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 487 records · Page 27Linked to original sources
PubMed2001

Primary visual cortex and memory. Retinal position specificity and lack of size constancy at early stages of learning a visual memory task in the macaque.

Two monkeys were trained in a novel version of a delayed match-to-sample (DMS) task. They were required to fixate on a small spot at the center of the monitor and distinguish whether two gratings presented one after the other with delays up to 1.5 s in a specific visual field location were similar or not. It was found that such learning fails to transfer readily to other retinal locations. In fact, the learning was sensitive even to very small retinal displacements of the visual stimuli. Such acute retinal position specificity implies that at least a component of the learning in this particular memory task occurs at an early visual area such as the striate cortex, which has a fine-grain topographical representation. Furthermore, at early stages of learning the DMS task, when the monkeys had not generalized the learning to stimuli of different sizes, they failed to show size constancy. That is, when the display was placed at a different distance but with the same absolute size, the performance dropped. The performance was almost fully restored when, at the new display location, stimuli were changed to fit the original retinal size. This indicates that a crucial component of the learning does occur at a site even prior to size constancy. These results show that, under certain situations, an early visual area such as the primary visual cortex may be involved even in complex behaviours such as a memory task as more than just a feature-detecting area or a relay station.

Animals↗
PubMed2005

Perceptual context-dependent remodeling of the forepaw map in the SI cortex of rats trained on tactile discrimination.

We combined behavioral assessment of texture discrimination and electrophysiological mapping of concomitant reorganization in the forepaw representation within the SI cortex. Rats were housed in enriched (EE) or impoverished (IE) environments which have been shown to remodel the forepaw map and possibly alter discriminative abilities. In addition, animals were trained to discriminate homogeneous floorboards of invariant roughness from heterogeneous floorboards of gradually decreasing roughness contrasts during locomotion. As reported recently, differences in perceptual abilities were not related to housing conditions, but to a predilection for a floorboard type [Bourgeon S, Xerri C, Coq JO. Abilities in tactile discrimination of textures in adult rats exposed to enriched or impoverished environments. Behav Brain Res 2004;153:217-231]. Consistently, the present study shows that cortical map remodeling resulting from short-duration daily experience can prevail over changes induced by housing conditions. The relative area of glabrous skin representation was related to the discrimination performance and learning abilities in the rats (H) with a predilection for heterogeneous floorboards, i.e. in the animals performing discrimination in the most challenging perceptual context. By contrast, this cortical area was influenced by the duration of sensory experience in rats (h) with a predilection for homogeneous floorboards. Both EE condition and training to discrimination selectively decreased the sizes of the SI neurons' receptive fields (RFs) located on glabrous skin. Smaller RFs and larger cortical areas serving glabrous skin were correlated with better perceptual performances and learning abilities in the H rats only. The present study shows that representational reorganization related to tactile discrimination performances depends upon the perceptual context.

Analysis of Variance↗
PubMed2002

Representations of odors in the rat orbitofrontal cortex change during and after learning.

Cells in the orbitofrontal cortex (OF) respond to odors and their associated rewards. To determine how these responses are acquired and maintained, the authors recorded single OF units in rats performing an odor discrimination task. Approximately 64% of all cells differentiated between rewarded and nonrewarded odors. These odor valence responses changed during learning in 26% of all cells, and these changes were positively correlated with improving performance, supporting the idea that the information provided by these cells is used in learning the task. However, changes in odor valence responses were also observed after learning, and included not only increases in odor discrimination, but also decreases or mixed increases and decreases. Thus, only some of the changes in firing reflected acquisition of the task. The results suggest that learning triggers a continuing reorganization of OF neural ensembles representing odors and their rewards.

Action Potentials↗
PubMed2002

[Psychodynamic therapy approaches in depressive disorders. Pathogenesis models and empirical principles].

