Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Ensemble learning”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

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

At least 181 records · Page 10Linked to original sources
PubMed1998

Distributed encoding and retrieval of spatial memory in the hippocampus.

To determine whether memory is processed in a localized or distributed manner by the hippocampus, we inactivated small regions of the structure in pretrained rats before a retention test. Ibotenic acid-induced lesions removing 40% of the hippocampal tissue disrupted retrieval of spatial memory in a water maze but failed to affect new learning or retrieval of a task that was acquired postoperatively. Partial inactivation of the hippocampus by local intrahippocampal 5-aminomethyl-3-hydroxyisoxazole muscimol infusion also impaired retrieval but not new learning. This impairment was temporary; infusions had no effect on retrieval of predrug performance when the test was conducted 48 hr after the infusion. Systematic variation of the volume of dorsal and ventral hippocampal lesions showed that successful retrieval required the integrity of the entire dorsal 70% of the hippocampus. Our data suggest that although spatial tasks can be acquired with local ensembles of hippocampal neurons when other parts of the hippocampus are inactivated, spatial memory is normally both encoded and retrieved by a widely distributed hippocampal network.

Animals↗
PubMed1991

Dissociation of brain sites necessary for registration and storage of memory for a one-trial passive avoidance task in the chick.

Although memory formation occurs in a sequence of pharmacologically dissociable stages, many models assume that this sequence is located within a single neuronal ensemble. Three forebrain areas in the young chick-the intermediate medial hyperstriatum ventrale (IMHV), the lobus parolfactorius (LPO), and the paleostriatum augmentatum--have been identified as important structures in mediating learning and memory processes. It has been shown that pretraining lesions placed to the left IMHV produce amnesia for a 1-trial passive avoidance task. Posttraining lesions in the IMHV are not amnestic. The present study demonstrated that bilateral lesions to the LPO are amnestic but only if made subsequent to rather than before training. These results suggest that long-term storage of the memory is dependent on the LPO. Further experiments determined that in the absence of the LPO at training, the right IMHV can act a long-term memory storage site. In the absence of the right IMHV at training, other, as yet undetermined, areas can take up this role.

Afferent Pathways↗
PubMed2001

Receptive fields in the rat piriform cortex.

Current models of odor discrimination in mammals involve molecular feature detection by a large family of diverse olfactory receptors, refinement of molecular feature extraction through precise projections of olfactory receptor neurons to the olfactory bulb to form an odor-specific spatial map of molecular features across glomerular layer, and synthesis of these features into odor objects within the piriform cortex. This review describes our recent work on odor and spatial receptive fields within the anterior piriform cortex and compares these fields with receptive fields of their primary afferent, olfactory bulb mitral/tufted cells. The results suggest that receptive fields in the piriform cortex are ensemble in nature, highly dynamic, and may contribute to odor discrimination and odor memory.

Animals↗
PubMed2006

A connectionist computational model for epistemic and temporal reasoning.

The importance of the efforts to bridge the gap between the connectionist and symbolic paradigms of artificial intelligence has been widely recognized. The merging of theory (background knowledge) and data learning (learning from examples) into neural-symbolic systems has indicated that such a learning system is more effective than purely symbolic or purely connectionist systems. Until recently, however, neural-symbolic systems were not able to fully represent, reason, and learn expressive languages other than classical propositional and fragments of first-order logic. In this article, we show that nonclassical logics, in particular propositional temporal logic and combinations of temporal and epistemic (modal) reasoning, can be effectively computed by artificial neural networks. We present the language of a connectionist temporal logic of knowledge (CTLK). We then present a temporal algorithm that translates CTLK theories into ensembles of neural networks and prove that the translation is correct. Finally, we apply CTLK to the muddy children puzzle, which has been widely used as a test-bed for distributed knowledge representation. We provide a complete solution to the puzzle with the use of simple neural networks, capable of reasoning about knowledge evolution in time and of knowledge acquisition through learning.

Algorithms↗
PubMedDate not supplied

Extracting the principal behavior of a probabilistic supervisor through neural networks ensemble.

