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 217 records · Page 12Linked to original sources
PubMed2000

Overcoming selective ensemble averaging: unsupervised identification of event-related brain potentials.

We present a novel approach to the problem of event-related potential (ERP) identification, based on a competitive artificial neural network (ANN) structure. Our method uses ensembled electroencephalogram (EEG) data just as used in conventional averaging, however without the need for a priori data subgrouping into distinct categories (e.g., stimulus- or event-related), and thus avoids conventional assumptions on response invariability. The competitive ANN, often described as a winner takes all neural structure, is based on dynamic competition among the net neurons where learning takes place only with the winning neuron. Using a simple single-layered structure, the proposed scheme results in convergence of the actual neural weights to the embedded ERP patterns. The method is applied to real event-related potential data recorded during a common odd-ball type paradigm. For the first time, within-session variable signal patterns are automatically identified, dismissing the strong and limiting requirement of a priori stimulus-related selective grouping of the recorded data. The results present new possibilities in ERP research.

Artifacts↗
PubMed2026

CCNA2 orchestrates the PI3K/AKT signaling axis to propel prostate cancer metastasis.

BACKGROUND: Prostate cancer (PCa) remains one of the most common malignancies in men, posing a persistent global burden in terms of both public health and socioeconomic costs. Although early detection is essential for improving patient outcomes, existing clinical tools, including prostate-specific antigen (PSA) screening, digital rectal examination, and transrectal ultrasound-guided biopsy, are hampered by suboptimal specificity and positive predictive value, resulting in frequent overdiagnosis and overtreatment of indolent lesions while missing a subset of aggressive tumors at an early stage. In this context, the rapid advancement of high-throughput omics technologies, coupled with sophisticated machine learning (ML) algorithms, provides a powerful computational framework to dissect high-dimensional genomic data, uncover latent gene expression signatures, and identify candidate biomarkers with superior discriminative performance over conventional clinicopathological parameters. Therefore, in this study, we sought to screen for crucial ML-based biomarkers associated with PCa, with a particular focus on systematically assessing the diagnostic and prognostic value of CCNA2. Leveraging large-scale transcriptomic cohorts from public repositories, we employed an ensemble of ML approaches to prioritize candidate genes and subsequently evaluated the diagnostic performance of CCNA2 through receiver operating characteristic curve analysis, as well as its prognostic utility via Kaplan-Meier survival estimation and multivariate Cox proportional hazards modeling. Our findings are anticipated to elucidate the molecular landscape of PCa and offer a promising biomarker candidate for early detection and risk stratification. METHODS: This study integrated single-cell RNA sequencing, bulk transcriptomic data from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) repositories, immunofluorescence, and multiple ML algorithms with in vitro functional assays to evaluate CCNA2 expression, clinical relevance, and biological behavior in PCa. RESULTS: CCNA2 was linked to metastasis and poor prognosis. High CCNA2 expression significantly correlated with adverse survival outcomes, and knockdown of CCNA2 suppressed proliferation, migration, and invasion in PCa cell lines. Mechanistically, CCNA2 modulated the PI3K/AKT signaling pathway. An ML-based diagnostic model incorporating CCNA2 demonstrated high predictive accuracy across multiple validation cohorts. CONCLUSIONS: CCNA2 serves as a promising prognostic biomarker and therapeutic target in prostate adenocarcinoma, driving tumor progression potentially via the PI3K/AKT axis.

CCNA2↗
PubMed1999

Hippocampal place cells can develop distinct representations of two visually identical environments.

The pattern separation ability of hippocampal place cells was tested in an environment in which two visually identical rectangular compartments (Box A and Box B) were connected by a hidden door. Small ensembles of neurons were recorded with tetrodes while the rat searched for randomly distributed loci for reinforcing brain stimulation. The first recording session in Box A was conducted after the rat had explored the environment for the first time for 30 min. Immediately thereafter, a hidden door between Box A and Box B was opened to let the rat into the unexplored compartment, and a 5-min recording session was run with the door concealed. A rearrangement of place fields in Box B was observed in 18/20 neurons and in 5/6 ensembles. Most place fields did not change between two successive sessions in Box B. When the rat returned to Box A, the ensembles of neurons were as likely to adopt the original Box A firing field pattern as the more recent Box B pattern. In order to control for the influence of extra-arena cues, the rat was gradually lifted in a closed bucket from Box A into Box B while the whole arena was rotated by 90 degrees. All but one neuron and all the ensembles followed the intra-arena cues. Both rotated Box B and Box A firing field patterns were represented but Box B pattern was stronger among the neuronal ensembles. These findings indicate that hippocampal place cells not only can develop distinct representations of two visually identical environments but also can selectively reactivate either one of these representations depending on the rat's recent experience.

