Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “sparse 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 91 records · Page 5Linked to original sources
PubMed2001

A comparison of memory for verbal and non-verbal material in schizophrenia.

Verbal memory impairment has been well explored in schizophrenia, but it is unclear whether findings relate to the type of material to be learned or the component process required by the memory task. Also, sparse data on non-verbal memory also open the question of how well schizophrenia patients encode this material. We tested whether episodic memory performance in schizophrenia varies as a function of stimulus material (verbal/non-verbal) and determined the integrity of various component memory processes. Memory tests that differ in stimulus material (words, California Verbal Learning Test, CVLT; designs, Biber Figure Learning Test-Extended, BFLT-E) yet produce similar memory component measures were used. Subjects were 28 neuroleptic-medicated inpatients with a diagnosis of chronic schizophrenia. Results showed that both verbal and non-verbal memory performance was impaired relative to age-matched controls. Learning and recall measures were most severely impaired, with memory storage problems and impairment in recognition memory evident. On the verbal task, the relative sparing of recognition memory suggested retrieval processes, in addition to encoding processes, were disrupted. On the non-verbal task, the deficits appeared more limited to encoding. Therefore, while the operational integrity of components such as encoding were compromised regardless of material, retrieval processes showed material-specific effects. To the degree verbal and non-verbal memory functions can be lateralized in the brain, these data support the possibility of deficits in both right and left hemisphere declarative memory systems in schizophrenia.

Adult↗
PubMed2004

Sparse distributed memory using N-of-M codes.

An analysis is presented of a sparse distributed memory (SDM) inspired by that described by Kanerva [Kanerva, P. (1988). Sparse distributed memory. Cambridge, MA: MIT Press] but modified to facilitate an implementation based on spiking neurons. The memory presented here employs sparse binary N-of-M codes, unipolar binary synaptic weights and a simple Hebbian learning rule. It is a two-layer network, the first (fixed) layer being similar to the 'address decoder' in Jaeckel's [Jaeckel, L.A. (1989). A class of designs for a sparse distributed memory. RIACS Technical Report 89.30, NASA Ames Research Centre] 'hyperplane' variant of Kanerva's SDM and the second (writeable) 'data store' layer being a correlation matrix memory as first proposed by Willshaw et al. [Willshaw, D. J., Buneman, O.P., & Longuet-Higgins, H.C. (1969). Non-holographic associative memory. Nature, 222, 960-962]. The resulting network is shown to have good storage efficiency and is scalable. The analysis is supported by numerical simulations and gives results that enable the configuration of the memory to be optimised for a range of noiseless and noisy environments.

Association Learning↗
PubMedDate not supplied

Mapping of olfactory memory circuits: region-specific c-fos activation after odor-reward associative learning or after its retrieval.

Although there is growing knowledge about intracellular mechanisms underlying neuronal plasticity and memory consolidation and reconsolidation after retrieval, information concerning the interaction among brain areas during formation and retrieval of memory is relatively sparse and fragmented. Addressing this question requires simultaneous monitoring of activity in multiple brain regions during learning, the post-acquisition consolidation period, and retrieval and subsequent reconsolidation. Immunoreaction to the immediate early gene c-fos is a powerful tool to mark neuronal activation of specific populations of neurons. Using this method, we are able to report, for the first time, post-training activation of a network of closely related brain regions, particularly in the frontal cortex and the basolateral amygdala (BLA), that is specific to the learning of an odor-reward association. On the other hand, retrieval of a well-established associative memory trace does not seem to differentially activate the same regions. The amygdala, in particular, is not engaged after retrieval, whereas the lateral habenula (LHab) shows strong activation that is restricted to animals having previously learned the association. Although intracellular mechanisms may be similar during consolidation and reconsolidation, this study indicates that different brain circuits are involved in the two processes, at least with respect to a rapidly learned olfactory task.

Amygdala↗
PubMed1981

Transfer of perceptual learning: role of tactual-kinesthetic feedback reexamined.