In this paper, we propose a model of a neural network ensemble that can be trained with a supervisor having two kinds of input-output functions where the occurrence probability of each function is not even. This condition can be likened to a learning condition, in which the learning data are hampered by noise. In this case, the neural network has the impression that the learning supervisor (object) has a probabilistic behavior in which the supervisor generates correct learning data most of the time but occasionally generates erroneous ones. The objective is to train the neural network to approximate the greatest distributed input-output relation, which can be considered to be the principal nature of the supervisor, so that we can obtain a neural network that is able, to some extent, to suppress the ill effect of erroneous data encountered during the learning process.

Algorithms↗
PubMed2026

GENKI: A generative framework for scalable and robust metabolic kinetic modeling.

GENKI (Generative ENsemble KPI-Informed) is a variational autoencoder-based framework for large-scale kinetic modeling of metabolism. Developed for metabolic engineering applications, GENKI is designed to improve the recovery of kinetically feasible models that reproduce experimentally observed phenotypes under genetic and environmental perturbations. The framework is trained on feasible kinetic model ensembles and uses phenotype-based key performance indicators (KPIs), derived from multi-omics and bioprocess data, to label and enrich models according to their agreement with mutant and condition-specific observations. This enables targeted generation of biologically relevant parameter sets with improved predictive performance. Crucially, GENKI recovers kinetic parameter sets that jointly reproduce wild-type and multiple perturbed physiologies within a single model. We apply GENKI to large-scale kinetic models of Escherichia coli and Saccharomyces cerevisiae under enzyme perturbations and oxygen shifts. In both systems, GENKI enriches kinetic ensembles with models that more accurately reproduce experimentally observed physiologies across multiple perturbations and conditions. GENKI therefore provides a practical framework for perturbation-aware kinetic model refinement within iterative Design-Build-Test-Learn workflows.

DBTL↗
PubMed1995

Neuroleptic effects on acquisition and performance of learned behaviors: a reinterpretation.

It is well-established that dopamine facilitates motor responsiveness. However, neuroleptics--drugs that block dopaminergic transmission--do not affect equally motor responses to environmental stimuli: responses to some stimuli seem completely preserved while responses to other stimuli are greatly disturbed. For example, escape responses to a noxious stimulus are typically preserved, even when avoidance to a cue predicting the noxious stimulus is absent. In this paper, we propose a connectionist account of this differential effect. We assume that dopamine determines the "gain" of the function relating the activation of a neural ensemble to its excitatory or inhibitory input. Because such a function is necessarily non-linear, we show that the influence of gain on whether a neural ensemble reaches a "threshold" of activation is critically different for low and high excitatory drives. This analysis makes specific predictions about the effect of neuroleptics on motor responses at different stages of training.

Animals↗
PubMed2006

Decision tree methods in pharmaceutical research.

Decision trees are among the most popular of the new statistical learning methods being used in the pharmaceutical industry for predicting quantitative structure-activity relationships. This article reviews applications of decision trees in drug discovery research and extensions to the basic algorithm using hybrid or ensemble methods that improve prediction accuracy.

Chemistry, Pharmaceutical↗
PubMed2025

Lit-OTAR framework for extracting biological evidences from literature.

SUMMARY: The lit-OTAR framework, developed through a collaboration between Europe PMC and Open Targets, leverages deep learning to revolutionize drug discovery by extracting evidence from scientific literature for drug target identification and validation. This novel framework combines named entity recognition for identifying gene/protein (target), disease, organism, and chemical/drug within scientific texts, and entity normalization to map these entities to databases like Ensembl, Experimental Factor Ontology, and ChEMBL. Continuously operational, it has processed over 39 million abstracts and 4.5 million full-text articles and preprints to date, identifying more than 48.5 million unique associations that significantly help accelerate the drug discovery process and scientific research >29.9 m distinct target-disease, 11.8 m distinct target-drug, and 8.3 m distinct disease-drug relationships. AVAILABILITY AND IMPLEMENTATION: The results are accessible through Europe PMC's SciLite web app (https://europepmc.org/) and its annotations API (https://europepmc.org/annotationsapi), as well as via the Open Targets Platform (https://platform.opentargets.org/). The daily pipeline is available at https://github.com/ML4LitS/otar-maintenance, and the Open Targets ETL processes are available at https://github.com/opentargets.

