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 703 records · Page 39Linked to original sources

PubMed2005

Cue interaction effects in causal judgement: an interpretation in terms of the evidential evaluation model.

In judging the extent to which a cue causes an outcome, judgement can be affected by information about other cues that are correlated with the one being judged. These cue interaction effects have usually been interpreted in terms of associative learning processes. I propose that a different model of causal judgement, the evidential evaluation model, offers a viable alternative interpretation of cue interaction phenomena. Under the evidential evaluation model, instances of contingency information are interpreted as evidence, which is confirmatory, disconfirmatory, or irrelevant for the cue being judged. When two cues co-occur in a set of instances the evidential value of the instances for one of them is determined by three factors: the proportion of confirming instances in the set; disambiguation value, which concerns the relation between the set of information and prior beliefs about the co-occurring cue; and confirmation value, which concerns the relation between the set of information and prior beliefs about the cue being judged. Any previous judgement of the cue is then modified in the light of these. It is shown that this model can account for all the cue interaction phenomena that have been investigated in studies of human causal judgement. The model also generates novel predictions, and the results of three experiments give support to these predictions. It is also shown that several other current models of causal judgement fail to predict a key result from Experiment 3.

Analysis of Variance↗

PubMed1994

Spatial planning deficits in limb apraxia.

Geschwind (1975) proposed a disconnection model in which an apraxic subject is unable to carry out movements to command because the left hemisphere that comprehended the verbal command is disconnected from the right premotor and motor areas which controls the left hand. An alternate model, however, proposes that apraxia results from destruction of spatiotemporal representations of learned movement stored in the left hemisphere (Heilman, 1979). The disconnection hypothesis would predict that apraxic subjects should be able to correctly imitate gestures and correctly use actual tools since these tasks do not require language. The movement representation model predicts that imitation and actual tool use would also be impaired. Motion analyses were performed on the trajectories of repetitive 'slicing' gestures made in a series of conditions in which contextual cues were introduced in a graded fashion. Four cue conditions were presented: no cues (verbal command), object present, tool present and both object and tool present. Positions of the hand, wrist, elbow, and shoulder were digitized from neighbouring views, reconstructed in three dimensions and analysed with respect to specific spatiotemporal features of the trajectories. Three subjects with limb apraxia, who had lesions that included left parietal cortex, and four neurologically intact subjects participated. The apraxic subjects showed disturbances in planning the movement of the hand in space across the cue conditions. For example, they showed deficits in the plane of motion, the shape of the trajectory and in the coupling of hand speed and trajectory shape even when given full contextual cues. These data support the hypothesis that apraxia can result from the destruction of spatiotemporal representations of learned movement, rather than from a disconnection between the receptive language areas in the left hemisphere and the contralateral motor cortices.

Aged↗

PubMed2026

RCoxNet: A Deep Learning Framework Integrating Random Walk with Restart, Mutation, and Clinical Data for Cancer Survival Prediction.

Accurate survival prediction in cancer remains challenging due to the sparsity of somatic mutation profiles and the failure of existing models to capture higher-order gene-gene dependencies. Network diffusion methods such as Random Walk with Restart (RWR) can propagate mutation signals across protein-protein interaction (PPI) networks to address sparsity, yet their integration within a deep learning Cox survival framework has not been comprehensively benchmarked across multiple cancer cohorts. We present RCoxNet, a deep learning framework that maps somatic mutation profiles onto a ConsensusPathDB-derived PPI network via RWR, selects prognostic genes by log-rank filtering, and processes network-informed mutation scores through three fully connected hidden layers feeding into a Cox proportional hazards output. RCoxNet was evaluated on The Cancer Genome Atlas (TCGA) cohorts for four cancer types (breast invasive carcinoma [BRCA], lung adenocarcinoma [LUNG], glioblastoma multiforme [GBM], and ovarian serous cystadenocarcinoma [OV]) using 20 independent random splits. The model achieved mean C-index values of 0.807 ± 0.044 (BRCA), 0.750 ± 0.039 (LUNG), 0.704 ± 0.041 (GBM), and 0.668 ± 0.036 (OV), consistently outperforming DeepSurv, Cox-nnet, SurvivalNet, Cox Elastic-Net (Cox-EN), and DeepHit, with statistically significant gains over Cox-EN, Cox-nnet, SurvivalNet, and DeepHit across the majority of cohorts. RCoxNet demonstrates that embedding sparse mutation profiles into a PPI network context substantially improves cancer survival prediction and yields biologically interpretable prognostic features relevant to precision oncology.

cancer survival prediction↗

PubMed2000

Learning non-stationary conditional probability distributions.

