PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “representation learning”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

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

At least 55 records · Page 3Linked to original sources
PubMed1999

Dissociating stimulus information from internal representation--a case study in object recognition.

Human object recognition is a function of both internal memory representation(s) and stimulus input information. The role of the latter has been so far largely overlooked, and the nature of the representation is often directly equated with recognition performance. We quantify stimulus information for three classes of objects in order of decreasing object complexity: unconnected balls, balls connected with lines, and balls connected with cylinders. In an object discrimination task, subjects' performance improved with the decreasing object complexity. We show that input information also increases with decreasing object complexity. Therefore, the results could potentially be accounted for either by differences in the object representations learned for each class of objects, or by the increased information about the three-dimensional (3D) structure inherent in images of the less complex objects, or by both. We demonstrate that, when image information is taken into account, by computing efficiencies relative to a set of ideal observers, subjects were more efficient in recognizing the less complex objects. This suggests that differences in subjects' performance for different object classes is at least partly a function of the internal representations learned for the different object classes. We stress that this conclusion cannot be achieved without the quantitative analysis of stimulus input information.

Discrimination, Psychological↗
PubMed1997

Self-organizing Internal Representation in Learning of Navigation: A Physical Experiment by the Mobile Robot YAMABICO.

This paper discusses a novel scheme for sensory-based navigation of a mobile robot. In our previous work ([Tani and Fukumura, 1994], Neural Networks, 7(3), 553-563), we formulated the problem of goal-directed navigation as an embedding problem of dynamical systems: desired trajectories in a task space should be embedded in an adequate sensory-based internal state space so that a unique mapping from the internal state space to the motor command could be established. In the current formulation a recurrent neural network is employed, which shows that an adequate internal state space can be self-organized, through supervised training with sensorimotor sequences. The experiment was conducted using a real mobile robot equipped with a laser range sensor, demonstrating the validity of the presented scheme by working in a noisy real-world environment. Copyright 1996 Elsevier Science Ltd.

Journal Article↗
PubMed2026

Resolution-dependent self-supervised transfer in chest radiograph classification.

BACKGROUND: Self-supervised learning (SSL) has improved visual representation learning, but its value in chest radiography remains uncertain. DINOv3 extends earlier SSL models through Gram-anchored self-distillation and explicit high-resolution adaptation. Whether these changes improve transfer learning for chest radiograph classification has not been established. METHODS: We benchmarked DINOv3 against DINOv2 and supervised ImageNet initialization across seven chest radiograph datasets comprising 816,183 radiographs from pediatric and adult cohorts. ViT-B/16 and ConvNeXt-B were evaluated under full fine-tuning at 224 × 224 and 512 × 512 pixels, with targeted 1024 × 1024 experiments on three cohorts. Additional analyses examined parameter-efficient adaptation, synthetic label corruption, external validation, frozen 7B features, and computational efficiency. The primary outcome was the mean area under the receiver operating characteristic curve across labels. RESULTS: In adult cohorts, DINOv3 did not consistently outperform DINOv2 at 224 × 224 pixels, but became the strongest initialization at 512 × 512 pixels, especially with ConvNeXt-B. Gains were greatest for small focal and boundary-dependent abnormalities, whereas large-structure findings changed little. The pediatric cohort showed no significant benefit from DINOv3, higher resolution, or backbone choice. Scaling to 1024 × 1024 rarely improved performance and markedly increased computational cost. ConvNeXt-B remained superior to ViT-B/16 under both full and parameter-efficient adaptation. External validation preserved the 512 × 512 DINOv3 advantage, whereas synthetic label corruption showed that this benefit should not be interpreted simply as superior noise robustness. Frozen DINOv3-7B features underperformed relative to fully adapted 86 to 89M-parameter backbones. CONCLUSIONS: For adult chest radiograph classification, DINOv3 provides its most reliable benefit at 512 × 512 pixels, particularly with ConvNeXt-B. Fully adapted mid-sized models at 512 × 512 pixels provided the best performance-cost trade-off in our benchmark.

Journal Article↗
PubMed2005

Attention-gated reinforcement learning of internal representations for classification.

