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 73 records · Page 4Linked to original sources

PubMed2002

Invariant object recognition in the visual system with novel views of 3D objects.

To form view-invariant representations of objects, neurons in the inferior temporal cortex may associate together different views of an object, which tend to occur close together in time under natural viewing conditions. This can be achieved in neuronal network models of this process by using an associative learning rule with a short-term temporal memory trace. It is postulated that within a view, neurons learn representations that enable them to generalize within variations of that view. When three-dimensional (3D) objects are rotated within small angles (up to, e.g., 30 degrees), their surface features undergo geometric distortion due to the change of perspective. In this article, we show how trace learning could solve the problem of in-depth rotation-invariant object recognition by developing representations of the transforms that features undergo when they are on the surfaces of 3D objects. Moreover, we show that having learned how features on 3D objects transform geometrically as the object is rotated in depth, the network can correctly recognize novel 3D variations within a generic view of an object composed of a new combination of previously learned features. These results are demonstrated in simulations of a hierarchical network model (VisNet) of the visual system that show that it can develop representations useful for the recognition of 3D objects by forming perspective-invariant representations to allow generalization within a generic view.

Neural Networks, Computer↗

PubMed2000

How hallucinations may arise from brain mechanisms of learning, attention, and volition.

This article suggests how brain mechanisms of learning, attention, and volition may give rise to hallucinations during schizophrenia and other mental disorders. The article suggests that normal learning and memory are stabilized through the use of learned top-down expectations. These expectations learn prototypes that are capable of focusing attention upon the combinations of features that comprise conscious perceptual experiences. When top-down expectations are active in a priming situation, they can modulate or sensitize their target cells to respond more effectively to matched bottom-up information. They cannot, however, fully activate these target cells. These matching properties are shown to be essential towards stabilizing the memory of learned representations. The modulatory property of top-down expectations is achieved through a balance between top-down excitation and inhibition. The learned prototype is the excitatory on-center in this top-down network. Phasic volitional signals can shift the balance between excitation and inhibition to favor net excitatory activation. Such a volitionally mediated shift enables top-down expectations, in the absence of supportive bottom-up inputs, to cause conscious experiences of imagery and inner speech and thereby to enable fantasy and planning activities to occur. If these volitional signals become tonically hyperactive during a mental disorder, the top-down expectations can give rise to conscious experiences in the absence of bottom-up inputs and volition. These events are compared with data about hallucinations. The article predicts where these top-down expectations and volitional signals may act in the laminar circuits of visual cortex and, by extension, in other sensory and cognitive neocortical areas, and how the level of abstractness of learned prototypes may covary with the abstractness of hallucinatory content. A similar breakdown of volition may lead to delusions of control in the motor system.

Attention↗

PubMed2025

A Graph Contrastive Learning Method for Enhancing Genome Recovery in Complex Microbial Communities.

Accurate genome binning is essential for resolving microbial community structure and functional potential from metagenomic data. However, existing approaches-primarily reliant on tetranucleotide frequency (TNF) and abundance profiles-often perform sub-optimally in the face of complex community compositions, low-abundance taxa, and long-read sequencing datasets. To address these limitations, we present MBGCCA, a novel metagenomic binning framework that synergistically integrates graph neural networks (GNNs), contrastive learning, and information-theoretic regularization to enhance binning accuracy, robustness, and biological coherence. MBGCCA operates in two stages: (1) multimodal information integration, where TNF and abundance profiles are fused via a deep neural network trained using a multi-view contrastive loss, and (2) self-supervised graph representation learning, which leverages assembly graph topology to refine contig embeddings. The contrastive learning objective follows the InfoMax principle by maximizing mutual information across augmented views and modalities, encouraging the model to extract globally consistent and high-information representations. By aligning perturbed graph views while preserving topological structure, MBGCCA effectively captures both global genomic characteristics and local contig relationships. Comprehensive evaluations using both synthetic and real-world datasets-including wastewater and soil microbiomes-demonstrate that MBGCCA consistently outperforms state-of-the-art binning methods, particularly in challenging scenarios marked by sparse data and high community complexity. These results highlight the value of entropy-aware, topology-preserving learning for advancing metagenomic genome reconstruction.

canonical correlation analysis↗

PubMed2006

Spatial learning in Long-Evans Hooded rats and C57BL/6J mice: different strategies for different performance.

