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 1,765 records · Page 98Linked to original sources
PubMed2004

Tools for the body (schema).

What happens in our brain when we use a tool to reach for a distant object? Recent neurophysiological, psychological and neuropsychological research suggests that this extended motor capability is followed by changes in specific neural networks that hold an updated map of body shape and posture (the putative "Body Schema" of classical neurology). These changes are compatible with the notion of the inclusion of tools in the "Body Schema", as if our own effector (e.g. the hand) were elongated to the tip of the tool. In this review we present empirical support for this intriguing idea from both single-neuron recordings in the monkey brain and behavioural performance of normal and brain-damaged humans. These relatively simple neural and behavioural aspects of tool-use shed light on more complex evolutionary and cognitive aspects of body representation and multisensory space coding for action.

Animals↗
PubMed2000

Knowledge-based analysis of microarray gene expression data by using support vector machines.

We introduce a method of functionally classifying genes by using gene expression data from DNA microarray hybridization experiments. The method is based on the theory of support vector machines (SVMs). SVMs are considered a supervised computer learning method because they exploit prior knowledge of gene function to identify unknown genes of similar function from expression data. SVMs avoid several problems associated with unsupervised clustering methods, such as hierarchical clustering and self-organizing maps. SVMs have many mathematical features that make them attractive for gene expression analysis, including their flexibility in choosing a similarity function, sparseness of solution when dealing with large data sets, the ability to handle large feature spaces, and the ability to identify outliers. We test several SVMs that use different similarity metrics, as well as some other supervised learning methods, and find that the SVMs best identify sets of genes with a common function using expression data. Finally, we use SVMs to predict functional roles for uncharacterized yeast ORFs based on their expression data.

Algorithms↗
PubMed1994

A storage algorithm for two-layered neural networks.

A learning algorithm for the two-layered committee machine is proposed. The proof of its convergence in a finite time is given. Its efficiency is compared to the simple exhaustive enumeration of the internal representations of the training set.

Algorithms↗
PubMed1989

Ergonomics in ultrasound equipment: productivity and patient throughput.

The important issues to consider when purchasing ultrasound equipment are: image quality, speed of interface, controls that are obvious, quick or slow configuring, a narrow or wide triangle of interest, fast or slow function shift capability, the amount of layering, color that is muted or not muted, whether the controls are back lit, easily managed cables and probes, and whether the machine is pleasant to operate and easy to learn. All these factors will provide you with some idea of a system's productivity and assist the buyer in making a purchasing decision. Consider these points as a checklist when shopping for an ultrasound system, especially when the radiology manager is concerned about throughput and the bottom line as well as diagnostic information quality.

Decision Making↗
PubMed1986

Office glucose analysis.

The advent of dry chemistry techniques has made inexpensive glucose testing equipment available to physicians and their patients. The ability to measure blood glucose concentration quickly, in almost any setting, has eliminated urinary glucose monitoring as the parameter of choice for managing diabetic patients. Blood glucose monitoring has allowed improved control of diabetic patients who avail themselves of one of the techniques. The physician choosing to offer blood glucose testing in the office laboratory has a variety of test equipment from which to choose. Most physicians will want to own and operate an inexpensive, dedicated glucose reflectometer to test glucose samples in the office and to use in patient education. Machines used by both patients and physicians are about the same price. They are easy to learn to use. Office personnel must be trained to perform the procedure, teach it to patients, maintain the machine, and keep adequate quality control records.

Blood Glucose↗
PubMed1975

The use of an interactive computer terminal in the assessment of cognitive function in elderly psychiatric patients.

The use of a teaching machine is the assessment of mental function has been described by Gredye and his colleagues. This report concerns its use in testing 56 elderly patients suffering from functional psychiatric disorders of dementia. After a diagnostic interview patients were tested on the teaching machine as well as on the Mill Hill, Progressive Matrices, Paired Associate Learning Test and Digit Copying Test. After a fixed period all tests were repeated and clincal progress rated. Results showed a significant correlation (P less than 0.01) between teaching-machine scores and those on the standard psychological tests. The correlation between the machine scores on the two occasions was high (r equals 0.58) but this was complicated by practice effects and by low 'ceiling' of the test. It is concluded that the test provided a relatively reliable and valid measure of cognitive function but that its value would be increased by providing a parallel form and by extending its level of difficulty.

Age Factors↗
PubMed2004

A similarity learning approach to content-based image retrieval: application to digital mammography.