Drug Discovery↗
PubMed2006

Relative spike timing in pairs of hippocampal neurons distinguishes the beginning and end of journeys.

Episodic memory organizes experience in time, so that we can review past events and anticipate the future. In a hippocampus-dependent memory task, spike timing in pairs of simultaneously active CA1 neurons with overlapping place fields distinguished the start and end of trials. At the common starting point of different journeys, the relative spike timing of the neurons was highly correlated. As the rat approached a common goal from different starting points, however, temporal firing patterns were strongly modulated across journeys even if the cells fired in the same spatial locations within fields, implying that different processes influenced when and where cells fire. Spike timing within hippocampal ensembles may thereby help parse the beginning from the end of episodes in memory.

Action Potentials↗
PubMed1998

Microcircuitry and function of the inferior olive.

The inferior olive, which provides the climbing fibers to Purkinje cells in the cerebellar cortex, has been implicated in various functions, such as learning and timing of movements, and comparing intended with achieved movements. For example, climbing-fiber activity could transmit error signals during eye-blink conditioning or adaptation of the vestibulo-ocular reflex, or it could carry motor command signals beating on the rhythm of the oscillating and synchronous firing of ensembles of olivary neurons, or both. In this review, we approach the controversial issue of olivocerebellar function from the perspective of the unique organization of the microcircuitry of the olivary neuropil. The characteristic glomeruli are formed by a core of long dendritic or axonal spines, each of which is innervated by both an inhibitory terminal derived from the hindbrain and an excitatory terminal derived from either an ascending or descending input. The dendritic spines, which originate from dendrites with varicosities carrying dendritic lamellar bodies, are coupled by gap junctions. By drawing a comparison with a computational model by Segev and Rall,which might be applicable to the typical olivary spine with its unique morphological features and combined excitatory and inhibitory input, we propose that the microcircuitry of the inferior olive is capable of functioning both in motor learning and motor timing, but does not directly compare intended with achieved movements.

Animals↗
PubMed2004

Abductive network committees for improved classification of medical data.

OBJECTIVES: To introduce abductive network classifier committees as an ensemble method for improving classification accuracy in medical diagnosis. While neural networks allow many ways to introduce enough diversity among member models to improve performance when forming a committee, the self-organizing, automatic-stopping nature, and learning approach used by abductive networks are not very conducive for this purpose. We explore ways of over-coming this limitation and demonstrate improved classification on three standard medical datasets. METHODS: Two standard 2-class medical datasets (Pima Indians Diabetes and Heart Disease) and a 6-class dataset (Dermatology) were used to investigate ways of training abductive networks with adequate independence, as well as methods of combining their outputs to form a network that improves performance beyond that of single models. RESULTS: Two- or three-member committees of models trained on completely or partially different subsets of training data and using simple output combination methods achieve improvements between 2 and 5 percentage points in the classification accuracy over the best single model developed using the full training set. CONCLUSIONS: Varying model complexity alone gives abductive network models that are too correlated to ensure enough diversity for forming a useful committee. Diversity achieved through training member networks on independent subsets of the training data outweighs limitations of the smaller training set for each, resulting in net gain in committee performance. As such models train faster and can be trained in parallel, this can also speed up classifier development.

Data Collection↗
PubMed2003

Glutamate motivational ensembles in nucleus accumbens: rostrocaudal shell gradients of fear and feeding.