Spatial learning abilities of rodents have been extensively used to explore the management of a wide range of cognitive and emotional processes such as learning, memory, attention and anxiety. Knowledge about the organization and processing of spatial learning has mainly been obtained in rats. Due to increasing generation of genetically modified mice, cognitive abilities of mice are now extensively tested. The present paper aimed at comparing spatial representation, learning and strategies in C57BL/6J mice and Long-Evans Hooded rats when subjected to the same spatial learning paradigm, i.e. learning a food location in a crossmaze. We also analyzed the influence of environmental richness on learning modalities in both species. Our results showed that rats and mice could exhibit similar spatial learning abilities in some circumstances. However, Long-Evans rats and C57BL/6J mice may set up different strategies depending on the availability of visual information within the environment. Rats' learning strategies mainly relied on distant visual cues and seemed more efficient than those used by mice as they needed less time than mice to solve the task. We emphasize that the strategies of mice are less robust and flexible than the ones set up by rats. Finally, the richness of the environment was shown to affect speed and quality of spatial learning in both species.

Analysis of Variance↗

PubMed2004

A theory of causal learning in children: causal maps and Bayes nets.

The authors outline a cognitive and computational account of causal learning in children. They propose that children use specialized cognitive systems that allow them to recover an accurate "causal map" of the world: an abstract, coherent, learned representation of the causal relations among events. This kind of knowledge can be perspicuously understood in terms of the formalism of directed graphical causal models, or Bayes nets. Children's causal learning and inference may involve computations similar to those for learning causal Bayes nets and for predicting with them. Experimental results suggest that 2- to 4-year-old children construct new causal maps and that their learning is consistent with the Bayes net formalism.

Adult↗

PubMed2005

Progressive transformation of hippocampal neuronal representations in "morphed" environments.

Hippocampal neural codes for different, familiar environments are thought to reflect distinct attractor states, possibly implemented in the recurrent CA3 network. A defining property of an attractor network is its ability to undergo sharp and coherent transitions between pre-established (learned) representations when the inputs to the network are changed. To determine whether hippocampal neuronal ensembles exhibit such discontinuities, we recorded in CA3 and CA1 when a familiar square recording enclosure was morphed in quantifiable steps into a familiar circular enclosure while leaving other inputs constant. We observed a gradual noncoherent progression from the initial to the final network state. In CA3, the transformation was accompanied by significant hysteresis, resulting in more similar end states than when only square and circle were presented. These observations suggest that hippocampal cell assemblies are capable of incremental plastic deformation, with incongruous information being incorporated into pre-existing representations.

Action Potentials↗

PubMed2005

Recursive principal components analysis.

A recurrent linear network can be trained with Oja's constrained Hebbian learning rule. As a result, the network learns to represent the temporal context associated to its input sequence. The operation performed by the network is a generalization of Principal Components Analysis (PCA) to time-series, called Recursive PCA. The representations learned by the network are adapted to the temporal statistics of the input. Moreover, sequences stored in the network may be retrieved explicitly, in the reverse order of presentation, thus providing a straight-forward neural implementation of a logical stack.

Humans↗

PubMed2025

PLNMFG: Pseudo-label guided non-negative matrix factorization model with graph constraint for single-cell multi-omics data clustering.