Targets for psychodynamic psychotherapy are the core conflictual relational mode and its consequences for mood, social behaviour, and self image. Libido- and conflict-based concepts of the relational mode are increasingly being replaced by the concept of intersubjectivity, which includes also nonconflictual, healthy modes of relations as a basic human mental task. According to recent mother-infant interaction research, the psychotherapeutic effect on the relational mode can be interpreted in terms of procedural learning rather than insight-oriented discourse. The mother-infant paradigm is a particularly suitable research paradigm to elucidate unconscious procedural acquisition of mental representations of dyadic interactional styles. Procedural learning requires a more active corrective style of interacting on the therapist's side, beyond abstinence and control of countertransference. Evaluative studies show that psychodynamic psychotherapy of depression is nearly as effective as cognitive behaviour therapy (CBT) and interpersonal therapy (IPT).

Adult↗
PubMed1996

Internal representation of two-dimensional shape.

The psychological space of shapes has been studied in many experiments. However, how shapes are represented in the brain has not been a major issue in psychological literature. Here, the characteristics of internal representation and how it was formed have been considered and an attempt has been made to explain the results of experiments in a unified manner. First, the data of similarity of alphabetic characters and random-dot patterns were reexamined. Multivariate analysis suggested that those patterns were represented by the combination of global features. Second, three-layer neural networks were trained to perform categorization or identity transformation of the same sets of patterns as used in psychological experiments, and activation patterns of the hidden units were analyzed. When the network learned categorization of the patterns, its internal representation was not similar to the representation suggested by psychological experiments. But a network which learned identity transformation of the patterns could acquire such an internal representation. The transformation performed by this kind of network is similar to principal-component analysis in that it projects the input image onto a lower-dimensional space. From these results it is proposed that two-dimensional shapes are represented in human brain by a process like principal-component analysis. This idea is compatible with the findings in neurophysiological studies about higher visual areas.

Animals↗
PubMed2004

Norepinephrine and dopamine as learning signals.

The present review focuses on the hypothesis that norepinephrine (NE) and dopamine (DA) act as learning signals. Both NE and DA are broadly distributed in areas concerned with the representation of the world and with the conjunction of sensory inputs and motor outputs. Both are released at times of novelty and uncertainty, providing plausible signal events for updating representations and associations. These catecholamines activate intracellular machinery postulated to serve as a memory-formation cascade. Yet, despite the plausibility of an NE and DA role in vertebrate learning and memory, most evidence that they provide a learning signal is circumstantial. The major weakness of the data available is the lack of a specific description of how the neural circuit modulated by NE or DA participates in the learning being analyzed. Identifying a conditioned stimuli (CS) representation would facilitate the identification of a learning signal role for NE or DA. Describing how the CS representation comes to relate to learned behavior, either through sensory-sensory associations, in which the CS acquires the motivational significance of reward or punishment, thus driving appropriate behavior, or through direct sensory-motor associations is necessary to identify how NE and DA participate in memory creation. As described here, evidence consistent with a direct learning signal role for NE and DA is seen in the changing of sensory circuits in odor preference learning (NE), defensive conditioning (NE), and auditory cortex remodeling in adult rats (DA). Evidence that NE and DA contribute to normal learning through unspecified mechanisms is extensive, but the details of that support role are lacking.

Animals↗
PubMed2005

The acquisition of allophonic rules: statistical learning with linguistic constraints.

Phonological rules relate surface phonetic word forms to abstract underlying forms that are stored in the lexicon. Infants must thus acquire these rules in order to infer the abstract representation of words. We implement a statistical learning algorithm for the acquisition of one type of rule, namely allophony, which introduces context-sensitive phonetic variants of phonemes. This algorithm is based on the observation that different realizations of a single phoneme typically do not appear in the same contexts (ideally, they have complementary distributions). In particular, it measures the discrepancies in context probabilities for each pair of phonetic segments. In Experiment 1, we test the algorithm's performances on a pseudo-language and show that it is robust to statistical noise due to sampling and coding errors, and to non-systematic rule application. In Experiment 2, we show that a natural corpus of semiphonetically transcribed child-directed speech in French presents a very large number of near-complementary distributions that do not correspond to existing allophonic rules. These spurious allophonic rules can be eliminated by a linguistically motivated filtering mechanism based on a phonetic representation of segments. We discuss the role of a priori linguistic knowledge in the statistical learning of phonology.

