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 1,639 records · Page 91Linked to original sources
PubMed2003

Learning to control a brain-machine interface for reaching and grasping by primates.

Reaching and grasping in primates depend on the coordination of neural activity in large frontoparietal ensembles. Here we demonstrate that primates can learn to reach and grasp virtual objects by controlling a robot arm through a closed-loop brain-machine interface (BMIc) that uses multiple mathematical models to extract several motor parameters (i.e., hand position, velocity, gripping force, and the EMGs of multiple arm muscles) from the electrical activity of frontoparietal neuronal ensembles. As single neurons typically contribute to the encoding of several motor parameters, we observed that high BMIc accuracy required recording from large neuronal ensembles. Continuous BMIc operation by monkeys led to significant improvements in both model predictions and behavioral performance. Using visual feedback, monkeys succeeded in producing robot reach-and-grasp movements even when their arms did not move. Learning to operate the BMIc was paralleled by functional reorganization in multiple cortical areas, suggesting that the dynamic properties of the BMIc were incorporated into motor and sensory cortical representations.

Animals↗
PubMed2004

Classification of incidental carcinoma of the prostate using learning vector quantization and support vector machines.

The subclassification of incidental prostatic carcinoma into the categories T1a and T1b is of major prognostic and therapeutic relevance. In this paper an attempt was made to find out which properties mainly predispose to these two tumor categories, and whether it is possible to predict the category from a battery of clinical and histopathological variables using newer methods of multivariate data analysis. The incidental prostatic carcinomas of the decade 1990-99 diagnosed at our department were reexamined. Besides acquisition of routine clinical and pathological data, the tumours were scored by immunohistochemistry for proliferative activity and p53-overexpression. Tumour vascularization (angiogenesis) and epithelial texture were investigated by quantitative stereology. Learning vector quantization (LVQ) and support vector machines (SVM) were used for the purpose of prediction of tumour category from a set of 10 input variables (age, Gleason score, preoperative PSA value, immunohistochemical scores for proliferation and p53-overexpression, 3 stereological parameters of angiogenesis, 2 stereological parameters of epithelial texture). In a stepwise logistic regression analysis with the tumour categories T1a and T1b as dependent variables, only the Gleason score and the volume fraction of epithelial cells proved to be significant as independent predictor variables of the tumour category. Using LVQ and SVM with the information from all 10 input variables, more than 80 of the cases could be correctly predicted as T1a or T1b category with specificity, sensitivity, negative and positive predictive value from 74-92%. Using only the two significant input variables Gleason score and epithelial volume fraction, the accuracy of prediction was not worse. Thus, descriptive and quantitative texture parameters of tumour cells are of major importance for the extent of propagation in the prostate gland in incidental prostatic adenocarcinomas. Classical statistical tools and neuronal approaches led to consistent conclusions.

Adenocarcinoma↗
PubMed1996

Varieties of Helmholtz Machine.

The Helmholtz machine is a new unsupervised learning architecture that uses top-down connections to build probability density models of input and bottom-up connections to build inverses to those models. The wake-sleep learning algorithm for the machine involves just the purely local delta rule. This paper suggests a number of different varieties of Helmholtz machines, each with its own strengths and weaknesses, and relates them to cortical information processing. Copyright 1996 Elsevier Science Ltd.

Journal Article↗
PubMed2005

Cortical ensemble adaptation to represent velocity of an artificial actuator controlled by a brain-machine interface.

Monkeys can learn to directly control the movements of an artificial actuator by using a brain-machine interface (BMI) driven by the activity of a sample of cortical neurons. Eventually, they can do so without moving their limbs. Neuronal adaptations underlying the transition from control of the limb to control of the actuator are poorly understood. Here, we show that rapid modifications in neuronal representation of velocity of the hand and actuator occur in multiple cortical areas during the operation of a BMI. Initially, monkeys controlled the actuator by moving a hand-held pole. During this period, the BMI was trained to predict the actuator velocity. As the monkeys started using their cortical activity to control the actuator, the activity of individual neurons and neuronal populations became less representative of the animal's hand movements while representing the movements of the actuator. As a result of this adaptation, the animals could eventually stop moving their hands yet continue to control the actuator. These results show that, during BMI control, cortical ensembles represent behaviorally significant motor parameters, even if these are not associated with movements of the animal's own limb.

