Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Machine 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 1,783 records · Page 99Linked to original sources
PubMed1991

Asymmetric Boltzmann machines.

We study asymmetric stochastic networks from two points of view: combinatorial optimization and learning algorithms based on relative entropy minimization. We show that there are non trivial classes of asymmetric networks which admit a Lyapunov function L under deterministic parallel evolution and prove that the stochastic augmentation of such networks amounts to a stochastic search for global minima of L. The problem of minimizing L for a totally antisymmetric parallel network is shown to be associated to an NP-complete decision problem. The study of entropic learning for general asymmetric networks, performed in the non equilibrium, time dependent formalism, leads to a Hebbian rule based on time averages over the past history of the system. The general algorithm for asymmetric networks is tested on a feed-forward architecture.

Algorithms↗
PubMed2004

Learning Boolean queries for article quality filtering.

Prior research has shown that Support Vector Machine models have the ability to identify high quality content-specific articles in the domain of internal medicine. These models, though powerful, cannot be used in Boolean search engines nor can the content of the models be verified via human inspection. In this paper, we use decision trees combined with several feature selection methods to generate Boolean query filters for the same domain and task. The resulting trees are generated automatically and exhibit high performance. The trees are understandable, manageable, and able to be validated by humans. The subsequent Boolean queries are sensible and can be readily used as filters by Boolean search engines.

Algorithms↗
PubMed1995

Speech technology in the year 2001.

This paper introduces the session "Technology in the Year 2001" and is the first of four papers dealing with the future of human-machine communication by voice. In looking to the future it is important to recognize both the difficulties of technological forecasting and the frailties of the technology as it exists today--frailties that are manifestations of our limited scientific understanding of human cognition. The technology to realize truly advanced applications does not yet exist and cannot be supported by our presently incomplete science of speech. To achieve this long-term goal, the authors advocate a fundamental research program using a cybernetic approach substantially different from more conventional synthetic approaches. In a cybernetic approach, feedback control systems will allow a machine to adapt to a linguistically rich environment using reinforcement learning.

Computers↗
PubMed2000

The 2000 Olympic Games of protein structure prediction; fully automated programs are being evaluated vis-à-vis human teams in the protein structure prediction experiment CAFASP2.

In this commentary, we describe two new protein structure prediction experiments being run in parallel with the CASP experiment, which together may be regarded as the 2000 Olympic Games of structure prediction. The first new experiment is CAFASP, the Critical Assessment of Fully Automated Structure Prediction. In CAFASP, the participants are fully automated programs or Internet servers, and here the automated results of the programs are evaluated, without any human intervention. The second new experiment, named LiveBench, follows the CAFASP ideology in that it is aimed towards the evaluation of automatic servers only, while it runs on a large set of prediction targets and in a continuous fashion. Researchers will be watching the 2000 protein structure prediction Olympic Games, to be held in December, in order to learn about the advances in the classical 'human-plus-machine' CASP category, the fully automated CAFASP category, and the comparison between the two.

Amino Acid Sequence↗
PubMed2006

A fully automated method for lung nodule detection from postero-anterior chest radiographs.

In the past decades, a great deal of research work has been devoted to the development of systems that could improve radiologists' accuracy in detecting lung nodules. Despite the great efforts, the problem is still open. In this paper, we present a fully automated system processing digital postero-anterior (PA) chest radiographs, that starts by producing an accurate segmentation of the lung field area. The segmented lung area includes even those parts of the lungs hidden behind the heart, the spine, and the diaphragm, which are usually excluded from the methods presented in the literature. This decision is motivated by the fact that lung nodules may be found also in these areas. The segmented area is processed with a simple multiscale method that enhances the visibility of the nodules, and an extraction scheme is then applied to select potential nodules. To reduce the high number of false positives extracted, cost-sensitive support vector machines (SVMs) are trained to recognize the true nodules. Different learning experiments were performed on two different data sets, created by means of feature selection, and employing Gaussian and polynomial SVMs trained with different parameters; the results are reported and compared. With the best SVM models, we obtain about 1.5 false positives per image (fp/image) when sensitivity is approximately equal to 0.71; this number increases to about 2.5 and 4 fp/image when sensitivity is = 0.78 and = 0.85, respectively. For the highest sensitivity (= 0.92 and 1.0), we get 7 or 8 fp/image.