Albino rats were pre-exposed to stimuli in an otherwise visually sparse environment, with visibility and opportunity to manipulate the forms controlled during rearing. Analysis indicated that pre-exposing animals to stimuli which provided either tactual-kinesthetic feedback or highly visible forms significantly facilitated subsequent discrimination learning. The findings question the adequacy of either an attention-getting or tactual-kinesthetic feedback to account for differences in transfer effects in studies using two- and three-dimensional forms. It is suggested that the visibility of the forms and the opportunity to inspect the forms during pre-exposure is the important variable in studies of this type.

Animals↗
PubMed2002

Learning generative models of natural images.

This work proposes an unsupervised learning process for analysis of natural images. The derivation is based on a generative model, a stochastic coin-flip process directly operating on many disjoint multivariate Gaussian distributions. Following the maximal likelihood principle and using the Potts encoding, the goodness-of-fit of the generative model to tremendous patches randomly sampled from natural images is quantitatively expressed by an objective function subject to a set of constraints. By further combination of the objective function and the minimal wiring criterion, we achieve a mixed integer and linear programming. A hybrid of the mean field annealing and the gradient descent method is applied to the mathematical framework and produces three sets of interactive dynamics for the learning process. Numerical simulations show that the learning process is effective for extraction of orientation, localization and bandpass features and the generative model can make an ensemble of a sparse code for natural images.

Learning↗
PubMed1992

Quality improvement and health care: an annotated bibliography.

W. Edwards Deming's theories of continuous quality improvement, using statistical analysis to identify problems or errors in operational processes, are in the early stages of development in service organizations after substantial success in industry, especially in Japan. Information on continuous quality improvement for libraries is sparse. The articles in this annotated bibliography will help interested readers learn more about this theory and its application in the health care business.

Hospital Administration↗
PubMed1999

Emotional and behavioral correlates of the anterior cingulate cortex during associative learning in rats.

Neuronal activity was recorded from the anterior cingulate cortex of behaving rats during discrimination and learning of conditioned stimuli associated with or without reinforcements. The rats were trained to lick a protruding spout just after a conditioned stimulus to obtain reward (intracranial self-stimulation or sucrose solution) or to avoid aversion. The conditioned stimuli included both elemental (auditory or visual stimuli) and configural (simultaneous presentation of auditory and visual stimuli predicting reward outcome opposite to that predicted by each stimulus presented alone) stimuli. Of the 62 anterior cingulate neurons responding during the task, 38 and four responded differentially and non-differentially to the conditioned stimuli (conditioned stimulus-related neurons), respectively. Of the 38 differential conditioned stimulus-related neurons, 33 displayed excitatory (n = 10) and inhibitory (n = 23) responses selectively to the conditioned stimuli predicting reward. These excitatory and inhibitory differential conditioned stimulus-related neurons were located mainly in the cingulate cortex areas 1 and 3 of the rostral and ventral parts of the anterior cingulate cortex, respectively. The remaining 20 neurons responded mainly during intracranial self-stimulation and/or ingestion of sucrose (ingestion/intracranial self-stimulation-related neurons). Increase in activity of the ingestion/intracranial self-stimulation-related neurons was correlated to the first lick to obtain rewards during the task, suggesting that the activity reflected some aspects of motor functions for learned instrumental behaviors. These ingestion/intracranial self-stimulation-related neurons were located sparsely in cingulate cortex area 1 of the rostral part of the anterior cingulate cortex and densely in frontal area 2 of the caudal and dorsal parts of the anterior cingulate cortex. Analysis by the multidimensional scaling of responses of 38 differential conditioned stimulus-related neurons indicated that the anterior cingulate cortex categorized the conditioned stimuli into three groups based on reward contingency, regardless of the physical characteristics of the stimuli, in a two-dimensional space; the three conditioned (two elemental and one configural) stimuli predicting sucrose solution, the three conditioned (two elemental and one configural) stimuli predicting no reward, and the lone conditioned stimulus predicting intracranial self-stimulation. The results suggest that the anterior cingulate cortex is organized topographically; stimulus attributes predicting reward or no reward are represented in the rostral and ventral parts of the anterior cingulate cortex, while the caudal and dorsal parts of the anterior cingulate cortex are related to execution of learned instrumental behaviors. These results are in line with recent neuropsychological studies suggesting that the rostral part of the anterior cingulate cortex plays a crucial role in socio-emotional behaviors by assigning a positive or negative value to future outcomes.