Adaptation, Physiological↗
PubMed2002

A support vector machine approach for detection of microcalcifications.

In this paper, we investigate an approach based on support vector machines (SVMs) for detection of microcalcification (MC) clusters in digital mammograms, and propose a successive enhancement learning scheme for improved performance. SVM is a machine-learning method, based on the principle of structural risk minimization, which performs well when applied to data outside the training set. We formulate MC detection as a supervised-learning problem and apply SVM to develop the detection algorithm. We use the SVM to detect at each location in the image whether an MC is present or not. We tested the proposed method using a database of 76 clinical mammograms containing 1120 MCs. We use free-response receiver operating characteristic curves to evaluate detection performance, and compare the proposed algorithm with several existing methods. In our experiments, the proposed SVM framework outperformed all the other methods tested. In particular, a sensitivity as high as 94% was achieved by the SVM method at an error rate of one false-positive cluster per image. The ability of SVM to out perform several well-known methods developed for the widely studied problem of MC detection suggests that SVM is a promising technique for object detection in a medical imaging application.

Algorithms↗
PubMed2004

Improved protein secondary structure prediction using support vector machine with a new encoding scheme and an advanced tertiary classifier.

Prediction of protein secondary structures is an important problem in bioinformatics and has many applications. The recent trend of secondary structure prediction studies is mostly based on the neural network or the support vector machine (SVM). The SVM method is a comparatively new learning system which has mostly been used in pattern recognition problems. In this study, SVM is used as a machine learning tool for the prediction of secondary structure and several encoding schemes, including orthogonal matrix, hydrophobicity matrix, BLOSUM62 substitution matrix, and combined matrix of these, are applied and optimized to improve the prediction accuracy. Also, the optimal window length for six SVM binary classifiers is established by testing different window sizes and our new encoding scheme is tested based on this optimal window size via sevenfold cross validation tests. The results show 2% increase in the accuracy of the binary classifiers when compared with the instances in which the classical orthogonal matrix is used. Finally, to combine the results of the six SVM binary classifiers, a new tertiary classifier which combines the results of one-versus-one binary classifiers is introduced and the performance is compared with those of existing tertiary classifiers. According to the results, the Q3 prediction accuracy of new tertiary classifier reaches 78.8% and this is better than the best result reported in the literature.

Algorithms↗
PubMed2006

A cerebellar model for predictive motor control tested in a brain-based device.

The cerebellum is known to be critical for accurate adaptive control and motor learning. We propose here a mechanism by which the cerebellum may replace reflex control with predictive control. This mechanism is embedded in a learning rule (the delayed eligibility trace rule) in which synapses onto a Purkinje cell or onto a cell in the deep cerebellar nuclei become eligible for plasticity only after a fixed delay from the onset of suprathreshold presynaptic activity. To investigate the proposal that the cerebellum is a general-purpose predictive controller guided by a delayed eligibility trace rule, a computer model based on the anatomy and dynamics of the cerebellum was constructed. It contained components simulating cerebellar cortex and deep cerebellar nuclei, and it received input from a middle temporal visual area and the inferior olive. The model was incorporated in a real-world brain-based device (BBD) built on a Segway robotic platform that learned to traverse curved paths. The BBD learned which visual motion cues predicted impending collisions and used this experience to avoid path boundaries. During learning, the BBD adapted its velocity and turning rate to successfully traverse various curved paths. By examining neuronal activity and synaptic changes during this behavior, we found that the cerebellar circuit selectively responded to motion cues in specific receptive fields of simulated middle temporal visual areas. The system described here prompts several hypotheses about the relationship between perception and motor control and may be useful in the development of general-purpose motor learning systems for machines.