Algorithms↗
PubMed2003

Designing clinically useful systems: examples from medicine and dentistry.

Despite promising results in medical informatics research and the development of a large number of different systems, few systems get beyond a prototype state and are really used in practice. Among other factors, the lack of explicit user focus is one main reason. The research projects presented in this paper follow a user-centered system development approach based on extensive work analyses in interdisciplinary working groups, taking into account human cognitive performance. Different medical and health-care specialists, together with researchers in human-computer interaction and medical informatics, specify future clinical work scenarios. Special focus is put on analysis and design of the information and communication flow and on exploration of intuitive visualization and interaction techniques for clinical information. Adequate choice of the technical access device is made depending on the user's work situation. It is the purpose of this paper to apply this method in two different research projects and thereby to show its potential for designing clinically useful systems that do support and not hamper clinical work. These research projects cover IT support for chairside work in dentistry (http://www.dis.uu.se/mdi/research/projects/orquest) and ICT support for home health care of elderly citizens (http://www.medsci.uu.se/mie/project/closecare).

Aged↗
PubMed1996

Convergence Properties of High-order Boltzmann Machines.

The high-order Boltzmann machine (HOBM) approximates probability distributions defined on a set of binary variables, through a learning algorithm that uses Monte Carlo methods. The approximation distribution is a normalized exponential of a consensus function formed by high-degree terms and the structure of the HOBM is given by the set of weighted connections. We prove the convexity of the Kullback-Leibler divergence between the distribution to learn and the approximation distribution of the HOBM. We prove the convergence of the learning algorithm to the strict global minimum of the divergence, which corresponds to the maximum likelihood estimate of the connection weights, establishing the uniqueness of the solution. These theoretical results do not hold in the conventional Boltzmann machine, where the consensus function has first and second-degree terms and hidden units are used. Copyright 1996 Elsevier Science Ltd.

Journal Article↗
PubMed2002

Comprehensive proteomic analysis of the human spliceosome.

The precise excision of introns from pre-messenger RNA is performed by the spliceosome, a macromolecular machine containing five small nuclear RNAs and numerous proteins. Much has been learned about the protein components of the spliceosome from analysis of individual purified small nuclear ribonucleoproteins and salt-stable spliceosome 'core' particles. However, the complete set of proteins that constitutes intact functional spliceosomes has yet to be identified. Here we use maltose-binding protein affinity chromatography to isolate spliceosomes in highly purified and functional form. Using nanoscale microcapillary liquid chromatography tandem mass spectrometry, we identify approximately 145 distinct spliceosomal proteins, making the spliceosome the most complex cellular machine so far characterized. Our spliceosomes comprise all previously known splicing factors and 58 newly identified components. The spliceosome contains at least 30 proteins with known or putative roles in gene expression steps other than splicing. This complexity may be required not only for splicing multi-intronic metazoan pre-messenger RNAs, but also for mediating the extensive coupling between splicing and other steps in gene expression.

Amino Acid Motifs↗
PubMed2001

Causal learning mechanisms in very young children: two-, three-, and four-year-olds infer causal relations from patterns of variation and covariation.

Three studies investigated whether young children make accurate causal inferences on the basis of patterns of variation and covariation. Children were presented with a new causal relation by means of a machine called the "blicket detector." Some objects, but not others, made the machine light up and play music. In the first 2 experiments, children were told that "blickets make the machine go" and were then asked to identify which objects were "blickets." Two-, 3-, and 4-year-old children were shown various patterns of variation and covariation between two different objects and the activation of the machine. All 3 age groups took this information into account in their causal judgments about which objects were blickets. In a 3rd experiment, 3- and 4-year-old children used the information when they were asked to make the machine stop. These results are related to Bayes-net causal graphical models of causal learning.

