SEARCH · PubMed Health

Results for “Predictive Learning Models”

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 865 records · Page 48Linked to original sources

PubMed2004

Cognitive navigation based on nonuniform Gabor space sampling, unsupervised growing networks, and reinforcement learning.

We study spatial learning and navigation for autonomous agents. A state space representation is constructed by unsupervised Hebbian learning during exploration. As a result of learning, a representation of the continuous two-dimensional (2-D) manifold in the high-dimensional input space is found. The representation consists of a population of localized overlapping place fields covering the 2-D space densely and uniformly. This space coding is comparable to the representation provided by hippocampal place cells in rats. Place fields are learned by extracting spatio-temporal properties of the environment from sensory inputs. The visual scene is modeled using the responses of modified Gabor filters placed at the nodes of a sparse Log-polar graph. Visual sensory aliasing is eliminated by taking into account self-motion signals via path integration. This solves the hidden state problem and provides a suitable representation for applying reinforcement learning in continuous space for action selection. A temporal-difference prediction scheme is used to learn sensorimotor mappings to perform goal-oriented navigation. Population vector coding is employed to interpret ensemble neural activity. The model is validated on a mobile Khepera miniature robot.

Cognition↗

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↗

PubMed1998

Quantization of human motions and learning of accurate movements.

This paper presents a mathematical model for the learning of accurate human arm movements. Its main features are that the movement is the superposition of smooth submovements, the intrinsic deviation of arm movements is considered, visual and kinesthetic feed-back are integrated in the motion control, and the movement duration and accuracy are optimized with practice. This model is consistent with the jerky arm movements of infants, and may explain how the adult motion behavior emerges from the infant behavior. Comparison with measurements of adult movements shows that the kinematics of accurate movements are well predicted by the model.

Adult↗

PubMed2006

Recent advances in computational prediction of drug absorption and permeability in drug discovery.

Approximately 40%-60% of developing drugs failed during the clinical trials because of ADME/Tox deficiencies. Virtual screening should not be restricted to optimize binding affinity and improve selectivity; and the pharmacokinetic properties should also be included as important filters in virtual screening. Here, the current development in theoretical models to predict drug absorption-related properties, such as intestinal absorption, Caco-2 permeability, and blood-brain partitioning are reviewed. The important physicochemical properties used in the prediction of drug absorption, and the relevance of predictive models in the evaluation of passive drug absorption are discussed. Recent developments in the prediction of drug absorption, especially with the application of new machine learning methods and newly developed software are also discussed. Future directions for research are outlined.

Computer Simulation↗

PubMed2002

Relearning of verbal labels in semantic dementia.

Semantic dementia is a degenerative disorder of temporal neocortex characterised by loss of word and object concepts. There is limited evidence that temporary relearning of lost vocabulary may be possible, attributed to sparing of hippocampal structures. However, learning is variable across patients and factors underlying learning success are poorly understood. The study investigated relearning of object names in two severely anomic semantic dementia patients. Following memory models that assume that hippocampal memories require some neocortical representation to underpin them it was predicted that relearning would be influenced by patients' residual semantic information about stimuli. Experiment 1 confirmed that residual knowledge influenced learning success. On the assumption that neocortical knowledge encompasses concepts of space and time, as well as words and objects, it was predicted that learning would be affected by the availability of contextual (temporo-spatial) information. Experiment 2 demonstrated effective learning of object names, attributed to the patient's use of temporal order and spatial position knowledge. Retention of object names over months was linked to the patient's capacity for autobiographical experiential (temporo-spatial contextual) association. The findings indicate that relearning of lost vocabulary is possible in semantic dementia, indicating a role of the medial temporal lobes in the acquisition of semantic information. Effective learning does not imply reinstatement of lost concepts, but, it is argued, does involve some reacquisition of meaning. The findings challenge the traditional semantic-episodic memory dichotomy and are consistent with a "levels of meaning" account of semantic memory.