Cerebellum↗
PubMed1995

[Ventilators for anesthesia. Models available in France. Criteria for choice].

This update article discusses the criteria for the choice of an anaesthetic machine and provides a short analysis of the main components of the models commercialized in France in 1994. The following items are considered: the design of the machine, the fresh gas delivery system, the anaesthesia breathing system(s), the ventilator and the waste gas scavenging system, the monitors associated with the machine and other criteria such as facility of learning to run the machine and of its daily use, ease of "in-house" maintenance and quality of after-sales service, cost of the machine and of its use (driving gas, disposable equipment).

Anesthesia, Inhalation↗
PubMed2005

Rigorous proof of termination of SMO algorithm for support vector machines.

Sequential minimal optimization (SMO) algorithm is one of the simplest decomposition methods for learning of support vector machines (SVMs). Keerthi and Gilbert have recently studied the convergence property of SMO algorithm and given a proof that SMO algorithm always stops within a finite number of iterations. In this letter, we point out the incompleteness of their proof and give a more rigorous proof.

Algorithms↗
PubMed2006

Learning beyond finite memory in recurrent networks of spiking neurons.

We investigate possibilities of inducing temporal structures without fading memory in recurrent networks of spiking neurons strictly operating in the pulse-coding regime. We extend the existing gradient-based algorithm for training feedforward spiking neuron networks, SpikeProp (Bohte, Kok, & La Poutré, 2002), to recurrent network topologies, so that temporal dependencies in the input stream are taken into account. It is shown that temporal structures with unbounded input memory specified by simple Moore machines (MM) can be induced by recurrent spiking neuron networks (RSNN). The networks are able to discover pulse-coded representations of abstract information processing states coding potentially unbounded histories of processed inputs. We show that it is often possible to extract from trained RSNN the target MM by grouping together similar spike trains appearing in the recurrent layer. Even when the target MM was not perfectly induced in a RSNN, the extraction procedure was able to reveal weaknesses of the induced mechanism and the extent to which the target machine had been learned.

Action Potentials↗
PubMed1983

[Necessity for and construction of cytological data banks].

Analytical and quantitative cytology is based upon photometric and morphometric measurements of single cells in stained cytological specimens. It analyzes the features of single cells and cell populations with respect to their cytodiagnostic relevance. One way to do this is the establishment of learning sets of visually selected cells, and the intercomparison of unknown cells with these data sets. Difficulties arise with the visual classification of single cells from PAP-stained gynecological smears and the pooling into classes due to the considerable photometric variation from specimen to specimen. It is demonstrated, that neither for a cancer prescreening apparatus nor an interactive diagnostic machine, highly differentiated learning sets can be dispensed with. The build-up of the TUDAB learning sets and results of single cell classification, visual reclassification, as well as population analysis and specimen classification are shown.

Cell Physiological Phenomena↗
PubMed2026

Data-centric, robust, and explainable multimodal deep learning for clinical decision support: A systematic review.

PURPOSE: Multimodal deep learning is increasingly proposed for clinical decision support (CDS) under a "data-centric" framing that prioritizes label quality, missing-modality robustness, distribution shift, calibration, and explainability. Prior reviews have examined multimodal medical AI, CDS, and data-centric methods separately, but none address their intersection. We mapped the modalities, fusion strategies, and data-centric and explainability techniques used in this recent literature, quantified how often each is implemented rather than merely mentioned, assessed deployment-relevant evidence (external validation, clinical-outcome measurement, equity), and formally appraised study-level risk of bias. METHODS: Following the PRISMA 2020 statement (PROSPERO CRD420261427815; registered retrospectively), we screened 150 records and included primary, clinical, multimodal studies that applied machine or deep learning to a decision-support task and reported at least one quantitative result. Two reviewers screened and extracted data with consensus adjudication. Each study was coded against pre-specified operational definitions, separating implemented or empirically evaluated techniques from those only mentioned. Study-level risk of bias was assessed with PROBAST + AI. Synthesis was narrative. RESULTS: Thirty-one studies met inclusion; 30 (97%) were published between 2024 and 2026, with a median of three modalities (range 2-6), most commonly structured EHR (71%) and imaging (39%). Data-centric techniques were frequently reported (74-84% across label-noise, distribution-shift, calibration, missing-modality and class-imbalance handling; equity 61%). However, external validation was reported in only 4/31 studies (13%), a clinical or provider outcome in 3/31 (10%), and no study reported routine deployment. Overall risk of bias was high in 27/31 studies (87%), driven by the analysis domain. CONCLUSION: Within this recent, self-selected slice of the field, technical robustness and explainability techniques are widely reported but rarely validated out-of-distribution or against clinical outcomes, and the underlying evidence is at high risk of bias. Progress requires external multi-site validation, clinical-outcome measurement, formal bias appraisal, and adherence to AI reporting standards (e.g., TRIPOD + AI) before deployment can be justified.