Acoustic Stimulation↗
PubMed2026

Artificial intelligence for anticancer drug discovery from natural products of macroalgae and sponges: A systematic review.

Marine natural products (MNPs) from macroalgae and marine sponges have inspired clinically important anticancer agents, including the cytarabine pharmacophore and the eribulin scaffold, while cyanobacterial dolastatin chemistry supplies the auristatin payloads of several marine-inspired antibody-drug conjugates (ADCs) such as brentuximab vedotin. Artificial intelligence (AI) methods, encompassing both classical machine learning (ML) with hand-engineered features and modern deep learning (DL) with many-layered neural networks, are increasingly supporting key decisions in natural-product anticancer drug discovery, including bioactivity prediction, target identification, absorption, distribution, metabolism, excretion and toxicity (ADMET) filtering, generative analogue design, and the selection of preclinical candidates. DL architectures relevant to this field include graph neural networks, transformer-based molecular generators, diffusion models for protein-ligand docking, and convolutional networks for mass spectrometry, while classical ML contributes interpretable fingerprint-based bioactivity models and molecular networking for dereplication. This review follows a systematic literature review methodology to organize the landscape of AI methods now applied to MNP anticancer discovery, distinguishing ML and DL approaches where relevant, situating them within the chemical context of macroalgal and sponge-derived oncology leads, and critically examining published case studies, including validation level (computational, in vitro, in vivo, clinical). The principal bottleneck for medical translation has shifted partly from algorithmic capability toward data infrastructure and experimental validation. Sparse, heterogeneous, and taxonomically biased bioactivity records limit what current models can learn and reduce the reliability of AI-prioritized candidates entering the preclinical pipeline. A roadmap is proposed that prioritizes open MNP-specific benchmarks, symbiont-aware modeling, and active learning loops with synthesizability and ADMET constraints. These AI workflows may accelerate the prioritization of marine-derived anticancer leads and support earlier, more evidence-based translational decisions in oncology drug development.

Biological Products↗
PubMed2000

The effect of intracortical competition on the formation of topographic maps in models of Hebbian learning.

Correlation-based learning (CBL) models and self-organizing maps (SOM) are two classes of Hebbian models that have both been proposed to explain the activity-driven formation of cortical maps. Both models differ significantly in the way lateral cortical interactions are treated, leading to different predictions for the formation of receptive fields. The linear CBL models predict that receptive field profiles are determined by the average values and the spatial correlations of the second order of the afferent activity patterns, whereas SOM models map stimulus features. Here, we investigate a class of models which are characterized by a variable degree of lateral competition and which have the CBL and SOM models as limit cases. We show that there exists a critical value for intracortical competition below which the model exhibits CBL properties and above which feature mapping sets in. The class of models is then analyzed with respect to the formation of topographic maps between two layers of neurons. For Gaussian input stimuli we find that localized receptive fields and topographic maps emerge above the critical value for intracortical competition, and we calculate this value as a function of the size of the input stimuli and the range of the lateral interaction function. Additionally, we show that the learning rule can be derived via the optimization of a global cost function in a framework of probabilistic output neurons which represent a set of input stimuli by a sparse code.

Algorithms↗
PubMed1988

Terrorist bombings. Lessons learned from Belfast to Beirut.

Experience in the management of mass casualties following a disaster is relatively sparse. The terrorist bombing serves as a timely and effective model for the analysis of patterns of injury and mortality and the determination of the factors influencing casualty survival in the wake of certain forms of disaster. For this purpose, a review of the published experience with terrorist bombings was carried out, providing a study population of 3357 casualties from 220 incidents worldwide. There were 2934 immediate survivors of these incidents (87%), of whom 881 (30%) were hospitalized. Forty deaths ultimately occurred among these survivors (1.4%), 39 of whom were among those hospitalized (4.4%). Injury severity was determined from available data for 1339 surviving casualties, 251 of whom were critically injured (18.7%). Of this population evaluable for injury severity, there were 31 late deaths, all of which occurred among those critically injured, accounting for an overall "critical mortality" rate of 12.4%. Overall triage efficiency was characterized by a mean overtriage rate (noncritically injured among those hospitalized or evacuated) of 59%, and a mean undertriage rate (critically injured among those not hospitalized or evacuated) of .05%. Multiple linear regression analysis of all major bombing incidents demonstrated a direct linear relationship between overtriage and critical mortality (r2 = .845), and an inversely proportional relationship between triage discrimination and critical mortality (r2 = 0.855). Although head injuries predominated in both immediate (71%) and late (52%) fatalities, injury to the abdomen carried the highest specific mortality rate (19%) of any single body system injury among immediate survivors. These data clearly document the importance of accurate triage as a survival determinant for critically injured casualties of these disasters. Furthermore, the data suggest that explosive force, time interval from injury to treatment, and anatomic site of injury are all factors that correlated with the ultimate outcome of terrorist bombing victims. Critical analysis of past disasters should allow for sufficient preparation so as to minimize casualty mortality in the future.