While sophisticated neural networks and graphical models have been developed for predicting conditional probabilities in a non-stationary environment, major improvements in the training schemes are still required to make these approaches practically viable.

Models, Neurological↗

PubMed2006

transFold: a web server for predicting the structure and residue contacts of transmembrane beta-barrels.

Transmembrane beta-barrel (TMB) proteins are embedded in the outer membrane of Gram-negative bacteria, mitochondria and chloroplasts. The cellular location and functional diversity of beta-barrel outer membrane proteins makes them an important protein class. At the present time, very few non-homologous TMB structures have been determined by X-ray diffraction because of the experimental difficulty encountered in crystallizing transmembrane (TM) proteins. The transFold web server uses pairwise inter-strand residue statistical potentials derived from globular (non-outer-membrane) proteins to predict the supersecondary structure of TMB. Unlike all previous approaches, transFold does not use machine learning methods such as hidden Markov models or neural networks; instead, transFold employs multi-tape S-attribute grammars to describe all potential conformations, and then applies dynamic programming to determine the global minimum energy supersecondary structure. The transFold web server not only predicts secondary structure and TMB topology, but is the only method which additionally predicts the side-chain orientation of transmembrane beta-strand residues, inter-strand residue contacts and TM beta-strand inclination with respect to the membrane. The program transFold currently outperforms all other methods for accuracy of beta-barrel structure prediction. Available at http://bioinformatics.bc.edu/clotelab/transFold.

Amino Acids↗

PubMed2000

The importance of frameworks for directing empirical questions: reply to Goodie and Fantino (2000).

A. S. Goodie and E. Fantino (2000) make two main criticisms of the predictions of M. C. Lovett and C. D. Schunn's (1999) RCCL model. (RCCL is pronounced "ReCyCLe"; it stands for Represent the task, Construct a set of action strategies, Choose from among those strategies according to success rate, Learn new success rates.) In both cases, the authors believe the criticisms reflect a failure to appreciate the difference between broad frameworks and specific mathematical/computational models. In this article, the value of a broad framework, such as RCCL, in directing new empirical analyses and guiding theoretical development is shown. In particular, RCCL expands on existing work to reveal how variability and change in mental representations influence base-rate sensitivity. The authors also address several other issues raised by A. S. Goodie and E. Fantino (2000) and show that qualitative shifts in individuals' choice behavior are present in their original data--a key prediction of RCCL that does not appear in previous accounts.

Decision Making↗

PubMed1999

HyFIS: adaptive neuro-fuzzy inference systems and their application to nonlinear dynamical systems.

This paper proposes an adaptive neuro-fuzzy system, HyFIS (Hybrid neural Fuzzy Inference System), for building and optimising fuzzy models. The proposed model introduces the learning power of neural networks to fuzzy logic systems and provides linguistic meaning to the connectionist architectures. Heuristic fuzzy logic rules and input-output fuzzy membership functions can be optimally tuned from training examples by a hybrid learning scheme comprised of two phases: rule generation phase from data; and rule tuning phase using error backpropagation learning scheme for a neural fuzzy system. To illustrate the performance and applicability of the proposed neuro-fuzzy hybrid model, extensive simulation studies of nonlinear complex dynamic systems are carried out. The proposed method can be applied to an on-line incremental adaptive learning for the prediction and control of nonlinear dynamical systems. Two benchmark case studies are used to demonstrate that the proposed HyFIS system is a superior neuro-fuzzy modelling technique.

Journal Article↗

PubMed2006

Effect of stimulus orderability and reinforcement history on transitive responding in pigeons.