Humans↗
PubMed2006

Associative encoding in anterior piriform cortex versus orbitofrontal cortex during odor discrimination and reversal learning.

Recent proposals have conceptualized piriform cortex as an association cortex, capable of integrating incoming olfactory information with descending input from higher order associative regions such as orbitofrontal cortex (OFC). If true, encoding in piriform cortex should reflect associative features prominent in these areas during associative learning involving olfactory cues. To test this hypothesis, we recorded from neurons in OFC and anatomically related parts of the anterior piriform cortex (APC) in rats, learning and reversing novel odor discriminations. Findings in OFC were similar to what we have reported previously, with nearly all the cue-selective neurons exhibiting substantial plasticity during learning and reversal. Also, many of the cue-selective neurons were originally responsive in anticipation of the outcomes early in learning, thereby providing a single-unit representation of the cue-outcome associations. Some of these features were also evident in firing activity in APC, including some plasticity across learning and reversal. However, APC neurons failed to reverse cue selectivity when the associated outcome was changed, and the cue-selective population did not include neurons that were active prior to outcome delivery. Thus, although representations in APC are substantially more associative than expected in a purely sensory region, they do appear to be somewhat more constrained by the sensory features of the odor cues than representations in downstream areas of OFC.

Animals↗
PubMed2004

Plasticity of the hippocampal place cell representation.

The role of the hippocampus in the representation of 'place' has been attributed to the place cells, whose spatially localised firing suggests their participation in forming a cognitive map of the environment. That this map is necessary for spatial memory formation is indicated by the propensity of almost all navigational tasks to be disrupted by hippocampal damage. The hippocampus has also long been implicated in the formation of episodic memories, and the unusually plastic nature of hippocampal synapses testifies to its probable mnemonic role. Arguably, the place cell representation should, if it is to support spatial learning, be modifiable according to known principles of synaptic reorganization. The present article reviews evidence that the place cell representation is indeed plastic, and that its plasticity depends on the same neurobiological mechanisms known to underlie experimentally induced synaptic plasticity. Inferences are drawn regarding the architecture of the spatial representation and the principles by which it is modified. Spatial learning is promising to be the first kind of memory which is completely understood at all levels, from molecular through circuitry to behaviour and beyond.

Animals↗
PubMed2004

Cortical synaptogenesis and motor map reorganization occur during late, but not early, phase of motor skill learning.

Extensive motor skill training induces reorganization of movement representations and synaptogenesis within adult motor cortex. Motor skill does not, however, develop uniformly across training sessions. It is characterized by an initial fast phase, followed by a later slow phase of learning. How cortical plasticity emerges during these phases is unknown. Here, we examine motor map topography and synapse number within rat motor cortex during the early and late phases of motor learning. Adult rats were placed in either a skilled or unskilled reaching condition (SRC and URC, respectively) for 3, 7, or 10 d. Intracortical microstimulation of layer V was used to determine the topography of forelimb movement representations within caudal forelimb area of motor cortex contralateral to the trained paw. Quantitative electron microscopy was used to measure the number of synapses per neuron within layer V. SRC animals showed significant increases in reaching accuracy after 3, 7, and 10 d of training. In comparison with URC animals, SRC animals had significantly larger distal forelimb representations after 10 d of training only. Furthermore, SRC animals had significantly more synapses per neuron than URC animals after 7 and 10 d of training. These results show that both motor map reorganization and synapse formation occur during the late phase of skill learning. Furthermore, synaptogenesis precedes map reorganization. We propose that motor map reorganization and synapse formation do not contribute to the initial acquisition of motor skills but represent the consolidation of motor skill that occurs during late stages of training.