Abdominal Injuries↗
PubMed1999

International education--a kaleidoscopic view.

International travel presents opportunities for perioperative nurses to share their knowledge about surgical patient care and preventing the spread of infection. This article outlines the author's personal experiences with international travel, educational pursuits, and conferring with nurses, physicians, epidemiologists, hospital administrators, and medical product company representatives. It also discusses culture and values, teaching and learning, and accomplishments in settings where both financial and human resources are sparse, but outcomes are positive and meaningful.

Consultants↗
PubMed2004

An efficient and effective region-based image retrieval framework.

An image retrieval framework that integrates efficient region-based representation in terms of storage and complexity and effective on-line learning capability is proposed. The framework consists of methods for region-based image representation and comparison, indexing using modified inverted files, relevance feedback, and learning region weighting. By exploiting a vector quantization method, both compact and sparse (vector) region-based image representations are achieved. Using the compact representation, an indexing scheme similar to the inverted file technology and an image similarity measure based on Earth Mover's Distance are presented. Moreover, the vector representation facilitates a weighted query point movement algorithm and the compact representation enables a classification-based algorithm for relevance feedback. Based on users' feedback information, a region weighting strategy is also introduced to optimally weight the regions and enable the system to self-improve. Experimental results on a database of 10,000 general-purposed images demonstrate the efficiency and effectiveness of the proposed framework.

Abstracting and Indexing↗
PubMed2005

A computational principle for hippocampal learning and neurogenesis.

In the three decades since Marr put forward his computational theory of hippocampal coding, many computational models have been built on the same key principles proposed by Marr: sparse representations, rapid Hebbian storage, associative recall and consolidation. Most of these models have focused on either the CA3 or CA1 fields, using "off-the-shelf" learning algorithms such as competitive learning or Hebbian pattern association. Here, we propose a novel coding principle that is common to all hippocampal regions, and from this one principal, we derive learning rules for each of the major pathways within the hippocampus. The learning rules turn out to have much in common with several models of CA3 and CA1 in the literature, and provide a unifying framework in which to view these models. Simulations of the complete circuit confirm that both recognition memory and recall are superior relative to a hippocampally lesioned model, consistent with human data. Further, we propose a functional role for neurogenesis in the dentate gyrus (DG), namely, to create distinct memory traces for highly similar items. Our simulation results support our prediction that memory capacity increases with the number of dentate granule cells, while neuronal turnover with a fixed dentate layer size improves recall, by minimizing interference between highly similar items.

Action Potentials↗
PubMed2001

Similarity in perception: a window to brain organization.

This paper presents a neural model of similarity perception in identification tasks. It is based on self-organizing maps and population coding and is examined through five different identification experiments. Simulating an identification task, the neural model generates a confusion matrix that can be compared directly with that of human subjects. The model achieves a fairly accurate match with the pertaining experimental data both during training and thereafter. To achieve this fit, we find that the entire activity in the network should decline while learning the identification task, and that the population encoding of the specific stimuli should become sparse as the network organizes. Our results, thus, suggest that a self-organizing neural model employing population coding can account for identification processing while suggesting computational constraints on the underlying cortical networks.

Brain↗
PubMed2005

Exploiting temporal information in functional magnetic resonance imaging brain data.