Animals↗
PubMed1995

Pruning of rat cortical taste neurons by an artificial neural network model.

1. Taste qualities are believed to be coded in the activity of ensembles of taste neurons. However, it is not clear whether all neurons are equally responsible for coding. To clarify the point, the relative contribution of each taste neuron to coding needs to be assessed. 2. We constructed simple three-layer neural networks with input units representing cortical taste neurons of the rat. The networks were trained by the back-propagation learning algorithm to classify the neural response patterns to the basic taste stimuli (sucrose, HCl, quinine hydrochloride, and NaCl). The networks had four output units representing the basic taste qualities, the values of which provide a measure for similarity of test stimuli (salts, tartaric acid, and umami substances) to the basic taste stimuli. 3. Trained networks discriminated the response patterns to the test stimuli in a plausible manner in light of previous physiological and psychological experiments. Profiles of output values of the networks paralleled those of across-neuron correlations with respect to the highest or second-highest values in the profiles. 4. We evaluated relative contributions of input units to the taste discrimination of the network by examining their significance Sj, which is defined as the sum of the absolute values of the connection weights from the jth input unit to the hidden layer. When the input units with weaker connection weights (e.g., 15 of 39 input units) were "pruned" from the trained network, the ability of the network to discriminate the basic taste qualities as well as other test stimuli was not greatly affected. On the other hand, the taste discrimination of the network progressively deteriorated much more rapidly with pruning of input units with stronger connection weights. 5. These results suggest that cortical taste neurons differentially contribute to the coding of taste qualities. The pruning technique may enable the evaluation of a given taste neuron in terms of its relative contribution to the coding, with Sj providing a quantitative measure for such evaluation.

Animals↗
PubMed2006

The experimental survey of protein-folding energy landscapes.

We review what has been learned about the protein-folding problem from experimental kinetic studies. These studies reveal patterns of both great richness and surprising simplicity. The patterns can be interpreted in terms of proteins possessing an energy landscape which is largely, but not completely, funnel-like. Issues such as speed limitations of folding, the robustness of folding, the origin of barriers and cooperativity and the ensemble nature of transition states, intermediate and traps are assessed using the results from several experimental groups highlighting energy-landscape ideas as an interpretive framework.

Energy Transfer↗
PubMed2004

Learning and production of movement sequences: behavioral, neurophysiological, and modeling perspectives.

A wave of recent behavioral studies has generated a new wealth of parametric observations about serial order behavior. What was a trickle of neurophysiological studies has grown to a steady stream of probes of neural sites and mechanisms underlying sequential behavior. Moreover, simulation models of serial behavior generation have begun to open a channel to link cellular dynamics with cognitive and behavioral dynamics. Here we review major results from prominent sequence learning and performance tasks, namely immediate serial recall, typing, 2 x N, discrete sequence production, and serial reaction time. These tasks populate a continuum from higher to lower degrees of internal control of sequential organization and probe important contemporary issues such as the nature of working-memory representations for sequential behavior, and the development and role of chunks in hierarchical control. The main movement classes reviewed are speech and keypressing, both involving small amplitude movements amenable to parametric study. A synopsis of serial order models, vis-a-vis major empirical findings leads to a focus on competitive queuing (CQ) models. Recently, the many behavioral predictive successes of CQ models have been complemented by successful prediction of distinctively patterned electrophysiological recordings. In lateral prefrontal cortex, parallel activation dynamics of multiple neural ensembles strikingly matches the parallel dynamics predicted by CQ theory. An extended CQ simulation model--the N-STREAMS neural network model--exemplifies ongoing attempts to accommodate a broad range of both behavioral and neurobiological data within a CQ-consistent theory.

Animals↗
PubMed2002

An ultra-sparse code underlies the generation of neural sequences in a songbird.