The development of single-cell multi-omics sequencing technologies has enabled the simultaneous analysis of multi-omics data within the same cell. Accurate clustering of these cells is crucial for downstream analyses of complex biological functions. Despite significant advances in multi-omics integration approaches, current methodologies exhibit two major limitations. First, they inadequately incorporate prior biological knowledge from various omic layers. Second, these methods often conduct independent dimensionality reduction on individual omic datasets, thereby failing to capture the intrinsic complementary information and potentially overlooking crucial cross-platform interactions. Motivated by these, this study investigates a non-negative matrix factorization model called PLNMFG, which integrates the unified latent representation learning that retains the features between and within omics and the cluster structure learning that retains the intrinsic structure of the data into one joint framework. Specially, PLNMFG performs adaptive imputation to handle dropout events and uses prior pseudo-labels as constraints during the process of collective non-negative matrix factorization, as a result, a more robust latent representation that preserves the double similarity information is obtained. Graph Laplacian constraint is applied during clustering which further preserves structure characteristic of multi-omics data. In addition, the weight of each omic is adaptively learned based on the omic contribution. A series of experiments on 8 benchmark datasets show that our model performs well in terms of clustering accuracy and computational efficiency.

Single-Cell Analysis↗

PubMed1997

HAVNET: A New Neural Network Architecture for Pattern Recognition.

A new artificial neural network architecture, specifically designed for two-dimensional binary pattern recognition, is introduced. The network employs a unique similarity metric, based on the Hausdorff distance, to determine the degree of match between an input pattern and a learned representation. Use of this metric in the network leads to behaviour that is more consistent with human performance than that generated by similarity metrics currently in use in other artificial neural networks. A detailed description of the architecture, the learning equations, and the recall equations for the network are presented. An extension of the network is also described in which each class of learned objects is represented by multiple two-dimensional aspects. This extension greatly increases the utility of the network for tasks like character recognition and three-dimensional vision. The network is employed on an example pattern recognition task to demonstrate its application, with very good results. Copyright 1996 Elsevier Science Ltd.

Journal Article↗

PubMed2026

CAGNet: a structure-aware clustering-alternated graph network for cell-cell interaction inference in spatial transcriptomics.

MOTIVATION: Understanding cell-cell interactions (CCIs) in spatial transcriptomics is crucial for uncovering the spatial organization and functional heterogeneity of tissues. However, existing graph-based models typically rely on static clustering or fixed adjacency structures, which limits their ability to capture dynamic cellular relationships. RESULTS: We propose CAGNet, a two-stage framework for CCI inference from spatial transcriptomics data. In Stage 1, a Graph Attention Network encoder with joint feature and graph reconstruction learns structure-aware node embeddings from spatial gene expression profiles. In Stage 2, an alternating optimization mechanism iteratively updates cluster centers via KL-guided soft assignment and refines node embeddings through spatial graph reconstruction, establishing a closed-loop between representation learning and clustering. Experiments on three 10x Genomics Visium datasets demonstrate that CAGNet consistently outperforms six CCI inference baselines across ACC, AUC, AP, Precision, Recall, and F1. CAGNet also achieves the highest Adjusted Rand Index on all three datasets against six spatial domain identification methods, confirming that the learned embeddings capture biologically relevant spatial organization. Information-theoretic analysis further shows that CAGNet retains the highest mutual information between input features and learned embeddings among all compared methods. Ablation studies and 5-fold cross-validation confirm the contribution of each component and the reproducibility of the results. AVAILABILITY: The proposed method is implemented in the CAGNet package available at http://github.com/mahan1233333-maker/CAGNet .

Spatial Transcriptomics↗

PubMed2025

The role of chromatin state in intron retention: A case study in leveraging large scale deep learning models.

Complex deep learning models trained on very large datasets have become key enabling tools for current research in natural language processing and computer vision. By providing pre-trained models that can be fine-tuned for specific applications, they enable researchers to create accurate models with minimal effort and computational resources. Large scale genomics deep learning models come in two flavors: the first are large language models of DNA sequences trained in a self-supervised fashion, similar to the corresponding natural language models; the second are supervised learning models that leverage large scale genomics datasets from ENCODE and other sources. We argue that these models are the equivalent of foundation models in natural language processing in their utility, as they encode within them chromatin state in its different aspects, providing useful representations that allow quick deployment of accurate models of gene regulation. We demonstrate this premise by leveraging the recently created Sei model to develop simple, interpretable models of intron retention, and demonstrate their advantage over models based on the DNA language model DNABERT-2. Our work also demonstrates the impact of chromatin state on the regulation of intron retention. Using representations learned by Sei, our model is able to discover the involvement of transcription factors and chromatin marks in regulating intron retention, providing better accuracy than a recently published custom model developed for this purpose.