Deep Learning↗
PubMed2003

Intelligent machines in the twenty-first century: foundations of inference and inquiry.

The last century saw the application of Boolean algebra to the construction of computing machines, which work by applying logical transformations to information contained in their memory. The development of information theory and the generalization of Boolean algebra to Bayesian inference have enabled these computing machines, in the last quarter of the twentieth century, to be endowed with the ability to learn by making inferences from data. This revolution is just beginning as new computational techniques continue to make difficult problems more accessible. Recent advances in our understanding of the foundations of probability theory have revealed implications for areas other than logic. Of relevance to intelligent machines, we recently identified the algebra of questions as the free distributive algebra, which will now allow us to work with questions in a way analogous to that which Boolean algebra enables us to work with logical statements. In this paper, we examine the foundations of inference and inquiry. We begin with a history of inferential reasoning, highlighting key concepts that have led to the automation of inference in modern machine-learning systems. We then discuss the foundations of inference in more detail using a modern viewpoint that relies on the mathematics of partially ordered sets and the scaffolding of lattice theory. This new viewpoint allows us to develop the logic of inquiry and introduce a measure describing the relevance of a proposed question to an unresolved issue. Last, we will demonstrate the automation of inference, and discuss how this new logic of inquiry will enable intelligent machines to ask questions. Automation of both inference and inquiry promises to allow robots to perform science in the far reaches of our solar system and in other star systems by enabling them not only to make inferences from data, but also to decide which question to ask, which experiment to perform, or which measurement to take given what they have learned and what they are designed to understand.

Artificial Intelligence↗
PubMed2006

Simultaneous quantification of carbamazepine crystal forms in ternary mixtures (I, III, and IV) by diffuse reflectance FTIR spectroscopy (DRIFTS) and multivariate calibration.

Diffuse reflectance FTIR spectroscopy (DRIFTS) coupled with modern multivariate calibration methods, namely artificial neural networks (ANNs) in two versions (ANN-raw and ANN-pca), support vector machines (SVMs), lazy learning (LL) and partial least squares (PLS) regression, is used in this study for the quantification of carbamazepine crystal forms in ternary powder mixtures (I, III, and IV). Two spectral regions (675-1180 and 3400-3600/cm) were selected and the data were partitioned into training and test subsets applying the Kennard-Stone design. It was found that all the selected algorithms perform better than the PLS regression (root mean squared error of prediction (RMSEP) from 3.0% to 8.2%). ANN-raw, trained on uncompressed spectral data, shows best predictive performance (RMSEP < 2.25%) but longest computation (up to 10 min). Principal component analysis (PCA) compression of the input spectral data accelerates significantly the computation (<16 s) at a relatively low cost in precision (RMSEP < 3.24%). The LL algorithm shows excellent performance in the 3400-3600/cm range (RMSEP < 1.6%), but in the 675-1180/cm range it shows strong dependence on data set structure (RMSEP between 1.6% and 8.9%). SVMs perform comparably well with ANNs (RMSEP < 3.1%), not showing the long computation time of ANNs (<1 s) and therefore may provide an attractive alternative to ANNs.

Algorithms↗