In this paper, we describe an approach to content-based retrieval of medical images from a database, and provide a preliminary demonstration of our approach as applied to retrieval of digital mammograms. Content-based image retrieval (CBIR) refers to the retrieval of images from a database using information derived from the images themselves, rather than solely from accompanying text indices. In the medical-imaging context, the ultimate aim of CBIR is to provide radiologists with a diagnostic aid in the form of a display of relevant past cases, along with proven pathology and other suitable information. CBIR may also be useful as a training tool for medical students and residents. The goal of information retrieval is to recall from a database information that is relevant to the user's query. The most challenging aspect of CBIR is the definition of relevance (similarity), which is used to guide the retrieval machine. In this paper, we pursue a new approach, in which similarity is learned from training examples provided by human observers. Specifically, we explore the use of neural networks and support vector machines to predict the user's notion of similarity. Within this framework we propose using a hierarchal learning approach, which consists of a cascade of a binary classifier and a regression module to optimize retrieval effectiveness and efficiency. We also explore how to incorporate online human interaction to achieve relevance feedback in this learning framework. Our experiments are based on a database consisting of 76 mammograms, all of which contain clustered microcalcifications (MCs). Our goal is to retrieve mammogram images containing similar MC clusters to that in a query. The performance of the retrieval system is evaluated using precision-recall curves computed using a cross-validation procedure. Our experimental results demonstrate that: 1) the learning framework can accurately predict the perceptual similarity reported by human observers, thereby serving as a basis for CBIR; 2) the learning-based framework can significantly outperform a simple distance-based similarity metric; 3) the use of the hierarchical two-stage network can improve retrieval performance; and 4) relevance feedback can be effectively incorporated into this learning framework to achieve improvement in retrieval precision based on online interaction with users; and 5) the retrieved images by the network can have predicting value for the disease condition of the query.

Algorithms↗
PubMed2004

Outcome of second surgery in LASIK cases aborted due to flap complications.

PURPOSE: To describe the technique and timing of second refractive surgery after aborted laser in situ keratomileusis (LASIK) due to intraoperative flap complication and determine the final visual outcome. SETTING: Outpatient ambulatory laser vision correction centers. METHODS: This retrospective noncomparative case series included 16 patients (16 eyes) who had a second refractive surgery after initial LASIK surgery was aborted because of a flap complication. Charts were reviewed with attention to initial preoperative data, intraoperative details of the aborted LASIK, postoperative examination, possible causes of the flap complication, timing and technique of second refractive surgery, and final visual outcome. RESULTS: Causes of the aborted LASIK were identified in 13 of 16 eyes (81.2%) and included eye squeezing (5 eyes), loss of suction or machine failure (5 eyes), steep corneas (2 eyes), and learning curve of the surgeon (1 eye). The mean time until the second surgery was 135 days (range 49 to 372 days). Repeat flaps were created deeper and larger than the initially attempted flaps when possible. No patient had a final uncorrected visual acuity (UCVA) worse than 20/30 after the second surgery. Two eyes (12.5%) lost 1 line of best spectacle-corrected visual acuity. CONCLUSION: A planned delayed reoperation after sufficient corneal healing following an intraoperative flap complication can result in satisfactory recovery of UCVA.

Adult↗
PubMed2005

Foley-Sammon optimal discriminant vectors using kernel approach.

A new nonlinear feature extraction method called kernel Foley-Sammon optimal discriminant vectors (KFSODVs) is presented in this paper. This new method extends the well-known Foley-Sammon optimal discriminant vectors (FSODVs) from linear domain to a nonlinear domain via the kernel trick that has been used in support vector machine (SVM) and other commonly used kernel-based learning algorithms. The proposed method also provides an effective technique to solve the so-called small sample size (SSS) problem which exists in many classification problems such as face recognition. We give the derivation of KFSODV and conduct experiments on both simulated and real data sets to confirm that the KFSODV method is superior to the previous commonly used kernel-based learning algorithms in terms of the performance of discrimination.

Algorithms↗
PubMed2003

Analyzing microarray data using cluster analysis.

As pharmacogenetics researchers gather more detailed and complex data on gene polymorphisms that effect drug metabolizing enzymes, drug target receptors and drug transporters, they will need access to advanced statistical tools to mine that data. These tools include approaches from classical biostatistics, such as logistic regression or linear discriminant analysis, and supervised learning methods from computer science, such as support vector machines and artificial neural networks. In this review, we present an overview of another class of models, cluster analysis, which will likely be less familiar to pharmacogenetics researchers. Cluster analysis is used to analyze data that is not a priori known to contain any specific subgroups. The goal is to use the data itself to identify meaningful or informative subgroups. Specifically, we will focus on demonstrating the use of distance-based methods of hierarchical clustering to analyze gene expression data.