Deep Learning↗

PubMed2026

A Knowledge-Enhanced Multimodal Framework with Genomic Reconstruction for DLBCL Drug Response Prediction.

Diffuse large B-cell lymphoma (DLBCL) exhibits substantial biological heterogeneity, leading to pronounced variability in patient response to therapy. Accurate drug response prediction is therefore critical for precision treatment but remains challenging in clinical settings where genomic sequencing, a highly informative modality, is frequently incomplete. Existing methods, often developed from cell-line pharmacogenomic datasets or single-modality data, typically assume fully observed molecular profiles and thus show limited robustness under missing genomic data. To address this limitation, a knowledge-enhanced multimodal framework with genomic reconstruction (KeM-DRP) is proposed for individualized drug response prediction in DLBCL. The framework models the central role of genomics by integrating biological prior knowledge through a gene-pathway-biological process hierarchy, enabling robust representation learning from sparse observations. To compensate for missing genomic measurements, a cross-modal genomic compensation module reconstructs genomically informed latent features from routinely available clinical modalities. Furthermore, a genomics-guided adaptive fusion strategy dynamically integrates heterogeneous modalities conditioned on observed or reconstructed genomic representation. Experiments on a real-world DLBCL cohort demonstrate that KeM-DRP consistently outperforms competitive baselines. The reconstructed genomic representation represents most predictive utility, highlighting the robustness and practical value of the framework under incomplete genomic data.

Journal Article↗

PubMed2005

Linear recursive distributed representations.

Connectionist networks have been criticized for their inability to represent complex structures with systematicity. That is, while they can be trained to represent and manipulate complex objects made of several constituents, they generally fail to generalize to novel combinations of the same constituents. This paper presents a modification of Pollack's Recursive Auto-Associative Memory (RAAM), that addresses this criticism. The network uses linear units and is trained with Oja's rule, in which it generalizes PCA to tree-structured data. Learned representations may be linearly combined, in order to represent new complex structures. This results in unprecedented generalization capabilities. Capacity is orders of magnitude higher than that of a RAAM trained with back-propagation. Moreover, regularities of the training set are preserved in the new formed objects. The formation of new structures displays developmental effects similar to those observed in children when learning to generalize about the argument structure of verbs.

Algorithms↗

PubMed2003

Human theta oscillations related to sensorimotor integration and spatial learning.

oscillations in the rat hippocampus have been implicated in sensorimotor integration (Bland, 1986), especially during exploratory and wayfinding behavior. We propose that human cortical activity coordinates sensory information with a motor plan to guide wayfinding behavior to known goal locations. To test this hypothesis, we analyzed invasive recordings from epileptic patients while they performed a spatially immersive, virtual taxi driver task. Consistent with this hypothesis, we found oscillations during both exploratory search and goal-seeking behavior and, in particular, during virtual movement, when sensory information and motor planning were both in flux, compared with periods of self-initiated stillness. oscillations had different topographic and spectral characteristics during searching than during goal-seeking, suggesting that different cortical networks exhibit depending on which cognitive functions are driving behavior (spatial learning during exploration vs orienting to a learned representation during goal-seeking). In contrast, oscillations in the beta band appeared to be related to simple motor planning, likely a variant of the Rolandic mu rhythm. These findings suggest that human cortical oscillations act to coordinate sensory and motor brain activity in various brain regions to facilitate exploratory learning and navigational planning.

Adolescent↗

PubMed2026

Deep generative models in biological sequence and structure analysis and design.