Animal learning is associated with changes in the efficacy of connections between neurons. The rules that govern this plasticity can be tested in neural networks. Rules that train neural networks to map stimuli onto outputs are given by supervised learning and reinforcement learning theories. Supervised learning is efficient but biologically implausible. In contrast, reinforcement learning is biologically plausible but comparatively inefficient. It lacks a mechanism that can identify units at early processing levels that play a decisive role in the stimulus-response mapping. Here we show that this so-called credit assignment problem can be solved by a new role for attention in learning. There are two factors in our new learning scheme that determine synaptic plasticity: (1) a reinforcement signal that is homogeneous across the network and depends on the amount of reward obtained after a trial, and (2) an attentional feedback signal from the output layer that limits plasticity to those units at earlier processing levels that are crucial for the stimulus-response mapping. The new scheme is called attention-gated reinforcement learning (AGREL). We show that it is as efficient as supervised learning in classification tasks. AGREL is biologically realistic and integrates the role of feedback connections, attention effects, synaptic plasticity, and reinforcement learning signals into a coherent framework.

Animals↗
PubMed2002

Functional integration and inference in the brain.

Self-supervised models of how the brain represents and categorises the causes of its sensory input can be divided into two classes: those that minimise the mutual information (i.e. redundancy) among evoked responses and those that minimise the prediction error. Although these models have similar goals, the way they are attained, and the functional architectures employed, can be fundamentally different. This review describes the two classes of models and their implications for the functional anatomy of sensory cortical hierarchies in the brain. We then consider how empirical evidence can be used to disambiguate between architectures that are sufficient for perceptual learning and synthesis. Most models of representational learning require prior assumptions about the distribution of sensory causes. Using the notion of empirical Bayes, we show that these assumptions are not necessary and that priors can be learned in a hierarchical context. Furthermore, we try to show that learning can be implemented in a biologically plausible way. The main point made in this review is that backward connections, mediating internal or generative models of how sensory inputs are caused, are essential if the process generating inputs cannot be inverted. Because these processes are dynamical in nature, sensory inputs correspond to a non-invertible nonlinear convolution of causes. This enforces an explicit parameterisation of generative models (i.e. backward connections) to enable approximate recognition and suggests that feedforward architectures, on their own, are not sufficient. Moreover, nonlinearities in generative models, that induce a dependence on backward connections, require these connections to be modulatory; so that estimated causes in higher cortical levels can interact to predict responses in lower levels. This is important in relation to functional asymmetries in forward and backward connections that have been demonstrated empirically. To ascertain whether backward influences are expressed functionally requires measurements of functional integration among brain systems. This review summarises approaches to integration in terms of effective connectivity and proceeds to address the question posed by the theoretical considerations above. In short, it will be shown that functional neuroimaging can be used to test for interactions between bottom-up and top-down inputs to an area. The conclusion of these studies points toward the prevalence of top-down influences and the plausibility of generative models of sensory brain function.

Animals↗
PubMed2026

DPAS-Graph: adaptive spatial-feature relation learning for spatial RNA-to-protein prediction and virtual protein profiling.

Paired spatial multi-omics provides a supervised basis for learning RNA-protein correspondence in situ, but predicting protein abundance from spatial transcriptomic data alone remains challenging across tissue contexts and protein panels. Here, we present DPAS-Graph, an adaptive relation-learning framework for spatial RNA-to-protein prediction. Rather than directly merging spatial proximity and transcriptomic similarity as fixed graph priors, DPAS-Graph represents them as two relation channels on a shared edge support and updates their contributions during representation learning for protein prediction. Its Niche-Coupled Field Encoder combines layer-wise edge-relation modeling, intra-branch relation refinement, and cross-branch residual correction to learn spot representations for protein abundance prediction. In a leave-one-dataset-out benchmark across seven paired spatial multi-omics datasets, DPAS-Graph achieved lower aggregate prediction errors and improved spot-level agreement of protein expression profiles, with gains mainly reflected in error-based metrics and PCC-Spot. Spatial autocorrelation and protein-derived domain agreement analyses were further used to characterize the spatial behavior of the predicted protein maps. When applied to external RNA-only spatial sections, DPAS-Graph generated qualitatively interpretable marker-level virtual protein maps, illustrating its use as a complementary tool for protein-level interpretation of transcriptomics-only spatial data.

RNA↗
PubMed2003

Abstract and associatively based representations in human sequence learning.