Anomia↗

PubMed2005

A revised identical elements model of arithmetic fact representation.

The identical elements model of arithmetic fact representation (T. C. Rickard, A. F. Healy, & L. E. Bourne, 1994) states that, for each triplet of numbers (e.g., 4, 7, 28) that are related by complementary multiplication and division problems, there are 3 independent fact representations in memory: (4, 7, x) --> 28; (28/7) --> 4; and (28/4) --> 7. In this article, the author reviews the evidence for this model, considers alternative accounts, and proposes a simple and empirically motivated revision to the model that (a) accommodates conflicting results, (b) provides a novel account of the ties effect, and (c) makes new and nonintuitive predictions for the factoring operation (e.g., factoring of 28 into 4 and 7). The author reports 3 experiments designed to test these predictions and discusses implications for arithmetic instruction.

Cognition↗

PubMed2026

Mitochondria related gene signature serves as prognosis prediction and risk stratification of cholangiocarcinoma.

BACKGROUND: Cholangiocarcinoma (CHOL) is a highly aggressive biliary malignancy with poor clinical outcomes and limited effective prognostic biomarkers. Mitochondrial dysfunction participates in multiple oncological processes of CHOL, yet the prognostic roles of mitochondria‑related genes (MRGs) remain poorly understood. This study aimed to characterize MRGs expression in CHOL and develop a molecular prognostic model for predicting patient survival and guiding clinical management. METHODS: RNA sequencing (RNA-seq) and clinical data of CHOL were obtained from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) (GSE89748) databases. Differentially expressed MRGs were identified, and 10 machine learning algorithms were used to construct prognostic models. The optimal model (highest average C-index) was selected to establish a mitochondria-related risk score (MRRS), which was validated internally and externally. A nomogram integrating clinical factors and MRRS was developed, and biological mechanisms were explored via functional and immune analyses. RESULTS: A 3-MRG (MAP3K1, MRPL18, PYGB) prognostic signature was constructed, stratifying patients into high- and low-risk groups with significantly different overall survival. The model showed high predictive accuracy, with an area under the curve (AUC) up to 0.845, and MRRS was an independent prognostic factor. The signature was associated with mitochondrial pathways, and the high-risk group had distinct immune infiltration and mutation profiles. CONCLUSIONS: A validated MRG prognostic model effectively stratifies CHOL patients and has potential clinical value for prognosis prediction. Further validation in larger cohorts is needed to confirm its applicability.

Cholangiocarcinoma (CHOL)↗

PubMed2026

Identification of Immune Response-Related Proteomic Biomarkers in Moyamoya Disease Using Serum Olink Proteomics.

Moyamoya disease, a rare chronic cerebrovascular disorder, requires invasive digital subtraction angiography (DSA) for diagnosis. This study employed high-throughput proteomics to identify plasma biomarkers for Moyamoya disease diagnosis. We conducted immunopanel analysis using the Olink platform to evaluate 92 immune-related proteins in plasma samples from 88 Moyamoya disease patients and 88 healthy controls. Key proteins were identified through differential expression analysis, GO, and KEGG enrichment analysis. A diagnostic model was constructed using LASSO regression, Boruta algorithm, and machine learning models including random forest and XGBoost. Validation of these proteins was performed using GEO external data sets, followed by prediction of potential therapeutic drugs and molecular docking validation through pharmacogenomic databases. A total of 44 differentially expressed proteins were identified through the Olink immunopanel, with 12 downregulated and 32 upregulated. GO and KEGG analyses revealed significant enrichment of these proteins in innate immune responses and signaling pathways such as NF-kB and MAPK. Through LASSO, random forest, and protein under-area analysis, four potential biomarkers for Moyamoya disease (MGMT, SIT1, PRDX1, TRAF2) were identified. A diagnostic model using these proteins showed the highest AUC value with the XGBoost model. Additionally, TRAF2 and PRDX1 exhibited significant expression differences in Moyamoya disease patients within the GEO data set. Our study revealed the immune landscape of Moyamoya disease, identified four biomarkers, and established a variety of diagnostic models.

