keyword
MENU ▼
Read by QxMD icon Read
search

Learning networks

keyword
https://www.readbyqxmd.com/read/28806717/efficient-construction-of-sparse-radial-basis-function-neural-networks-using-l1-regularization
#1
Xusheng Qian, He Huang, Xiaoping Chen, Tingwen Huang
This paper investigates the construction of sparse radial basis function neural networks (RBFNNs) for classification problems. An efficient two-phase construction algorithm (which is abbreviated as TPCLR1 for simplicity) is proposed by using L1 regularization. In the first phase, an improved maximum data coverage (IMDC) algorithm is presented for the initialization of RBF centers and widths. Then a specialized Orthant-Wise Limited-memory Quasi-Newton (sOWL-QN) method is employed to perform simultaneous network pruning and parameter optimization in the second phase...
July 27, 2017: Neural Networks: the Official Journal of the International Neural Network Society
https://www.readbyqxmd.com/read/28806715/recurrent-networks-with-soft-thresholding-nonlinearities-for-lightweight-coding
#2
MohammadMehdi Kafashan, ShiNung Ching
A long-standing and influential hypothesis in neural information processing is that early sensory networks adapt themselves to produce efficient codes of afferent inputs. Here, we show how a nonlinear recurrent network provides an optimal solution for the efficient coding of an afferent input and its history. We specifically consider the problem of producing lightweight codes, ones that minimize both ℓ1 and ℓ2 constraints on sparsity and energy, respectively. When embedded in a linear coding paradigm, this problem results in a non-smooth convex optimization problem...
July 22, 2017: Neural Networks: the Official Journal of the International Neural Network Society
https://www.readbyqxmd.com/read/28805472/network-experiences-from-a-cross-sector-biosafety-level-3-laboratory-collaboration-a-swedish-forum-for-biopreparedness-diagnostics
#3
Johanna Thelaus, Anna Lindberg, Susanne Thisted Lambertz, Mona Byström, Mats Forsman, Hans Lindmark, Rickard Knutsson, Viveca Båverud, Andreas Bråve, Pontus Jureen, Annelie Lundin Zumpe, Öjar Melefors
The Swedish Forum for Biopreparedness Diagnostics (FBD) is a network that fosters collaboration among the 4 agencies with responsibility for the laboratory diagnostics of high-consequence pathogens, covering animal health and feed safety, food safety, public health and biodefense, and security. The aim of the network is to strengthen capabilities and capacities for diagnostics at the national biosafety level-3 (BSL-3) laboratories to improve Sweden's biopreparedness, in line with recommendations from the EU and WHO...
August 14, 2017: Health Security
https://www.readbyqxmd.com/read/28803867/dynamics-of-eeg-functional-connectivity-during-statistical-learning
#4
Brigitta Tóth, Karolina Janacsek, Ádám Takács, Andrea Kóbor, Zsófia Zavecz, Dezso Nemeth
Statistical learning is a fundamental mechanism of the brain, which extracts and represents regularities of our environment. Statistical learning is crucial in predictive processing, and in the acquisition of perceptual, motor, cognitive, and social skills. Although previous studies have revealed competitive neurocognitive processes underlying statistical learning, the neural communication of the related brain regions (functional connectivity, FC) has not yet been investigated. The present study aimed to fill this gap by investigating FC networks that promote statistical learning in humans...
August 10, 2017: Neurobiology of Learning and Memory
https://www.readbyqxmd.com/read/28802184/functional-neural-bases-of-numerosity-judgments-in-healthy-adults-born-preterm
#5
Caron A C Clark, Yating Liu, Nicolas Lee Abbot Wright, Alan Bedrick, Jamie O Edgin
High rates of mathematics learning disabilities among individuals born preterm (<37weeksGA) have spurred calls for a greater understanding of the nature of these weaknesses and their neural underpinnings. Groups of healthy, high functioning young adults born preterm and full term (n=20) completed a symbolic and non-symbolic magnitude comparison task while undergoing functional MRI scanning. Collectively, participants showed activation in superior and inferior frontal and parietal regions previously linked to numeric processing when comparing non-symbolic magnitude arrays separated by small numeric distances...
August 9, 2017: Brain and Cognition
https://www.readbyqxmd.com/read/28801052/accompaniment-of-second-trimester-abortions-the-model-of-the-feminist-socorrista-network-of-argentina
#6
Ruth Zurbriggen, Brianna Keefe-Oates, Caitlin Gerdts
OBJECTIVE: Legal restrictions on abortion access impact the safety and timing of abortion. Women affected by these laws face barriers to safe care that often result in abortion being delayed. Second-trimester abortion affects vulnerable groups of women disproportionately, and is often more difficult to access. In Argentina, where abortion is legally restricted except in cases of rape or threat to the health of the woman, the Socorristas en Red, a feminist network, offers a model of accompaniment wherein they provide information and support to women seeking second-trimester abortions...
August 8, 2017: Contraception
https://www.readbyqxmd.com/read/28800619/-what-is-relevant-in-a-text-document-an-interpretable-machine-learning-approach
#7
Leila Arras, Franziska Horn, Grégoire Montavon, Klaus-Robert Müller, Wojciech Samek
Text documents can be described by a number of abstract concepts such as semantic category, writing style, or sentiment. Machine learning (ML) models have been trained to automatically map documents to these abstract concepts, allowing to annotate very large text collections, more than could be processed by a human in a lifetime. Besides predicting the text's category very accurately, it is also highly desirable to understand how and why the categorization process takes place. In this paper, we demonstrate that such understanding can be achieved by tracing the classification decision back to individual words using layer-wise relevance propagation (LRP), a recently developed technique for explaining predictions of complex non-linear classifiers...