This study demonstrates that microinjection of an AMPA/kainate glutamate antagonist elicits motivated fear and feeding behaviour mapped along rostrocaudal gradients of positive-to-negative valence in nucleus accumbens shell (similar to rostrocaudal shell gradients recently reported for GABA agonist microinjections). Rats received rostral or caudal microinjections of the glutamate AMPA/kainate receptor antagonist DNQX (0, 50, 450 or 850 ng in 0.5 micro L) or the NMDA receptor antagonist MK-801 (0, 0.5, 1 or 2 micro g in 0.5 micro L), into medial accumbens shell prior to behavioural tests for fear, feeding or conditioning of place preference or avoidance. Another group received rostral or caudal microinjections of DNQX in nucleus accumbens core. Rostral shell DNQX microinjections potently increased appetitive food intake and established only weak conditioned place avoidance. Caudal shell DNQX microinjections elicited defensive treading behaviour, caused rats to defensively bite the experimenter and emit fearful distress vocalizations when handled, and established strong conditioned place avoidance. By contrast, no rostrocaudal gradients of motivational bivalence were produced by microinjections of the glutamate AMPA/kainate receptor antagonist DNQX into the core, or by microinjections of the NMDA antagonist MK-801 into the shell. Our results indicate that appetitive and aversive motivation is carried in anatomically differentiated channels by mesocorticolimbic glutamate signals to microcircuits in the medial shell. Hyperpolarization of local shell ensembles by AMPA/kainate glutamate receptor blockade elicits fear and feeding behaviours mapped along distinct positive-to-negative rostrocaudal gradients.

Animals↗
PubMedDate not supplied

Prediction of P-glycoprotein substrates by a support vector machine approach.

P-glycoproteins (P-gp) actively transport a wide variety of chemicals out of cells and function as drug efflux pumps that mediate multidrug resistance and limit the efficacy of many drugs. Methods for facilitating early elimination of potential P-gp substrates are useful for facilitating new drug discovery. A computational ensemble pharmacophore model has recently been used for the prediction of P-gp substrates with a promising accuracy of 63%. It is desirable to extend the prediction range beyond compounds covered by the known pharmacophore models. For such a purpose, a machine learning method, support vector machine (SVM), was explored for the prediction of P-gp substrates. A set of 201 chemical compounds, including 116 substrates and 85 nonsubstrates of P-gp, was used to train and test a SVM classification system. This SVM system gave a prediction accuracy of at least 81.2% for P-gp substrates based on two different evaluation methods, which is substantially improved against that obtained from the multiple-pharmacophore model. The prediction accuracy for nonsubstrates of P-gp is 79.2% using 5-fold cross-validation. These accuracies are slightly better than those obtained from other statistical classification methods, including k-nearest neighbor (k-NN), probabilistic neural networks (PNN), and C4.5 decision tree, that use the same sets of data and molecular descriptors. Our study indicates the potential of SVM in facilitating the prediction of P-gp substrates.

ATP Binding Cassette Transporter, Subfamily B, Mem↗
PubMed2001

Predicting protein--protein interactions from primary structure.

MOTIVATION: An ambitious goal of proteomics is to elucidate the structure, interactions and functions of all proteins within cells and organisms. The expectation is that this will provide a fuller appreciation of cellular processes and networks at the protein level, ultimately leading to a better understanding of disease mechanisms and suggesting new means for intervention. This paper addresses the question: can protein-protein interactions be predicted directly from primary structure and associated data? Using a diverse database of known protein interactions, a Support Vector Machine (SVM) learning system was trained to recognize and predict interactions based solely on primary structure and associated physicochemical properties. RESULTS: Inductive accuracy of the trained system, defined here as the percentage of correct protein interaction predictions for previously unseen test sets, averaged 80% for the ensemble of statistical experiments. Future proteomics studies may benefit from this research by proceeding directly from the automated identification of a cell's gene products to prediction of protein interaction pairs.

Artificial Intelligence↗
PubMed2006

Predicting deleterious nsSNPs: an analysis of sequence and structural attributes.