Humans↗

PubMed1996

TraceLink: a model of amnesia and consolidation of memory.

A model of amnesia is introduced, called TraceLink, that consists of three systems: 1) a trace system (neocortex), 2) a link system (hippocampus), and 3) a modulatory system (hippocampus/fornix/basal forebrain). It aims to explain salient aspects of the neuropsychology of amnesia, such as Ribot gradients in retrograde amnesia, patterns of dissociation between anterograde and retrograde amnesia, recovery from amnesia, and a newly discovered form of amnesia (semantic dementia) that results from certain temporal lobe lesions that do not affect the hippocampus. The model, furthermore, offers a new explanation for the global neuroanatomy of the hippocampus and neocortex based on the assumption that the brain aims to minimize connectivity volume. It also offers various strategies for the consolidation of memory, the effects of which are explored in computer simulations. The paper concludes with ten, largely untested; predictions derived from the TraceLink model.

Amnesia, Retrograde↗

PubMed1988

Effect of irrelevant differences as a function of the relations between relevant and irrelevant dimensions in the same-different task.

The effects of irrelevant differences as a function of the relations between relevant and irrelevant dimensions in the same-different task were examined. Form, size, and orientation were used as task conditions in Experiment 1, and form, size, and color were used in Experiment 2. In each experiment, 6 subjects were instructed to report same or different according to a relevant dimension, irrespective of two irrelevant dimensions. In Experiment 3, the degree of integrality was examined in all the combinations of dimensions involved, in the restricted-classification task. The results of the three experiments suggested that (a) effects of irrelevant differences depended on the degree of integrality between relevant and irrelevant dimensions, and (b) two irrelevant dimensions were processed by the subjects serially. Neither the relevance rechecking model (Miller & Bauer, 1981) nor the response competition model (e.g., Williams, 1974) alone could explain all the types of effects of irrelevant dimensions obtained in this study. Instead, a modified relevance rechecking model, in which the degree of integrality was introduced to the original relevance rechecking model, could predict and explain all types of effects.

Adult↗

PubMed2000

The effects of massive repetition on speeded recognition of faces.

Models of face processing suggest that recognizing a person should prime recognition of a consecutive, but different, image of the same person. This prediction is tested in four experiments using large blocks of different views of the same person. The experiments demonstrate that reaction times decreased according to a negative power function as the number of repetitions increased. After sufficient repetitions, however, the reaction times lengthened. The presentation of a different familiar person between blocks of repetitions caused the reaction time for the target to increase to a level equivalent to that with no repetitions. Experiments 2 and 3 investigated the effect of different intervening stimuli (unfamiliar faces and objects). Such stimuli reduced the effect of mass repetition--but the reduction using a familiar face was greater than that with either unfamiliar faces or objects. Experiment 4 confirmed that the effects of massive repetition occur for a face familiarity task as well as for face identification tasks. The results are discussed in terms of the predictions of Burton's (1994) IACL model.

Association Learning↗

PubMed1999

Significantly lower entropy estimates for natural DNA sequences.