Transitive responding in humans and non-human animals has attracted considerable attention because of its presumably inferential nature. In an attempt to replicate our earlier study with crows [Lazareva, O.F., Smirnova, A.A., Bagozkaja, M.S., Zorina, Z.A., Rayevsky, V.V., Wasserman, E.A., 2004. Transitive responding in hooded crows requires linearly ordered stimuli. J. Exp. Anal. Behav. 82, 1-19], we trained pigeons to discriminate overlapping pairs of colored squares (A+ B-, B+ C-, C+ D-, and D+ E-). For some birds, the colored squares, or primary stimuli, were followed by a circle of the same color (feedback stimuli) whose diameter decreased from A to E (Ordered Feedback group); these circles were made available to help order the stimuli along a physical dimension. For other birds, all of the feedback stimuli had the same diameter (Constant Feedback group). In later testing, novel choice pairs were presented, including the critical BD pair. The pigeons' reinforcement history with Stimuli B and D was controlled, so that the birds should not have chosen Stimulus B during the BD test. Unlike the crows, the pigeons selected Stimulus B over Stimulus D in both ordered and Constant Feedback groups, suggesting that the orderability of the post-choice feedback stimuli did not affect pigeons' transitive responding. Post hoc simulations showed that associative models [Wynne, C.D.L., 1995. Reinforcement accounts for transitive inference (TI) performance. Anim. Learn. Behav. 23, 207-217; Siemann, M., Delius, J.D., 1998. Algebraic learning and neural network models for transitive and non-transitive responding. Eur. J. Cogn. Psychol. 10, 307-334] failed to predict pigeons' responding in the BD test.

Animals↗

PubMed1996

Causal order does not affect cue selection in human associative learning.

Waldmann and Holyoak (1992) presented evidence in support of the claim that cue selection does not emerge in "diagnostic" human learning tasks in which the cues are interpretable as effects and the outcomes as the causes of those effects. Waldmann and Holyoak argued that this evidence presents a major difficulty for associationist theories of learning and instead supports a "causal model" theory. We identify a number of flaws in Waldmann and Holyoak's experimental procedures and report three new experiments designed to test their claim. In Experiment 1, cue selection was observed regardless of causal order and regardless of whether the cues were abstractly or concretely specified. In Experiments 2 and 3, cue selection was again observed when subjects predicted causes from effects. We conclude that our results are consistent with simple associationist theories of learning but contradict Waldmann and Holyoak's causal model theory.

Adult↗

PubMed1999

Minimizing strain and maximizing learning: the role of job demands, job control, and proactive personality.

Using a sample of 268 production employees, this study extended research on R. Karasek's (1979) demands-control model of stress in 2 ways. First, results show that R. Karasek's proposed interaction between demands and control when predicting strain occurred only for more proactive employees. This 3-way interaction helps reconcile previous inconsistent findings about the interaction between demands and control when predicting strain. Second, the study extends research by investigating the demands-control interaction and the moderating influence of proactive personality in relation to learning-oriented outcomes (perceived mastery, role breadth self-efficacy, and production ownership). There were no 3-way interactions among the variables when predicting these learning-oriented outcomes, but all were important predictors. These results show (a) that demands and control can influence learning as proposed in the dynamic version of the demands-control model and (b) that proactive personality plays an important moderating role.

Achievement↗

PubMed1999

Cognitive functioning and health as determinants of mortality in an older population.

The authors studied whether the ability of cognitive functioning to predict mortality is pervasive or specific, and they considered the role of health in the cognition-mortality association. Data were taken from a sample of 2,380 persons aged 55-85 years who took part in the Netherlands' Longitudinal Aging Study Amsterdam in 1992-1993. Five cognitive measures were distinguished: general cognitive functioning, information processing speed, fluid intelligence, learning, and proportion retained. Mortality data were obtained during an average follow-up period of 1,215 days. Cox proportional hazards regression models revealed that all cognitive functions predicted mortality independent of age, sex, education, and depressive symptoms. When health (self-rated health, medication use, physical performance, functional limitations, lung function, specific chronic diseases) was also taken into account, information processing speed, fluid intelligence, and proportion retained remained independent predictors of mortality, whereas the ability of general cognitive functioning and learning to determine mortality was lost. The authors concluded that the ability of cognitive functioning to predict mortality is pervasive to all cognitive functions that were included in the study when age, sex, education, and depressive symptoms are considered and is more specific to some functions when also controlling for health.