Adult↗
PubMed1994

Kinesiological motion expert system.

Kinesiology builds on anatomical information by establishing which muscles contribute to human motion and to what extent. This 'body as machine' approach seeks to identify particular muscles as contractile 'engines'. The learning of muscular contributions to human motions based on long tables of origins, insertions, innervations, and actions is tedious and often incomplete based on author judgments of which muscles and motions to include. The kinesiological motion expert system (KMES) was developed so that students could easily select joints, actions, and tension types and receive computerized output listing the muscles that could contribute to the motion requested. In addition, a student can select a particular muscle and tension type and the program will return all of the motions that the selected muscle might contribute. The KMES was written in PDC Prolog and has a knowledge base of 1583 movements. Implementation of the KMES in kinesiology classes resulted in an increase in average student final scores of approximately 15% (F(3,190) = 12.11, P < 0.0001).

Anatomy↗
PubMed2000

Digital VLSI algorithms and architectures for support vector machines.

In this paper, we propose some very simple algorithms and architectures for a digital VLSI implementation of Support Vector Machines. We discuss the main aspects concerning the realization of the learning phase of SVMs, with special attention on the effects of fixed-point math for computing and storing the parameters of the network. Some experiments on two classification problems are described that show the efficiency of the proposed methods in reaching optimal solutions with reasonable hardware requirements.

Algorithms↗
PubMedDate not supplied

Paving the road to maximum productivity.

"Job security" is an oxymoron in today's environment of downsizing, mergers, and acquisitions. Workers find themselves living by new rules in the workplace that they may not understand. How do we cope? It is the leader's charge to take advantage of this chaos and create conditions under which his or her people can understand the need for change and come together with a shared purpose to effect that change. The clinical laboratory at Arkansas Children's Hospital has taken advantage of this chaos to down-size and to redesign how the work gets done to pave the road to maximum productivity. After initial hourly cutbacks, the workers accepted the cold, hard fact that they would never get their old world back. They set goals to proactively shape their new world through reorganizing, flexing staff with workload, creating a rapid response laboratory, exploiting information technology, and outsourcing. Today the laboratory is a lean, productive machine that accepts change as a way of life. We have learned to adapt, trust, and support each other as we have journeyed together over the rough roads. We are looking forward to paving a new fork in the road to the future.

Adaptation, Psychological↗
PubMed1989

[Changes in the EEG frequency spectrum in various phases of mental stress].

To obtain evidence about the relationship between spontaneous EEG activity and mental activity, an experiment was designed and executed with EEG recordings during a concept-learning task. We varied task performance (self-paced vs. machine-paced) and distinguished different stages of information processing during task performance. Using factor analysis calculated on all spectral coefficients, we found two orthogonal variables in the clinical alpha band. Alpha 2 power (10.5-12 Hz) seems to reflect the overall processing demands imposed on the individuals. Furthermore, there are different EEG frequency patterns during perceptual-central- compared with response-related processing as well as during processing of positive vs. negative feedback. The results suggest using (1) conservative procedures in hypothesis testing and (2) procedures to reduce between subject variability (a posteriori defined frequency variables, relative power values, scaling of reaction values) in further studies relating EEG activity to mental activity during task performance.

Adolescent↗
PubMed2004

A model for setting up interdisciplinary collaborative working in groups: lessons from an experience of action learning.

There is a current policy emphasis within health services on collaborative interdisciplinary groupworking between professionals, exemplified by the increasing use of action learning sets in a health context. Most of the evaluative research into this type of group collaboration has concentrated on evaluating outcomes, whereas this project aimed to evaluate qualitatively the experiences of the professional group members. The research uses a grounded theory methodology to investigate their perceptions and to analyse the data collected through interview methods. The research addresses an emergent theoretical model that could be of use when planning multidisciplinary task groups. It aims to enhance the success of these groups using a theory based on the concept of project momentum.

Cooperative Behavior↗
PubMed1991

An informational perspective on skill transfer in human-machine systems.