We give an analysis of performance in an artificial neural network for which the claim had been made that it could learn abstract representations. Our argument is that this network is associative in nature, and cannot develop abstract representations. The network thus converges to a solution that is solely based on the statistical regularities of the training set. Inspired by human experiments that have shown that humans can engage in both associative (statistical) and abstract learning, we present a new, hybrid computational model that combines associative and more abstract, cognitive processes. To cross-validate the model we attempted to predict human behaviour in further experiments. One of these experiments reveals some evidence for the use of abstract representations, whereas the others provide evidence for associatively based performance. The predictions of the hybrid model stand in line with our empirical data.

Computer Simulation↗
PubMed2025

soFusion: facilitating tissue structure identification via spatial multi-omics data fusion.

The rapid advancement of spatial multi-omics technologies has opened new avenues for dissecting tissue architecture with unprecedented resolution. However, inherent disparities across omics modalities, such as differences in biological hierarchy and resolution, pose significant challenges for integrative analysis. To address this, we present soFusion, a method for representation learning on spatial multi-omics data that enables automated identification of tissue compartmentalization. soFusion employs a graph convolutional network (GCN) to extract latent embeddings from spatial omics profiles. To simultaneously capture both cross-modality relationships and modality-specific features, we introduce a novel strategy for intra- and inter-omics feature learning. Moreover, modality-specific decoders are designed to preserve the unique information embedded in each omics type. We evaluated soFusion on multiple datasets including gene expression, protein expression, and epigenetic features. Across all benchmarks, soFusion consistently outperformed existing methods in delineating anatomical structures and identifying spatial domains with improved continuity and reduced noise. Collectively, soFusion offers an effective solution for spatial multi-omics integration, substantially enhancing the robustness of spatial domain identification.

Humans↗
PubMedDate not supplied

[Analysis and cognitive modelling of the analogical process in psychosis].

The disturbances of cognitive processes in psychotic patients are well known: the delusional interpretation is "the inference from a right perception into a wrong concept" (Dromard), "an wrong intuition about the meaning of what is perceived, seen or heard" (H. Ey). Analogy is the very core of any cognitive process: relating a strange thing to some object already part of the experience enables to set up differences, oppositions, connections, classes. Any semantic process (something stands for another thing) originates in analogy. It is the basis of every interpretation and world's knowledge. Its soundness is by no means reliable, but for the inner strength of the analogical network and its power to integrate new objects. It's easy to fall out of the track... A wrong analogy, better, a wrong one that would not be acknowledged as a mistake, would be enough: the gap is quite narrow between interpretations leading either to understanding or to misreading, only filled through the relation of other people providing the necessary clues. The contemporary papers about cognitive process are driving towards two main trends: 1) Neuromimetic models, and the building of neuronal networks, whose emergent properties point out the basically analogical character of representations, learning and memory. 2) Cognitive models, dealing with representations and algorithms, and leading to Artificial Intelligence Programs. We tried to build a model (both cognitive and AI) of the analogical process and its psychotic disturbances. Our model describes how simple analogical problems are solved: If (A) becomes (B), what about (C)? Making up the psychological model and its AI translation led to propound the concept of Universes as sets consisting of ONE likely or relevant link between two objects, and such intrinsic of extrinsic properties of the objects as are involved in this relation. The model uses 3 different universes: Universe U1, made up of one of the possible transformation kinks from (A) to (B) and (A)'s properties involved in this actual transformation. Universe U2, made out of the likeness link between Universe U1 and (C). Universe U3, performing in fact the validation procedure of the result. The analogical reasoning goes through the three universes, along an iterative loop again and again until a nice result is found.(ABSTRACT TRUNCATED AT 400 WORDS)

Artificial Intelligence↗
PubMed2005

Neural control of rhythmic sequences.

We investigated whether the temporal structure of movement sequences can be represented and learned independently of their ordinal structure, and whether some brain regions are particularly important for temporal sequence performance. Using a learning transfer design, we found evidence for independent temporal representations: learning a spatiotemporal sequence facilitated learning its temporal and ordinal structure alone; learning a temporal and an ordinal structure facilitated learning of a sequence where the two were coupled. Second, learning of temporal structures was found during reproduction of sequential stimuli with random ordinal structure, suggesting independent mechanisms for temporal learning. We then used functional magnetic resonance imaging to investigate the neural control of sequences during well-learned performance. The temporal and ordinal structures of the sequences were varied in a 2 x 2 factorial design. A dissociation was found between brain regions involved in ordinal and temporal control, the latter mainly involving the presupplementary motor area, the inferior frontal gyrus and precentral sulcus, and the superior temporal gyri. Finally, in a second fMRI experiment, well-learned temporal sequences were performed with the left or right index fingers, or using rhythmic speech. The overlap in brain activity during performance with the different effectors included a similar set of brain regions as that found in the first fMRI experiment: the supplementary motor area (SMA), the superior temporal gyrus, and the inferior frontal cortex. We thus suggest that this set of regions is important for abstract, movement-independent, temporal sequence control. This organization may be important for increased flexibility in voluntarily timed motor tasks.