Activities of Daily Living↗

PubMed2006

Ab initio prediction of peptide-MHC binding geometry for diverse class I MHC allotypes.

Since determining the crystallographic structure of all peptide-MHC complexes is infeasible, an accurate prediction of the conformation is a critical computational problem. These models can be useful for determining binding energetics, predicting the structures of specific ternary complexes with T-cell receptors, and designing new molecules interacting with these complexes. The main difficulties are (1) adequate sampling of the large number of conformational degrees of freedom for the flexible peptide, (2) predicting subtle changes in the MHC interface geometry upon binding, and (3) building models for numerous MHC allotypes without known structures. Whereas previous studies have approached the sampling problem by dividing the conformational variables into different sets and predicting them separately, we have refined the Biased-Probability Monte Carlo docking protocol in internal coordinates to optimize a physical energy function for all peptide variables simultaneously. We also imitated the induced fit by docking into a more permissive smooth grid representation of the MHC followed by refinement and reranking using an all-atom MHC model. Our method was tested by a comparison of the results of cross-docking 14 peptides into HLA-A*0201 and 9 peptides into H-2K(b) as well as docking peptides into homology models for five different HLA allotypes with a comprehensive set of experimental structures. The surprisingly accurate prediction (0.75 A backbone RMSD) for cross-docking of a highly flexible decapeptide, dissimilar to the original bound peptide, as well as docking predictions using homology models for two allotypes with low average backbone RMSDs of less than 1.0 A illustrate the method's effectiveness. Finally, energy terms calculated using the predicted structures were combined with supervised learning on a large data set to classify peptides as either HLA-A*0201 binders or nonbinders. In contrast with sequence-based prediction methods, this model was also able to predict the binding affinity for peptides to a different MHC allotype (H-2K(b)), not used for training, with comparable prediction accuracy.

Binding Sites↗

PubMed2001

Reading the three-dimensional structure of lattice model-designed proteins from their amino acid sequence.

While all the information required for the folding of a protein is contained in its amino acid sequence, one has not yet learned how to extract this information to predict the detailed, biological active, three-dimensional structure of a protein whose sequence is known. Using insight obtained from lattice model simulations of the folding of small proteins (fewer than 100 residues), in particular of the fact that this phenomenon is essentially controlled by conserved contacts (Mirny et al., Proc Natl Acad Sci USA 1995;92:1282) among (few) strongly interacting ("hot") amino acids (Tiana et al., J Chem Phys 1998;108:757-761), which also stabilize local elementary structures formed early in the folding process and leading to the (postcritical) folding core when they assemble together (Broglia et al., Proc Natl Acad Sci USA 1998;95:12930, Broglia & Tiana, J Chem Phys 2001;114:7267), we have worked out a successful strategy for reading the three-dimensional structure of lattice model-designed proteins from the knowledge of only their amino acid sequence and of the contact energies among the amino acids.

Amino Acid Sequence↗

PubMed2006

Skin conductance responses are elicited by the airway sensory effects of puffs from cigarettes.

The airway sensations stimulated by smoking are an important source of hedonic impact (pleasure) for dependent smokers. The learning process by which these sensations become pleasurable is not well understood. The classical conditioning model predicts that airway sensory stimulation will elicit sympathetic arousal that is positively correlated with the hedonic impact that is elicited by airway sensory stimulation. To test this prediction, we measured skin conductance responses (SCRs) and subjective hedonic impact elicited by a series of individual puffs from nicotinized, denicotinized and unlit cigarettes. Nicotinized puffs elicited more subjective hedonic impact than denicotinized and unlit puffs partly as a result of the fact that they provided a greater level of airway sensory stimulation. We found that SCRs were not larger for nicotinized puffs than for denicotinized puffs, but that they were larger for both nicotinized and denicotinized puffs than for unlit puffs. We also found that the average SCR of a subject to denicotinized puffs was positively correlated with the average hedonic impact that a subject obtained from denicotinized puffs. Together, this suggests that SCR magnitude does not reflect within-subject variations in hedonic impact that are due to variations in the level of airway sensory stimulation, but that it does reflect individual differences in the amount of hedonic impact that is derived from a given level of airway sensory stimulation. The results of a post hoc correlation analysis suggest that these individual differences may have been due to variations in the prevailing urge to smoke. The implications of these findings for the classical conditioning model, as well as for other learning models, are discussed.