Deep generative models have transformed biological sequence modeling from predictive analysis toward increasingly controllable design. Early biological applications of Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs) established latent representation learning and sequence synthesis, while recent advances in transformer-based language models, discrete diffusion, flow-matching, and multimodal generative frameworks have substantially expanded the scope of biological design. This review examines generative models for DNA, RNA, and protein sequence design, emphasizing how different model classes represent biological constraints, operate over discrete and continuous spaces, and integrate sequence, structure, and function. We compare VAEs, GANs, autoregressive and masked language models, diffusion models, and flow-based approaches across genomics, transcriptomics, and proteomics, with particular attention to controllability, long-range dependency modeling, structural grounding, generalization, and experimental utility. We further examine evaluation strategies, out-of-distribution generalization, and closed-loop design-build-test-learn workflows that connect in silico generation with empirical validation. We distinguish fundamental modality-dependent constraints including sequence discreteness, context length, structural coupling, and physical or thermodynamic requirements from architecture-dependent advantages that reflect the current state of the field. Current studies suggest that long-context models are particularly useful for genome-scale representation and sequence modeling, whereas structure-aware diffusion, flow-based, and inverse-folding approaches provide better frameworks for geometry-constrained RNA and protein design. This perspective provides a critical framework for understanding the present capabilities, limitations, and convergence of generative approaches toward reliable and experimentally grounded biological design.

Biological sequence analysis↗

PubMed1999

Associative learning modifies neural representations of odors in the insect brain.

Recording brain activity in vivo during learning is fundamental to understanding how memories are formed. We used functional calcium imaging to track odor representations in the primary chemosensory center of the honeybee, the antennal lobe, while training animals to discriminate a rewarded odor from an unrewarded one. Our results show that associative learning transforms odor representations and decorrelates activity patterns for the rewarded versus the unrewarded odor, making them less similar. Additionally, activity for the rewarded but not for the unrewarded odor is increased. These results indicate that neural representations of the environment may be modified through associative learning.

Animals↗

PubMed2025

Multimodal deep learning for immunotherapy response prediction and biomarker discovery in non-small cell lung cancer.

OBJECTIVE: Immunotherapy has emerged as a promising treatment for advanced non-small cell lung cancer (NSCLC), but accurately predicting which patients will benefit from it remains a major clinical challenge. To address this, we aim to develop a novel multimodal method, DeepAFM, that integrates histopathology, genomic features, and clinical information to predict patient responses to anti-PD-(L)1 immunotherapy. MATERIALS AND METHODS: A total of 93 patients with advanced NSCLC were included in this study. Histopathological whole-slide images were processed using a self-supervised VQVAE2 for representation learning. PCA and K-means clustering were then applied for dimensionality reduction and feature grouping. Key regions of interest were visualized through permutation importance evaluation and color-coding techniques. The extracted histopathological features, along with genomic alterations and clinical variables, were integrated into the DeepAFM multimodal prediction model. RESULTS: The DeepAFM achieved a high predictive performance with an area under the curve (AUC) of 0.77 (95% confidence interval: 0.69-1.00). Attention-based heatmaps revealed that the model could identify critical pathological patterns, genomic mutations, and clinical indicators associated with patient responses to immunotherapy. DISCUSSION: The integration of multimodal data enabled the model to capture complex interactions among pathology, genomics, and clinical characteristics, enhancing the interpretability and predictive power of immunotherapy response prediction. The visualization techniques facilitated the identification of biologically meaningful features and potential biomarkers. CONCLUSION: This study demonstrates the effectiveness of the DeepAFM in predicting responses to immunotherapy in advanced NSCLC. The approach not only improves prediction accuracy but also provides valuable insights for personalized treatment strategies and biomarker discovery.

Humans↗

PubMed2000

Medical text representations for inductive learning.

Inductive learning algorithms have been proposed as methods for classifying medical text reports. Many of these proposed techniques differ in the way the text is represented for use by the learning algorithms. Slight differences can occur between representations that may be chosen arbitrarily, but such differences can significantly affect classification algorithm performance. We examined 8 different data representation techniques used for medical text, and evaluated their use with standard machine learning algorithms. We measured the loss of classification-relevant information due to each representation. Representations that captured status information explicitly resulted in significantly better performance. Algorithm performance was dependent on subtle differences in data representation.

Algorithms↗