Brain Mapping↗
PubMed2026

Multimodal alignment improves generalizability of genomic biomarker prediction in computational pathology.

Computational pathology models that use digitized histopathology whole-slide images have the potential to become a cost-effective and scalable alternative to molecular assays for the prediction of genomic biomarkers, a key task in precision oncology. However, as new genomic biomarkers are discovered or quantified, large, labeled datasets must be prospectively collected to train new models. To address this challenge, we developed multimodal alignment for biomarker learning and generalization (MARBLE), a multimodal contrastive pretraining strategy that integrates structured biomarker knowledge into representation learning of histopathology images. MARBLE aligns histopathology-derived representations with representations of genomic biomarkers generated by a large language model (LLM) and a protein language model (PLM). This biologically informed alignment enables data-efficient generalization to novel, out-of-distribution biomarkers. Using the MSK-IMPACT cohort of over 40,000 patients across multiple biomarker panel versions, we design experiments grounded in real-world data to demonstrate the value of our proposed approach.

CP: computational biology↗
PubMed2003

Comparison of computational models of familiarity discrimination in the perirhinal cortex.

This study compares the efficiency and plausibility of published computational models of familiarity discrimination in the perirhinal cortex. Substantial evidence indicates that the perirhinal cortex is involved in both the familiarity discrimination aspect of recognition memory and in perceptual functions involved with representations of complete stimuli (i.e., object identification). Published models of how the perirhinal cortex may perform familiarity discrimination can be divided into two groups. The first group assumes that a proportion of perirhinal neurons form a network specialised just for familiarity discrimination (these models may be based on Hebbian or anti-Hebbian synaptic plasticity). In contrast, the second group assumes that both familiarity discrimination and learning representations of complete stimuli are performed within a single combined network. This study establishes that when the responses of neurons that provide input to the familiarity discrimination network are correlated (as indicated by experimental data), specialised networks based on anti-Hebbian learning may recognise the previous occurrence of many more stimuli (i.e., have a capacity up to thousands of times larger) than specialised networks based on Hebbian learning. The currently published combined models do not learn an optimal stimulus representation (they do not fully extract statistically independent features), and hence their capacities are even lower than those of the specialised models based on Hebbian learning. Hence, the combined models published thus far are critically less efficient than the specialised models based on anti-Hebbian learning. This study also compares the consistency of the models with experimental observations concerning what is known of synaptic plasticity in the perirhinal cortex and the responses of its neurons. Many theoretically important parameters remain undetermined, and experiments are suggested to provide information critical for refining and distinguishing between the various models. However, the above theoretical arguments and currently published data favour the existence of a separate network specialised for familiarity discrimination.

Animals↗
PubMed2002

Teaching Bayesian reasoning: an evaluation of a classroom tutorial for medical students.

How likely is a diagnosis, given a particular medical test result? This probability can be determined by using Bayes's rule; however, previous research has shown that doctors often experience problems with Bayesian inferences. These findings illustrate the need to teach statistical reasoning in medical education. A new method of teaching Bayesian reasoning is representation learning: the key idea is to instruct medical students how to translate probability information into a representation that is easier to process, namely natural frequencies. This approach was implemented in a one-hour classroom tutorial to evaluate its effectiveness in this setting and compared with a traditional rule-learning approach. Evaluation took place two months after training by testing students' ability to correctly solve a Bayesian inference task with information represented as probabilities. While both approaches improved performance, almost three times as many students were able to profit from representation training as opposed to rule training.

Adult↗
PubMed2026

GBFN: A gated bimodal fusion network leveraging foundation model embeddings for cancer drug sensitivity prediction.

