of a visual discrimination task in which a predictor stimulus was followed, after a delay, by a GO or NO-GO choice stimulus. Association learning had two major influences on neuronal responses. First, responses to frequently paired predictor-choice stimuli were more similar to one another than was the case with infrequently paired stimuli. Second, the magnitude of activity during the delay was correlated with the magnitude of responses to both the predictor and choice stimuli. Both of these learning effects were found only for stimulus pairs that had been associated on at least 2 d of training. Early in training, the delay activity was correlated only with the response to the predictor stimuli. Thus, with long-term training, perirhinal neurons tend to link the representations of temporally associated stimuli.

Animals↗
PubMedDate not supplied

Short-lasting classical conditioning induces reversible changes of representational maps of vibrissae in mouse SI cortex--a 2DG study.

It has been known for several years that receptive field properties of sensory cortical neurons can be altered by learning experiences. We attempted to visualize a global change of the cortical body map induced by learning. In order to do this a short-duration classical conditioning involving stimulation of a row of mystacial vibrissae in mice was followed with 2-deoxyglucose (2DG) mapping of functional activity. Three conditioning sessions that paired stimulation of a row of whiskers with a tail shock produced an increase of the functional representation in somatosensory cortex (SI) of a row of the whiskers stimulated during the training. This plastic change of vibrissal representation in SI was visualized with 2DG autoradiography a day after completion of training. The expansion of representation was the most pronounced in cortical layer IV, and to a lesser extent, in layer IIIb. The expansion was observed in conditioned but not in pseudoconditioned mice or in animals that received only the conditioned stimulus. If training was discontinued, the enlargement of vibrissal representation progressively faded. The reversal could be accelerated by a behavioral extinction procedure. This study gives the pictorial demonstration of rapid, transient, and extinguishable learning-dependent changes in SI cortical maps.

Animals↗
PubMed2003

Automatic learning of the morphology of medical language using information compression.

Conversion of free-text strings in a natural language to a standard representation (codes) is an important reoccurring problem in biomedical informatics. Determining the content of a string involves identifying its meaningful constituents (morphemes). One current method of identifying these constituents is to look them up in a preexisting table (lexicon). Manual construction of lexicons and grammars in complex domains such as biomedicine is extremely laborious. As an alternative to the lexico-grammatical approach, we introduce a segmentation algorithm that automatically learns lexical and structural preferences from corpora via information compression. The method is based on the Minimum Description Length (MDL) principle from classic information theory.

Algorithms↗
PubMed1988

Machine learning in quantitative histopathology.

The role of expert systems functioning as process controllers in learning image understanding systems is discussed. Numeric learning systems already have found a number of applications in cytologic and histopathologic diagnosis. Depending on the required capabilities, systems of increasing complexity are needed. Expert systems to guide scene segmentation in histopathologic imagery require model-based reasoning. Diagnostic image interpretation with learning capability demands a full model of the human expert's competence, including a considerable variety of knowledge representation schemes and inference strategies, coordinated by a meta-process controller.

Artificial Intelligence↗
PubMed2001

Noise-tolerant stimulus discrimination by synchronization with depressing synapses.

Some synapses between cortical pyramidal neurons exhibit a rapid depression of excitatory postsynaptic potentials for successive presynaptic spikes. Since depressing synapses do not transmit information on sustained presynaptic firing rates, it has been speculated that they are favorable for temporal coding. In this paper. we study the dynamical effects of depressing synapses on stimulus-induced transient synchronization in a simple network of inhibitory interneurons and excitatory neurons, assuming that the recurrent excitation is mediated by depressing synapses. This synchronization occurs in a temporal pattern which depends on a given stimulus. Since the presence of noise is always a potential hazard in temporal coding, we investigate the extent to which noise in stimuli influences the synchronization phenomena. It is demonstrated that depressing synapses greatly contribute to suppressing the influences of noise on the stimulus-specific temporal patterns of synchronous firing. The timing-based Hebbian learning revealed by physiological experiments is shown to stabilize the temporal patterns in cooperation with synaptic depression. Thus, the times at which synchronous firing occurs provides a reliable information representation in the presence of synaptic depression.

Action Potentials↗