Animals↗
PubMed2004

Plasticity in the human cerebral cortex: lessons from the normal brain and from stroke.

The adult brain maintains the ability for reorganization or plasticity throughout life. Results from neurophysiological and neuroanatomical experiments in animals and noninvasive neuroimaging and electrophysiological studies in humans show considerable plasticity of motor representations with use or nonuse, skill learning, or injury to the nervous system. An important concept of reorganization in the motor cortex is that of a distributed neuronal network in which multiple overlapping motor representations are functionally connected through an extensive horizontal network. By changing the strength of horizontal connections between motor neurons, functionally different neuronal assemblies can form, thereby providing a substrate to construct dynamic motor output zones. Modulation of inhibition and synaptic efficacy are mechanisms involved. Recent evidence from animal experiments indicates that these functional changes are accompanied by anatomical changes. Because plasticity of the brain plays a major role in the recovery of function after stroke, the knowledge of the principles of plasticity may help to design strategies to enhance plasticity when it is beneficial, such as after brain infarction.

Animals↗
PubMed2026

BioNeuralNet: a graph neural network based Multi-Omics network data analysis tool.

SUMMARY: Multi-omics data offer unprecedented insights into complex biological systems, yet their high dimensionality, sparsity, and intricate interactions pose significant analytical challenges. Network-based approaches have advanced multi-omics research by effectively capturing biologically relevant relationships among molecular features (e.g., genes, proteins, metabolites). While these methods are powerful for representing molecular interactions, there remains a need for tools specifically designed to effectively utilize these network representations across diverse downstream analyses. To fulfill this need, we introduce BioNeuralNet, a flexible and modular Python framework tailored for end-to-end network-based multi-omics data analysis. BioNeuralNet leverages Graph Neural Networks (GNNs) to learn biologically meaningful low-dimensional representations from multi-omics networks, converting these complex molecular networks into versatile embeddings. BioNeuralNet supports all major stages of multi-omics network analysis, including several network construction techniques, generation of low-dimensional representations, and a broad range of downstream analytical tasks. Its extensive utilities, including diverse GNN architectures, and compatibility with established Python packages (e.g., scikit-learn, PyTorch, NetworkX), enhance usability and facilitate quick adoption. BioNeuralNet is an open-source, user-friendly, and extensively documented framework designed to support flexible and reproducible multi-omics network analysis in precision medicine. AVAILABILITY AND IMPLEMENTATION: The BioNeuralNet library is available via The Python Package Index (PyPI). Source code, documentation, tutorials, and workflows are hosted at https://bioneuralnet.readthedocs.io. Code archived at https://doi.org/10.5281/zenodo.17503083.

Graph Neural Networks↗
PubMed2006

Invariant visual object recognition: a model, with lighting invariance.

How are invariant representations of objects formed in the visual cortex? We describe a neurophysiological and computational approach which focusses on a feature hierarchy model in which invariant representations can be built by self-organizing learning based on the statistics of the visual input. The model can use temporal continuity in an associative synaptic learning rule with a short term memory trace, and/or it can use spatial continuity in Continuous Transformation learning. The model of visual processing in the ventral cortical stream can build representations of objects that are invariant with respect to translation, view, size, and in this paper we show also lighting. The model has been extended to provide an account of invariant representations in the dorsal visual system of the global motion produced by objects such as looming, rotation, and object-based movement. The model has been extended to incorporate top-down feedback connections to model the control of attention by biased competition in for example spatial and object search tasks. The model has also been extended to account for how the visual system can select single objects in complex visual scenes, and how multiple objects can be represented in a scene.

Animals↗
PubMed1991

A self-organizing multiple-view representation of 3D objects.

We explore representation of 3D objects in which several distinct 2D views are stored for each object. We demonstrate the ability of a two-layer network of thresholded summation units to support such representations. Using unsupervised Hebbian relaxation, the network learned to recognize ten objects from different viewpoints. The training process led to the emergence of compact representations of the specific input views. When tested on novel views of the same objects, the network exhibited a substantial generalization capability. In simulated psychophysical experiments, the network's behavior was qualitatively similar to that of human subjects.