Sequences of motor activity are encoded in many vertebrate brains by complex spatio-temporal patterns of neural activity; however, the neural circuit mechanisms underlying the generation of these pre-motor patterns are poorly understood. In songbirds, one prominent site of pre-motor activity is the forebrain robust nucleus of the archistriatum (RA), which generates stereotyped sequences of spike bursts during song and recapitulates these sequences during sleep. We show that the stereotyped sequences in RA are driven from nucleus HVC (high vocal centre), the principal pre-motor input to RA. Recordings of identified HVC neurons in sleeping and singing birds show that individual HVC neurons projecting onto RA neurons produce bursts sparsely, at a single, precise time during the RA sequence. These HVC neurons burst sequentially with respect to one another. We suggest that at each time in the RA sequence, the ensemble of active RA neurons is driven by a subpopulation of RA-projecting HVC neurons that is active only at that time. As a population, these HVC neurons may form an explicit representation of time in the sequence. Such a sparse representation, a temporal analogue of the 'grandmother cell' concept for object recognition, eliminates the problem of temporal interference during sequence generation and learning attributed to more distributed representations.

Action Potentials↗
PubMed1992

Self-organization of day cycle and hierarchical associative memory in "live" neural network.

The "live" neural network model is proposed on the basis of "live" neuron model and optimal learning rule. By means of numerical simulation the initial stages of neural network self-organization have been shown: (1) the formation of two activity forms, which are identified with sleep and awaking, and (2) the self-organization of hierarchical associative memory when feeding a receptor excitation to the neural network. The energetic profit of self-organization is demonstrated. The formation of neural ensembles, playing the role of generalized neurons, is obtained.

Biological Clocks↗
PubMed2001

Neuronal responses in the frontal cortico-basal ganglia system during delayed matching-to-sample task: ensemble recording in freely moving rats.

Electrophysiological recording of single neuron activity has been conducted in rats to investigate the patterns of distributed neuronal responses in the frontal cortico-basal ganglia system that code information during a spatial-delayed matching-to-sample task (DMTSt). Rats were trained to press one of the two retractable levers presented randomly as a sample response. The first valid nose-poke after a delay resulted in the presentation of both levers. Pressing the same lever as the sample lever led to a water reward (match to sample), whereas pressing the lever opposite the sample lever resulted in a time-out (house light turned off). One hundred seventy-one neurons in the medial prefrontal cortex (mPFC), 51 in the dorsal striatum (STR), and 93 in the nucleus accumbens (NAc) were recorded during DMTSt. Different patterns of neuronal responses were observed during different behavioral episodes (sample, delay, and match phases) in all three recording areas. Space-related neuronal responses specific to the side of the lever pressed were more often found in the sample phase than in the match phase in all three areas studied. Neuronal responses specific to either correct or error trials were observed with similar percentages in the mPFC and the NAc, while the incidence of correct/error-coded activity in the STR was lower. Ensemble neuronal activity that coded sample versus match lever presses was observed in three out of five rats in sets of trials with similar speed and trajectory of lever press. The results reveal specific patterns of neural responses in the frontal cortico-basal ganglia system in rats during the DMTSt and suggest the existence of specific neuronal coding for different behavioral events associated with a learned short-term memory process.

Action Potentials↗
PubMed2002

Biological information: making it accessible and integrated (and trying to make sense of it).

The availability of the genome sequences of human and mouse, human sequence variation data and other large genetic data sets will lead to a revolution in understanding of the human machine and the treatment of its diseases. The success of the international genome sequencing consortiums shows what can be achieved by well coordinated large scale public domain projects and the benefits of data access to all. It is already clear that the availability of this sequence is having a huge impact on research worldwide. Complete genome sequences provide a framework to pull all biological data together such that each piece has the potential to say something about biology as a whole. Biology is too complex for any organisation to have a monopoly of ideas or data, so the collection, analysis and access to this data can be contributed to by research institutes around the world. However, although it is possible for all this data to be accessible to all through the internet, the more organisations provide data or analysis separately, the harder it becomes for anyone to collect and integrate the results. To address these problems of intergration of data, open standards for biological data exchange, such as the 'Distributed Annotation System' (DAS) are being developed and bioinformatics (Dowell et al., 2001) as a whole is now being strongly driven by the open source software (OSS) model for collaborative software development (Hubbard and Birney, 1999). The leading provider of human genome annotation, the Ensembl project (http://www.ensembl.org), is entirely an OSS project and has been widely adopted by academic and commerical organisations alike (Hubbard et al., 2002). Accurate automatic annotation of features such as genes in vertebrate genomes currently relies on supporting evidence in the form of homologies to mRNAs, ESTs or protein. However, it appears that sufficient high quality experimentally curated annotation now exists to be used as a substrate for machine learning algorithms to create effective models of biological signal sequences (Down and Hubbard, 2002). Is there hope for ab initio prediction methods after all?