Cluster Analysis↗
PubMed2004

Peptide binding at class I major histocompatibility complex scored with linear functions and support vector machines.

We explore two different methods to predict the binding ability of nonapeptides at the class I major histocompatibility complex using a general linear scoring function that defines a separating hyperplane in the feature space of sequences. In absence of suitable data on non-binding nonapeptides we generated sequences randomly from a selected set of proteins from the protein data bank. The parameters of the scoring function were determined by a generalized least square optimization (LSM) and alternatively by the support vector machine (SVM). With the generalized LSM impaired data for learning with a small set of binding peptides and a large set of non-binding peptides can be treated in a balanced way rendering LSM more successful than SVM, while for symmetric data sets SVM has a slight advantage compared to LSM.

Amino Acid Sequence↗
PubMed2000

Stable encoding of finite-state machines in discrete-time recurrent neural nets with sigmoid units.

There has been a lot of interest in the use of discrete-time recurrent neural nets (DTRNN) to learn finite-state tasks, with interesting results regarding the induction of simple finite-state machines from input-output strings. Parallel work has studied the computational power of DTRNN in connection with finite-state computation. This article describes a simple strategy to devise stable encodings of finite-state machines in computationally capable discrete-time recurrent neural architectures with sigmoid units and gives a detailed presentation on how this strategy may be applied to encode a general class of finite-state machines in a variety of commonly used first- and second-order recurrent neural networks. Unlike previous work that either imposed some restrictions to state values or used a detailed analysis based on fixed-point attractors, our approach applies to any positive, bounded, strictly growing, continuous activation function and uses simple bounding criteria based on a study of the conditions under which a proposed encoding scheme guarantees that the DTRNN is actually behaving as a finite-state machine.

Models, Neurological↗
PubMed2006

Modular learning models in forecasting natural phenomena.

Modular model is a particular type of committee machine and is comprised of a set of specialized (local) models each of which is responsible for a particular region of the input space, and may be trained on a subset of training set. Many algorithms for allocating such regions to local models typically do this in automatic fashion. In forecasting natural processes, however, domain experts want to bring in more knowledge into such allocation, and to have certain control over the choice of models. This paper presents a number of approaches to building modular models based on various types of splits of training set and combining the models' outputs (hard splits, statistically and deterministically driven soft combinations of models, 'fuzzy committees', etc.). An issue of including a domain expert into the modeling process is also discussed, and new algorithms in the class of model trees (piece-wise linear modular regression models) are presented. Comparison of the algorithms based on modular local modeling to the more traditional 'global' learning models on a number of benchmark tests and river flow forecasting problems shows their higher accuracy and transparency of the resulting models.

Artificial Intelligence↗
PubMed1980

Human operator dynamics in manual tracking systems with auditory input.

Response characteristics of human operators in manual pursuit tracking with auditory input are investigated. The human operator hears in his left ear a sound whose frequency varies in proportion to an external random signal. At the same time, he hears in his right ear another sound whose frequency varies in proportion to the angle of a control lever of a potentiometer. The operator controls the angle of the lever so that the frequencies, of the sounds in both ears remain as close as possible. The dynamics of the human operator is studied by assuming a "man-machine system" whose input is the external signal and whose output is the voltage of the potentiometer. A learning identification method proposed by one of the authors is used to calculate the weighting function of the man-machine system, which is displayed on a CRT screen in renal time. During the tracking task, the skin potential activity (SPA) is measured as an index of arousal of the operator.

Arousal↗
PubMedDate not supplied

Role of the cerebellum in the visual guidance of movement.

Mathematicians, control engineers and information technologists are beginning to take a greater interest in neuroscience. They are perhaps starting to realize that they may be able to learn a few tricks from nature with which to improve their machines. At the same time there is a good chance that neuroscientists will benefit from their input of fresh ideas and techniques with which to attack the problems of understanding neural processing. One area of the brain which seems particularly promising in these respects is the cerebellum.

Brain Mapping↗
PubMed2000

The effects of task complexity and experience on learning and forgetting: a field study.

This paper examines the effects of task complexity and experience on parameters of individual learning and forgetting. Three attributes of task complexity and experience are addressed: the method, machine, and material employed. The task involved a high-manual-dexterity skill taken from an operating textile assembly plant; there were 2853 individual participant learning/forgetting episodes. A parametric model of individual learning and forgetting that allows the evaluation of worker response to the attributes of task complexity and experience is discussed. Results indicate that both task complexity and experience significantly affect learning and forgetting rates. Potential applications of this research include the allocation of workers to tasks based on individual learning/forgetting characteristics.

Analysis of Variance↗