If DNA were a random string over its alphabet {A, C, G, T}, an optimal code would assign two bits to each nucleotide. DNA may be imagined to be a highly ordered, purposeful molecule, and one might therefore reasonably expect statistical models of its string representation to produce much lower entropy estimates. Surprisingly, this has not been the case for many natural DNA sequences, including portions of the human genome. We introduce a new statistical model (compression algorithm), the strongest reported to date, for naturally occurring DNA sequences. Conventional techniques code a nucleotide using only slightly fewer bits (1.90) than one obtains by relying only on the frequency statistics of individual nucleotides (1.95). Our method in some cases increases this gap by more than fivefold (1.66) and may lead to better performance in microbiological pattern recognition applications. One of our main contributions, and the principle source of these improvements, is the formal inclusion of inexact match information in the model. The existence of matches at various distances forms a panel of experts which are then combined into a single prediction. The structure of this combination is novel and its parameters are learned using Expectation Maximization (EM). Experiments are reported using a wide variety of DNA sequences and compared whenever possible with earlier work. Four reasonable notions for the string distance function used to identify near matches, are implemented and experimentally compared. We also report lower entropy estimates for coding regions extracted from a large collection of nonredundant human genes. The conventional estimate is 1.92 bits. Our model produces only slightly better results (1.91 bits) when considering nucleotides, but achieves 1.84-1.87 bits when the prediction problem is divided into two stages: (i) predict the next amino acid-based on inexact polypeptide matches, and (ii) predict the particular codon. Our results suggest that matches at the amino acid level play some role, but a small one, in determining the statistical structure of nonredundant coding sequences.

Algorithms↗

PubMed1993

A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information.

We present a biologically plausible model of an attentional mechanism for forming position- and scale-invariant representations of objects in the visual world. The model relies on a set of control neurons to dynamically modify the synaptic strengths of intracortical connections so that information from a windowed region of primary visual cortex (V1) is selectively routed to higher cortical areas. Local spatial relationships (i.e., topography) within the attentional window are preserved as information is routed through the cortex. This enables attended objects to be represented in higher cortical areas within an object-centered reference frame that is position and scale invariant. We hypothesize that the pulvinar may provide the control signals for routing information through the cortex. The dynamics of the control neurons are governed by simple differential equations that could be realized by neurobiologically plausible circuits. In preattentive mode, the control neurons receive their input from a low-level "saliency map" representing potentially interesting regions of a scene. During the pattern recognition phase, control neurons are driven by the interaction between top-down (memory) and bottom-up (retinal input) sources. The model respects key neurophysiological, neuroanatomical, and psychophysical data relating to attention, and it makes a variety of experimentally testable predictions.

Animals↗

PubMed2004

Software reliability prediction using recurrent neural network with Bayesian regularization.

A recurrent neural network modeling approach for software reliability prediction with respect to cumulative failure time is proposed. Our proposed network structure has the capability of learning and recognizing the inherent internal temporal property of cumulative failure time sequence. Further, by adding a penalty term of sum of network connection weights, Bayesian regularization is applied to our network training scheme to improve the generalization capability and lower the susceptibility of overfitting. The performance of our proposed approach has been tested using four real-time control and flight dynamic application data sets. Numerical results show that our proposed approach is robust across different software projects, and has a better performance with respect to both goodness-of-fit and next-step-predictability compared to existing neural network models for failure time prediction.

Algorithms↗

PubMed2006

Lessons learned from LNG safety research.

During the period from 1977 to 1989, the Lawrence Livermore National Laboratory (LLNL) conducted a liquefied gaseous fuels spill effects program under the sponsorship of the US Department of Energy, Department of Transportation, Gas Research Institute and others. The goal of this program was to develop and validate tools that could be used to predict the effects of a large liquefied gas spill through the execution of large scale field experiments and the development of computer models to make predictions for conditions under which tests could not be performed. Over the course of the program, three series of LNG spill experiments were performed to study cloud formation, dispersion, combustion and rapid phase transition (RPT) explosions. The purpose of this paper is to provide an overview of this program, the lessons learned from 12 years of research as well as some recommendations for the future. The general conclusion from this program is that cold, dense gas related phenomena can dominate the dispersion of a large volume, high release rate spill of LNG especially under low ambient wind speed and stable atmospheric conditions, and therefore, it is necessary to include a detailed and validated description of these phenomena in computer models to adequately predict the consequences of a release. Specific conclusions include: * LNG vapor clouds are lower and wider than trace gas clouds and tend to follow the downhill slope of terrain due to dampened vertical turbulence and gravity flow within the cloud. Under low wind speed, stable atmospheric conditions, a bifurcated, two lobed structure develops. * Navier-Stokes models provide the most complete description of LNG dispersion, while more highly parameterized Lagrangian models were found to be well suited to emergency response applications. * The measured heat flux from LNG vapor cloud burns exceeded levels necessary for third degree burns and were large enough to ignite most flammable materials. * RPTs are of two types, source generated and enrichment generated, and were observed to increase the burn area by a factor of two and to extend the downwind burn distance by 65%. Additional large scale experiments and model development are recommended.