Functional Magnetic Resonance Imaging(fMRI) has enabled scientists to look into the active human brain, leading to a flood of new data, thus encouraging the development of new data analysis methods. In this paper, we contribute a comprehensive framework for spatial and temporal exploration of fMRI data, and apply it to a challenging case study: separating drug addicted subjects from healthy non-drug-using controls. To our knowledge, this is the first time that learning on fMRI data is performed explicitly on temporal information for classification in such applications. Experimental results demonstrate that, by selecting discriminative features, group classification can be successfully performed on our case study although training data are exceptionally high dimensional, sparse and noisy fMRI sequences. The classification performance can be significantly improved by incorporating temporal information into machine learning. Both statistical and neuroscientific validation of the method's generalization ability are provided. We demonstrate that incorporation of computer science principles into functional neuroimaging clinical studies, facilitates deduction about the behavioral probes from the brain activation data, thus providing a valid tool that incorporates objective brain imaging data into clinical classification of psychopathologies and identification of genetic vulnerabilities.

Algorithms↗
PubMed1997

Associative List Memory.

This paper introduces an Associative List Memory (ALM) that has high recall fidelity with low memory and low processing requirements. This permits a simple implementation in software on a personal computer or space instrument microprocessor. Associative List Memory has a performance comparable with Sparse Distributed Memory (SDM) but differs from SDM in that convergence occurs during learning, rather than on recall, and in that the memory is in the form of a dynamic list rather than static randomly distributed locations. Associative List Memory is suitable for unsupervised finding of classes of phenomena in large databases. In particular, all of the class exemplars deduced can be easily accessed at any time to provide a summary of current database knowledge, being essentially the contents of the list. Examples are given where patterns of 1000 bits length with > 30% noise can be learned unsupervised to deduce the original pattern's noise free. A second pass through the data in recall mode can be used to assign to each input the appropriate original pattern, effectively removing all noise from the input data. At large input bit sizes the recall fidelity approaches closely to the maximum possible value. Associative List Memory compares well in recall fidelity with SDM and other associative memories. Its processing times on a personal computer are found to be practical for database applications. Implemented within a space instrument processor, ALM would greatly reduce downlink data transmission rates. Copyright 1997 Elsevier Science Ltd.

Journal Article↗
PubMed1992

Suicide notes of the older adult.

Although not true in all countries, older adults are the developmental age group at highest risk for death by suicide in the United States. Our knowledge of suicide in the elderly is, however, limited. The psychological characteristics for suicide cannot be attributed primarily or even solely to being old. One avenue to understanding this complicated act in the elderly is suicide notes. Despite their limitations, suicide notes contain special revelations of the human mind and there is much one can learn from them about suicide in the older adult. This paper outlines the sparse literature on the topic of suicide notes of the older adult and then presents the author's own life-span research related to the elderly. The research indicated that long-term instability was critical in understanding suicide in the older adult. However, indirect expressions (e.g., ambivalence, unconscious implications) were much less frequently observed in the notes of the elderly than other adults. The research also found that older males often wrote about painful problems in their interpersonal relations in their final letters and this pain was significant in making their final decision. Future research, specifically regarding a protocol analysis based on a review of the research on suicide in the elderly, will be discussed.

Adult↗
PubMed1997

The "independent components" of natural scenes are edge filters.

It has previously been suggested that neurons with line and edge selectivities found in primary visual cortex of cats and monkeys form a sparse, distributed representation of natural scenes, and it has been reasoned that such responses should emerge from an unsupervised learning algorithm that attempts to find a factorial code of independent visual features. We show here that a new unsupervised learning algorithm based on information maximization, a nonlinear "infomax" network, when applied to an ensemble of natural scenes produces sets of visual filters that are localized and oriented. Some of these filters are Gabor-like and resemble those produced by the sparseness-maximization network. In addition, the outputs of these filters are as independent as possible, since this infomax network performs Independent Components Analysis or ICA, for sparse (super-gaussian) component distributions. We compare the resulting ICA filters and their associated basis functions, with other decorrelating filters produced by Principal Components Analysis (PCA) and zero-phase whitening filters (ZCA). The ICA filters have more sparsely distributed (kurtotic) outputs on natural scenes. They also resemble the receptive fields of simple cells in visual cortex, which suggests that these neurons form a natural, information-theoretic coordinate system for natural images.

Algorithms↗