BACKGROUND: There has been an explosion in the number of single nucleotide polymorphisms (SNPs) within public databases. In this study we focused on non-synonymous protein coding single nucleotide polymorphisms (nsSNPs), some associated with disease and others which are thought to be neutral. We describe the distribution of both types of nsSNPs using structural and sequence based features and assess the relative value of these attributes as predictors of function using machine learning methods. We also address the common problem of balance within machine learning methods and show the effect of imbalance on nsSNP function prediction. We show that nsSNP function prediction can be significantly improved by 100% undersampling of the majority class. The learnt rules were then applied to make predictions of function on all nsSNPs within Ensembl. RESULTS: The measure of prediction success is greatly affected by the level of imbalance in the training dataset. We found the balanced dataset that included all attributes produced the best prediction. The performance as measured by the Matthews correlation coefficient (MCC) varied between 0.49 and 0.25 depending on the imbalance. As previously observed, the degree of sequence conservation at the nsSNP position is the single most useful attribute. In addition to conservation, structural predictions made using a balanced dataset can be of value. CONCLUSION: The predictions for all nsSNPs within Ensembl, based on a balanced dataset using all attributes, are available as a DAS annotation. Instructions for adding the track to Ensembl are at http://www.brightstudy.ac.uk/das_help.html.

Algorithms↗
PubMed2006

EVEREST: automatic identification and classification of protein domains in all protein sequences.

BACKGROUND: Proteins are comprised of one or several building blocks, known as domains. Such domains can be classified into families according to their evolutionary origin. Whereas sequencing technologies have advanced immensely in recent years, there are no matching computational methodologies for large-scale determination of protein domains and their boundaries. We provide and rigorously evaluate a novel set of domain families that is automatically generated from sequence data. Our domain family identification process, called EVEREST (EVolutionary Ensembles of REcurrent SegmenTs), begins by constructing a library of protein segments that emerge in an all vs. all pairwise sequence comparison. It then proceeds to cluster these segments into putative domain families. The selection of the best putative families is done using machine learning techniques. A statistical model is then created for each of the chosen families. This procedure is then iterated: the aforementioned statistical models are used to scan all protein sequences, to recreate a library of segments and to cluster them again. RESULTS: Processing the Swiss-Prot section of the UniProt Knoledgebase, release 7.2, EVEREST defines 20,230 domains, covering 85% of the amino acids of the Swiss-Prot database. EVEREST annotates 11,852 proteins (6% of the database) that are not annotated by Pfam A. In addition, in 43,086 proteins (20% of the database), EVEREST annotates a part of the protein that is not annotated by Pfam A. Performance tests show that EVEREST recovers 56% of Pfam A families and 63% of SCOP families with high accuracy, and suggests previously unknown domain families with at least 51% fidelity. EVEREST domains are often a combination of domains as defined by Pfam or SCOP and are frequently sub-domains of such domains. CONCLUSION: The EVEREST process and its output domain families provide an exhaustive and validated view of the protein domain world that is automatically generated from sequence data. The EVEREST library of domain families, accessible for browsing and download at 1, provides a complementary view to that provided by other existing libraries. Furthermore, since it is automatic, the EVEREST process is scalable and we will run it in the future on larger databases as well. The EVEREST source files are available for download from the EVEREST web site.

Cluster Analysis↗
PubMed2005

A hierarchical Bayesian model for learning nonlinear statistical regularities in nonstationary natural signals.

Capturing statistical regularities in complex, high-dimensional data is an important problem in machine learning and signal processing. Models such as principal component analysis (PCA) and independent component analysis (ICA) make few assumptions about the structure in the data and have good scaling properties, but they are limited to representing linear statistical regularities and assume that the distribution of the data is stationary. For many natural, complex signals, the latent variables often exhibit residual dependencies as well as nonstationary statistics. Here we present a hierarchical Bayesian model that is able to capture higher-order nonlinear structure and represent nonstationary data distributions. The model is a generalization of ICA in which the basis function coefficients are no longer assumed to be independent; instead, the dependencies in their magnitudes are captured by a set of density components. Each density component describes a common pattern of deviation from the marginal density of the pattern ensemble; in different combinations, they can describe nonstationary distributions. Adapting the model to image or audio data yields a nonlinear, distributed code for higher-order statistical regularities that reflect more abstract, invariant properties of the signal.

Bayes Theorem↗