Differentiation of perceptual invariants is proposed as a theoretical approach to explain skill transfer for control at the human-machine interface. I propose that sensitivity to perceptual invariants is enhanced during learning and that this sensitivity forms the basis for transfer of skill from one task to another. The hypothesis implies that detection and discrimination of critical features, patterns, and dimension of difference are important for learning and for transfer. This account goes beyond other similarity conceptions of transfer. To the extent that those conceptions are specific, they cannot account for effects in which performance is better following training on tasks that are less rather than more similar to the criterion task. In essence, this is a theory about the central role of low-dimensional informational patterns for control of behavior within a high-dimensional environment, and about the adjustment of an actor's sensitivity to changes in those low-dimensional patterns.

Inservice Training↗
PubMed2005

Prediction of genotoxicity of chemical compounds by statistical learning methods.

Various toxicological profiles, such as genotoxic potential, need to be studied in drug discovery processes and submitted to the drug regulatory authorities for drug safety evaluation. As part of the effort for developing low cost and efficient adverse drug reaction testing tools, several statistical learning methods have been used for developing genotoxicity prediction systems with an accuracy of up to 73.8% for genotoxic (GT+) and 92.8% for nongenotoxic (GT-) agents. These systems have been developed and tested by using less than 400 known GT+ and GT- agents, which is significantly less in number and diversity than the 860 GT+ and GT- agents known at present. There is a need to examine if a similar level of accuracy can be achieved for the more diverse set of molecules and to evaluate other statistical learning methods not yet applied to genotoxicity prediction. This work is intended for testing several statistical learning methods by using 860 GT+ and GT- agents, which include support vector machines (SVM), probabilistic neural network (PNN), k-nearest neighbor (k-NN), and C4.5 decision tree (DT). A feature selection method, recursive feature elimination, is used for selecting molecular descriptors relevant to genotoxicity study. The overall accuracies of SVM, k-NN, and PNN are comparable to and those of DT lower than the results from earlier studies, with SVM giving the highest accuracies of 77.8% for GT+ and 92.7% for GT- agents. Our study suggests that statistical learning methods, particularly SVM, k-NN, and PNN, are useful for facilitating the prediction of genotoxic potential of a diverse set of molecules.

Computational Biology↗
PubMed1986

Adams' closed-loop concept of learning and motor performance: its application in behavioural kinesiology and patients' education in rehabilitation.

The earlier attempts to explain the process of learning were briefly reviewed. The limitations of these attempts led to the origin of the closed-loop concept of learning and motor performance. The analogy between the concept and a closed-loop machine model was explained in order to substantiate the relevance of this concept in human performance. The reason for the choice of Adams' concept (amongst those of others) has been identified--its uniqueness in the definition of the perceptual trace and, more importantly, the role of the knowledge of result (KR) of a performance in the learning process. A synthetic review of some literature that discussed Adams' concept has also been done. Finally, this paper has revealed that Adams' closed-loop concept is very applicable to behavioural kinesiology and patients' education in rehabilitation. It is, therefore, hypothesized that a more specific model can be developed to explain the detail of the environmental and kinematic contingencies that are inherent in this application.

Feedback↗
PubMed2005

SVM-BALSA: remote homology detection based on Bayesian sequence alignment.

Biopolymer sequence comparison to identify evolutionarily related proteins, or homologs, is one of the most common tasks in bioinformatics. Support vector machines (SVMs) represent a new approach to the problem in which statistical learning theory is employed to classify proteins into families, thus identifying homologous relationships. Current SVM approaches have been shown to outperform iterative profile methods, such as PSI-BLAST, for protein homology classification. In this study, we demonstrate that the utilization of a Bayesian alignment score, which accounts for the uncertainty of all possible alignments, in the SVM construction improves sensitivity compared to the traditional dynamic programming implementation over a benchmark dataset consisting of 54 unique protein families. The SVM-BALSA algorithms returns a higher area under the receiver operating characteristic (ROC) curves for 37 of the 54 families and achieves an improved overall performance curve at a significance level of 0.07.

Bayes Theorem↗