Despite recent progress in deep learning for cancer drug sensitivity prediction, many existing models still rely on task-specific representation learning or relatively simple multimodal fusion, which may limit their ability to capture complex drug-cell interactions. To address this issue, we developed GBFN, a gated bimodal fusion network for continuous IC50 prediction that integrates pretrained drug and cell-line representations. Specifically, drug embeddings were obtained from SMI-TED, whereas cell-line embeddings were derived from transcriptomic profiles using BulkFormer. These two modalities were then combined through a dimension-wise gated fusion module and used to predict IC50 values in matched drug-cell line pairs. On the CCLE-based benchmark, GBFN outperformed representative neural baselines, including GraphDRP, TGSA, and TransEDRP, and achieved the best overall performance, with an R² of 0.8714 and an RMSE of 0.8938. Moreover, ablation analysis showed that the model using drug features and cell-line expression data with gated fusion performed better than the corresponding model using direct concatenation, indicating that the improvement was associated with the fusion strategy rather than with the input modalities alone. In addition, cell-line expression data were more informative than mutation data in the present setting, and adding mutation data to the model using drug features and expression data did not further improve performance. Across major cancer types, GBFN maintained generally high cell-line-level predictive performance, and perturbation-based attribution identified biologically relevant transcriptomic programs in selected drug-cell line settings. Together, these findings support GBFN as a compact and effective framework for continuous drug response prediction.

Humans↗
PubMed2002

Alignment effects on learning multiple, use-relevant classification systems.

People often learn multiple classification systems that are relevant to some goal or use. We compared conditions in which subclassification within a category hierarchy was predicted by values on either the same (alignable) or different (nonalignable) dimensions between category hierarchies. The results indicated that learning in alignable conditions occurred in fewer blocks and with fewer errors than did learning in nonalignable conditions. This facilitation was not the result of differences between conditions in the representations learned by the participants, the number of dimensions needed for subclassification (Experiment 1), or the objective complexity of the learning task (Experiment 2). The facilitated learning in the alignable conditions appears to reflect a commitment on the part of the learner to alignment: the belief that the structure relevant to the use of one category system will also be relevant to the use of a comparable system.

Decision Making↗
PubMed2001

In vivo recordings of spontaneous and odor-modulated dynamics in the Limax olfactory lobe.

The major central site of olfactory information processing in the terrestrial slug Limax maximus is the procerebral lobe of the cerebral ganglion, which exhibits oscillatory dynamics of its local field potential and propagates activity waves from its apex to its base, as determined by multisite optical and electrical measurements in vitro. The learning-dependent uptake of Lucifer yellow into procerebral neurons suggests that the procerebral lobe may form learned representations of odors. To determine the role of the procerebral lobe in odor processing and odor learning, we developed procedures to implant fine wire electrodes in the lobe, which allowed recordings of local field potential in freely behaving slugs. The procerebral lobe displays oscillatory dynamics of its local field potential in vivo; however the amplitude and frequency of the local field potential are much more variable in vivo than in vitro. Odor presentation leads to increased frequency and amplitude of the local field potential signal. Several lines of evidence indicate that the variations in the local field potential signal recorded in vivo are not due to movement artifacts or activity in adjacent muscles. Multiple amine, gaseous, and peptide neuromodulators known to be present in the procerebral lobe provide pathways by which activity or coupling of bursting neurons in the procerebral lobe could be altered, resulting in the observed amplitude and frequency modulation of the local field potential.

Animals↗
PubMed1997

Reconstruction of vascular networks using three-dimensional models.

Reconstructing vasculature in three dimensions is a challenging problem. Early approaches concentrated on coronary vasculature in X-ray images, recent work uses magnetic resonance imagery of cerebral vasculature. In both cases a priori information has been used, and often the way this is represented has proven limiting to the scope of applications supported. For example, a particular representation may be useful only for X-ray images. This paper addresses two issues: 1) representing a collection of vasculature and 2) the reconstruction of individual vasculature from images. Our representation learns the variations in branching structures and vessel shapes that occur between individuals. It supports a vascular catalogue containing three-dimensional (3-D) anatomical models. The representation is task independent; here we use it to reconstruct vasculature from images. Our algorithm has four features to which we draw attention: 1) it is not premised wholly upon X-ray images (though that is our focus here); 2) it produces several feasible solutions rather than one; 3) it can generalize from the catalogue to reconstruct instances not yet learned; 4) it exhibits polynomial time complexity, reasonable memory consumption, and is reliable. Both our representation and reconstruction algorithm are new and useful approaches. In support of these claims, we present results gathered from X-rays of both simulated and real vasculature.

Algorithms↗