Adolescent↗

PubMed2000

Acute stress induced modifications of calcium signaling in learned helpless rats.

Previous reports have demonstrated reduced elevations of free intracellular calcium concentration in blood cells of depressed patients after various stimuli. Therefore, a disturbance of intracellular calcium (Ca2+) homeostasis has been postulated to be involved in the pathophysiology of mood disorders. It was the aim of the present study to investigate whether Ca2+ signaling was affected in spleen T-lymphocytes of rats submitted to a learned helplessness paradigm, an animal model of depression with a high level of construct, face and predictive validity. In addition, we tested for effects of acute stress on the Ca2+ signaling in helpless rats, as compared to non-stressed rats. It was found that mitogen-induced Ca2+ signaling only tended to be reduced in helpless rats. However, when helpless rats were submitted to acute immobilization stress, Ca2+ signaling appeared to be significantly blunted, whereas the same stressor did not affect Ca2+ signaling in the non-helpless control rats. These acute stress-induced differences in Ca2+ signaling were not paralleled by a differential increase in plasma corticosterone. It is hypothesized that blunted Ca2+ signaling, as assessed in spleen T-lymphocytes of helpless rats, may be a correlate of the increased vulnerability of helpless rats to acute stressors.

Animals↗

PubMed1988

Effects of alcohol conditioning and expectancy on a visuo-motor integration task.

Two experiments were performed in which the classical conditioning model of tolerance, the habituation theory of tolerance, and state dependent learning theory made conflicting predictions. In the first experiment, alcohol conditioning did not produce a compensatory response under placebo on a visuo-motor integration task, but disguised alcohol produced a large decrement in performance. Since the results were consistent both with habituation and state dependent learning theories, a second experiment was performed in which all subjects received alcohol, but half were told that they were receiving pure tonic water. The finding of no expectancy effect was inconsistent with habituation theory, but fully consistent with state dependent learning theory.

Adult↗

PubMed2004

Predictors of substance use among homeless youth in San Diego.

This study examined the frequency of substance use among 14- to 24-year-old homeless youth (N=113) recruited from two community drop-in centers and explored the relationship between substance use and hypothesized psychosocial predictors. Audio-computer-assisted self-interviewing (A-CASI) was used for assessment. Including alcohol and tobacco, the mean number of different drugs used was 3.55 for lifetime and 2.34 for the last 3 months. A three-block hierarchical multiple regression was conducted to determine potential predictors of overall drug use (the sum of all different drugs used) during the last 3 months. Block 1 included demographic variables, Block 2 included a parental monitoring variable, and Block 3 included peer and environmental variables derived from learning theories. Parental monitoring (-) and peer variables (+) predicted overall 3-month drug use. The final model explained 36% of the variance in overall drug use. Results suggest that homeless adolescent drug use exists at high levels and is related to parental monitoring and peer modeling of other risk behaviors. These results may inform future prevention strategies for homeless youth and other high-risk populations.

Adolescent↗

PubMed2002

Hippocampal and neocortical contributions to memory: advances in the complementary learning systems framework.

The complementary learning systems framework provides a simple set of principles, derived from converging biological, psychological and computational constraints, for understanding the differential contributions of the neocortex and hippocampus to learning and memory. The central principles are that the neocortex has a low learning rate and uses overlapping distributed representations to extract the general statistical structure of the environment, whereas the hippocampus learns rapidly using separated representations to encode the details of specific events while minimizing interference. In recent years, we have instantiated these principles in working computational models, and have used these models to address human and animal learning and memory findings, across a wide range of domains and paradigms. Here, we review a few representative applications of our models, focusing on two domains: recognition memory and animal learning in the fear-conditioning paradigm. In both domains, the models have generated novel predictions that have been tested and confirmed.

Journal Article↗