Chromosome Mapping↗
PubMed2004

Chicken genomics charts a path to the genome sequence.

In this paper, the current status of chicken genomics is reviewed. This is timely given the current intense activity centred on sequencing the complete genome of this model species. The genome project is based on a decade of map building by genetic linkage and cytogenetic methods, which are now being replaced by high-resolution radiation hybrid and bacterial artificial chromosome (BAC) contig maps. Markers for map building have generally depended on labour-intensive screening procedures, but in recent years this has changed with the availability of almost 500,000 chicken expressed sequence tags (ESTs). These resources and tools will be critical in the coming months when the chicken genome sequence is being assembled (eg cross-checked with other maps) and annotated (eg gene structures based on ESTs). The future for chicken genome and biological research is an exciting one, through the integration of these resources. For example, through the proposed chicken Ensembl database, it will be possible to solve challenging scientific questions by exploiting the power of a chicken model. One area of interest is the study of developmental mechanisms and the discovery of regulatory networks throughout the genome. Another is the study of the molecular nature of quantitative genetic variation. No other animal species have been phenotyped and selected so intensively as agricultural animals and thus there is much to be learned in basic and medical biology from this research.

Animals↗
PubMed2004

Effect of field experiences on music therapy students' perceptions of choral music for geriatric wellness programs.

The purpose of the study was to examine the effect of field experiences on music therapy students' perceptions of choral music for geriatric wellness programs. Specifically, the study investigated music therapy students': a) personal comfort working with senior adult singers; b) perceptions of preparation in their educational training to work with senior adults in a choral music wellness program; c) perceptions of senior adults' functioning levels as singers in choral ensembles; d) perceptions of senior adults' functioning levels as learners; and e) willingness to seek additional opportunities to lead senior adults in choral music wellness programs. Comparative analysis using pretest and posttest scores for each grouping was completed. Significant mean score differences were found in the categories of student comfort, preparation, perceptions of singing, and willingness, with gains from pre- to posttest in all categories. The general demographics and perceptions of learning groupings increased and decreased, respectively, though not significantly, following the field experience. Analysis combining all groups, creating an overall pretest and posttest score, was also completed. Results revealed that students felt significantly more positive about choral music being used in wellness programs for senior adults after the field experience.

Adult↗
PubMed2006

Temporal encoding of place sequences by hippocampal cell assemblies.

Both episodic memory and spatial navigation require temporal encoding of the relationships between events or locations. In a linear maze, ordered spatial distances between sequential locations were represented by the temporal relations of hippocampal place cell pairs within cycles of theta oscillation in a compressed manner. Such correlations could arise due to spike "phase precession" of independent neurons driven by common theta pacemaker or as a result of temporal coordination among specific hippocampal cell assemblies. We found that temporal correlation between place cell pairs was stronger than predicted by a pacemaker drive of independent neurons, indicating a critical role for synaptic interactions and precise timing within and across cell assemblies in place sequence representation. CA1 and CA3 ensembles, identifying spatial locations, were active preferentially on opposite phases of theta cycles. These observations suggest that interleaving CA3 neuronal sequences bind CA1 assemblies representing overlapping past, present, and future locations into single episodes.

Action Potentials↗
PubMed2002

Reliability of lower extremity strength measures in persons with chronic stroke.

OBJECTIVE: To determine the reliability of isokinetic concentric strength measures of both the hemiparetic and noninvolved limbs for flexion and extension motions of the hip, knee, and ankle joints in individuals who have had a stroke. DESIGN: Test-retest, repeated-measures intraobserver reliability design. SETTING: Tertiary rehabilitation center. PARTICIPANTS: Twenty community-dwelling individuals who have had a stroke, with motor deficits ranging from 3 to 6 on the Chedoke-McMaster Stroke Assessment; volunteer sample. INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURES: Peak torque and average torque (ie, mean over the range of motion tested) from an ensemble-averaged (3 trials) torque-angle curve during isokinetic concentric extension and flexion movements of the ankle, knee, and hip. RESULTS: Although peak and average torque were significantly less for the hemiparetic limb compared with the noninvolved limb, the intraclass correlation coefficients (ICCs) between the 2 test sessions were high (.95-.99 for peak torque,.88-.98 for average torque) for both limbs for all 3 joints. However, there was a learning effect, as observed by the slightly greater values attained from the second test session. CONCLUSIONS: Peak and average isokinetic torque can be used to assess reliably lower extremity strength in persons with chronic stroke. Practice sessions may be required before the actual test to reduce the effect of learning.