Cybernetics↗
PubMed2003

"My future as a physician"--professional representations and their background among first-day medical students.

BACKGROUND: Professional representations orient students toward their future profession and influence their view of what things are important to learn. PURPOSE: To analyze medical students' professional representations and their background. METHODS: One hundred nine 1st-day medical students wrote an essay titled "My work and future as a physician in the 21st century" and filled in a questionnaire about their background. The essays were content analyzed to identify the dimensions of their professional representations. RESULTS: Four dimensions of representations emerged: impersonal-personal, foreclosed-reflective, traditional-transformative, and idealistic-realistic. The professional representations were associated with the students' gender, previous experiences of working and studying, their sources of information about the medical profession, and the time of career choice. CONCLUSIONS: Our study revealed different subgroups of medical students in view of their professional orientation. The relevance of this finding for the recruitment and educational practices of medical schools is discussed.

Adult↗
PubMed2005

Automated selection of appropriate pheromone representations in ant colony optimization.

Ant colony optimization (ACO) is a constructive metaheuristic that uses an analogue of ant trail pheromones to learn about good features of solutions. Critically, the pheromone representation for a particular problem is usually chosen intuitively rather than by following any systematic process. In some representations, distinct solutions appear multiple times, increasing the effective size of the search space and potentially misleading ants as to the true learned value of those solutions. In this article, we present a novel system for automatically generating appropriate pheromone representations, based on the characteristics of the problem model that ensures unique pheromone representation of solutions. This is the first stage in the development of a generalized ACO system that could be applied to a wide range of problems with little or no modification. However, the system we propose may be used in the development of any problem-specific ACO algorithm.

Algorithms↗
PubMed2001

The representations of the arithmetic operations include functional relationships.

Current theories of mathematical problem solving propose that people select a mathematical operation as the solution to a problem on the basis of a structure mapping between their problem representation and the representation of the mathematical operations. The structure-mapping hypothesis requires that the problem and the mathematical representations contain analogous relations. Past research has demonstrated that the problem representation consists of functional relationships, or principles. The present study tested whether people represent analogous principles for each arithmetic operation (i.e., addition, subtraction, multiplication, and division). For each operation, college (Experiments 1 and 2) and 8th grade (Experiment 2) participants were asked to rate the degree to which a set of completed problems was a good attempt at the operation. The pattern of presented answers either violated one of four principles or did not violate any principles. The distance of the presented answers from the correct answers was independently manipulated. Consistent with the hypothesis that people represent the principles, (1) violations of the principles were rated as poorer attempts at the operation, (2) operations that are learned first (e.g., addition) had more extensive principle representations than did operations learned later (multiplication), and (3) principles that are more frequently in evidence developed more quickly. In Experiment 3, college participants rated the degree to which statements were indicative of each operation. The statements were either consistent or inconsistent with one of two principles. The participants' ratings showed that operations with longer developmental histories had strong principle representations. The implications for a structure-mapping approach to mathematical problem solving are discussed.

Adolescent↗
PubMed1990

An ecological approach to language development: an alternative functionalism.

I argue for a new functionalist approach to language development, an ecological approach. A realist orientation is used that locates the causes of language development neither in the child nor in the language environment but in the functioning of perceptual systems that detect language-world relationships and use them to guide attention and action. The theory requires no concept of innateness, thus avoiding problems inherent in either the innate ideas or the genes-as-causal-programs explanations of the source of structure in language. An ecological explanation of language is discussed in relation to concepts and language, language as representation, problems in early word learning, metaphor, and syntactic development. Finally, problems incurred in using the idea of innateness are summarized: History prior to the chosen beginning point is ignored, data on organism-environment mutuality are not collected, and the explanation claims no effect of learning, which cannot be tested empirically.

Child Language↗