Accidents↗

PubMed2004

Three new consensus QSAR models for the prediction of Ames genotoxicity.

Three QSAR methods, artificial neural net (ANN), k-nearest neighbors (kNN), and Decision Forest (DF), were applied to 3363 diverse compounds tested for their Ames genotoxicity. The ratio of mutagens to non-mutagens was 60/40 for this dataset. This group of compounds includes >300 therapeutic drugs. All models were developed using the same initial set of 148 topological indices: molecular connectivity chi indices and electrotopological state indices (atom-type, bond-type and group-type E-state), as well as binary indicators. While previous studies have found logP to be a determining factor in genotoxicity, it was not found to be important by any modeling method employed in this study. The three models yielded an average training/test concordance value of 88%, with a low percentage of false positives and false negatives. External validation testing on 400 compounds not used for QSAR model development gave an average concordance of 82%. This value increased to 92% upon removal of less reliable outcomes, as determined by a reliability criterion used within each model. The ANN model showed the best performance in predicting drug compounds, yielding 97% concordance (34/35 drugs) after the removal of less reliable predictions. The appreciable commonality found among the top 10 ranked descriptors from each model is of particular interest because of the diversity in the learning algorithms and descriptor selection techniques employed in this study. Forty percent of the most important descriptors in any one model are found in one or two other models. Fourteen of the most important descriptors relate directly to known toxicophores involved in potent genotoxic responses in Salmonella typhimurium. A comparison of the validation results with those of MULTICASE and DEREK indicated that the new models presented in this work perform substantially better than the former models in predicting genotoxicity of therapeutic drugs. Substantially higher specificity was achieved with these new models as compared with MULTICASE or DEREK with comparable sensitivities among all models.

Algorithms↗

PubMed2004

Strategy execution in cognitive skill learning: an item-level test of candidate models.

This article investigates the transition to memory-based performance that commonly occurs with practice on tasks that initially require use of a multistep algorithm. In an alphabet arithmetic task, item response times exhibited pronounced step-function decreases after moderate practice that were uniquely predicted by T. C. Rickard's (1997) component power laws model. The results challenge parallel strategy execution models as developed to date and they demonstrate that the shift to retrieval is an item-specific, as opposed to task-general, learning phenomenon. The results also call into question the entire class of smooth speed-up functions as global empirical learning laws. It is shown that overlaying of averaged item fits on averaged data can provide a sensitive test for model sufficiency. Strategy probes agreed with strategy inferences that were based on step-function speed-up patterns, supporting the validity of the probing technique.

Cognition↗

PubMed2001

Effects of Training Goals and Goal Orientation Traits on Multidimensional Training Outcomes and Performance Adaptability.

This research examined the effects of mastery vs. performance training goals and learning and performance goal orientation traits on multidimensional outcomes of training. Training outcomes included declarative knowledge, knowledge structure coherence, training performance, and self-efficacy. We also examined the unique impact of the training outcomes on performance adaptability by predicting generalization to a more difficult and complex version of the task. The experiment involved 60 trainees learning a complex computer simulation over 2 days. The research model posited independent effects for training goals relative to goal orientation traits and independent contributions of training outcomes to the performance adaptability of trainees. The findings were consistent with the proposed model. In particular, self-efficacy and knowledge structure coherence made unique contributions to the prediction of performance adaptability after controlling for prior training performance and declarative knowledge. Implications and extensions are discussed. Copyright 2001 Academic Press.

Journal Article↗