Aged↗
PubMed2006

Complexation between a macromolecule and an amphiphile by Monte Carlo technique.

Using a simple modified version of Larson's model, we studied the complexation between a macromolecule and an amphiphile in a dilute range of concentrations. The main characteristic of amphiphile molecules, that is, the hydrophobicity of the tails and hydrophilicity of the heads, is used to model the self-assembling process. Contrary to the molecular thermodynamics approaches, no prior shape was considered for the aggregates and the system was allowed to choose the most stable structure. For true ensemble averaging, without any synthetic results, configurational bias Monte Carlo and reptation moves are used to produce a Markov chain of configurations. From the results, it is found that the macromolecule causes the clusters of surfactants to be formed at a concentration much lower than the critical micelle concentration. Furthermore, the shape of the clusters tends to be more spherical, which is in line with theory and experiments. From the results, it is learned how a polymer can change the behavior of an amphiphilic molecule. All of the results are in good qualitative agreement with experimental and molecular thermodynamics results. Furthermore, the model predicts network formation between bound clusters at high concentrations of the surfactant.

Journal Article↗
PubMed2006

Soft mixer assignment in a hierarchical generative model of natural scene statistics.

Gaussian scale mixture models offer a top-down description of signal generation that captures key bottom-up statistical characteristics of filter responses to images. However, the pattern of dependence among the filters for this class of models is prespecified. We propose a novel extension to the gaussian scale mixture model that learns the pattern of dependence from observed inputs and thereby induces a hierarchical representation of these inputs. Specifically, we propose that inputs are generated by gaussian variables (modeling local filter structure), multiplied by a mixer variable that is assigned probabilistically to each input from a set of possible mixers. We demonstrate inference of both components of the generative model, for synthesized data and for different classes of natural images, such as a generic ensemble and faces. For natural images, the mixer variable assignments show invariances resembling those of complex cells in visual cortex; the statistics of the gaussian components of the model are in accord with the outputs of divisive normalization models. We also show how our model helps interrelate a wide range of models of image statistics and cortical processing.

Animals↗
PubMed2006

Trainable fusion rules. I. Large sample size case.

A wide selection of standard statistical pattern classification algorithms can be applied as trainable fusion rules while designing neural network ensembles. A focus of the present two-part paper is finite sample effects: the complexity of base classifiers and fusion rules; the type of outputs provided by experts to the fusion rule; non-linearity of the fusion rule; degradation of experts and the fusion rule due to the lack of information in the design set; the adaptation of base classifiers to training set size, etc. In the first part of this paper, we consider arguments for utilizing continuous outputs of base classifiers versus categorical outputs and conclude: if one succeeds in having a small number of expert networks working perfectly in different parts of the input feature space, then crisp outputs may be preferable over continuous outputs. Afterwards, we oppose fixed fusion rules versus trainable ones and demonstrate situations where weighted average fusion can outperform simple average fusion. We present a review of statistical classification rules, paying special attention to these linear and non-linear rules, which are employed rarely but, according to our opinion, could be useful in neural network ensembles. We consider ideal and sample-based oracle decision rules and illustrate characteristic features of diverse fusion rules by considering an artificial two-dimensional (2D) example where the base classifiers perform well in different regions of input feature space.

Animals↗
PubMed2000

The paradigms of causality and treatment for autoimmune disease.

A key concept in medicine is that rational therapy rests on accurate diagnosis; quite simply, therapy that is not tuned to the cause of the disease will not cure the patient. This does not mean that effective treatments cannot emerge from faulty diagnoses. In truth, much of our therapeutic ensemble is composed of drugs developed as a result of chance observation, random screening, intuition or prescientific tradition. Nevertheless, the way to effective therapy is best paved by understanding. Effects are inherent in their causes, so if we want to cure autoimmune diseases using the scientific method, we are obliged to inquire into their causes. By reducing the discordant complexity of the disease to the single cause that underlies it, we can hope to learn the most efficient way to manipulate the disease process. How do we identify a cause when we see one? Quite simply, a single cause is that which is both necessary and sufficient to produce the effect. Here, I explore the general paradigm of autoimmune causality, using multiple sclerosis as a specific example.

Autoimmune Diseases↗