2017: PloS One
https://www.readbyqxmd.com/read/28800442/pre-trained-convolutional-neural-networks-as-feature-extractors-for-tuberculosis-detection
#8
U K Lopes, J F Valiati
It is estimated that in 2015, approximately 1.8 million people infected by tuberculosis died, most of them in developing countries. Many of those deaths could have been prevented if the disease had been detected at an earlier stage, but the most advanced diagnosis methods are still cost prohibitive for mass adoption. One of the most popular tuberculosis diagnosis methods is the analysis of frontal thoracic radiographs; however, the impact of this method is diminished by the need for individual analysis of each radiography by properly trained radiologists...
August 4, 2017: Computers in Biology and Medicine
https://www.readbyqxmd.com/read/28800339/perceptual-learning-improves-contrast-sensitivity-visual-acuity-and-foveal-crowding-in-amblyopia
#9
Michele Barollo, Giulio Contemori, Luca Battaglini, Andrea Pavan, Clara Casco
BACKGROUND: Amblyopic observers present abnormal spatial interactions between a low-contrast sinusoidal target and high-contrast collinear flankers. It has been demonstrated that perceptual learning (PL) can modulate these low-level lateral interactions, resulting in improved visual acuity and contrast sensitivity. OBJECTIVE: We measured the extent and duration of generalization effects to various spatial tasks (i.e., visual acuity, Vernier acuity, and foveal crowding) through PL on the target's contrast detection...
August 11, 2017: Restorative Neurology and Neuroscience
https://www.readbyqxmd.com/read/28798957/holographic-deep-learning-for-rapid-optical-screening-of-anthrax-spores
#10
YoungJu Jo, Sangjin Park, JaeHwang Jung, Jonghee Yoon, Hosung Joo, Min-Hyeok Kim, Suk-Jo Kang, Myung Chul Choi, Sang Yup Lee, YongKeun Park
Establishing early warning systems for anthrax attacks is crucial in biodefense. Despite numerous studies for decades, the limited sensitivity of conventional biochemical methods essentially requires preprocessing steps and thus has limitations to be used in realistic settings of biological warfare. We present an optical method for rapid and label-free screening of Bacillus anthracis spores through the synergistic application of holographic microscopy and deep learning. A deep convolutional neural network is designed to classify holographic images of unlabeled living cells...
August 2017: Science Advances
https://www.readbyqxmd.com/read/28798703/neural-correlates-of-morphology-acquisition-through-a-statistical-learning-paradigm
#11
Michelle Sandoval, Dianne Patterson, Huanping Dai, Christopher J Vance, Elena Plante
The neural basis of statistical learning as it occurs over time was explored with stimuli drawn from a natural language (Russian nouns). The input reflected the "rules" for marking categories of gendered nouns, without making participants explicitly aware of the nature of what they were to learn. Participants were scanned while listening to a series of gender-marked nouns during four sequential scans, and were tested for their learning immediately after each scan. Although participants were not told the nature of the learning task, they exhibited learning after their initial exposure to the stimuli...
2017: Frontiers in Psychology
https://www.readbyqxmd.com/read/28798678/striatal-neuropeptides-enhance-selection-and-rejection-of-sequential-actions
#12
David Buxton, Enrico Bracci, Paul G Overton, Kevin Gurney
The striatum is the primary input nucleus for the basal ganglia, and receives glutamatergic afferents from the cortex. Under the hypothesis that basal ganglia perform action selection, these cortical afferents encode potential "action requests." Previous studies have suggested the striatum may utilize a mutually inhibitory network of medium spiny neurons (MSNs) to filter these requests so that only those of high salience are selected. However, the mechanisms enabling the striatum to perform clean, rapid switching between distinct actions that form part of a learned action sequence are still poorly understood...
2017: Frontiers in Computational Neuroscience
https://www.readbyqxmd.com/read/28797934/building-workplace-social-capital-a-longitudinal-study-of-student-nurses-clinical-placement-experiences
#13
Michelle Materne, Amanda Henderson, Emma Eaton
Quality clinical placement experiences have been associated with nurses' workplace social capital. Social capital is broadly understood as the social organisation of trust, norms and networks that benefit society. Building social capital in the workplace may benefit experiences of staff and students. The aim of this study was to assess the impact of building workplace social capital on student nurse perceptions of clinical learning experiences. A quality improvement process was measured through repeated student surveys...
July 25, 2017: Nurse Education in Practice
https://www.readbyqxmd.com/read/28797709/word-embeddings-and-recurrent-neural-networks-based-on-long-short-term-memory-nodes-in-supervised-biomedical-word-sense-disambiguation
#14
Antonio Jimeno Yepes
Word sense disambiguation helps identifying the proper sense of ambiguous words in text. With large terminologies such as the UMLS Metathesaurus ambiguities appear and highly effective disambiguation methods are required. Supervised learning algorithm methods are used as one of the approaches to perform disambiguation. Features extracted from the context of an ambiguous word are used to identify the proper sense of such a word. The type of features have an impact on machine learning methods, thus affect disambiguation performance...
August 7, 2017: Journal of Biomedical Informatics
https://www.readbyqxmd.com/read/28797548/efficient-and-robust-cell-detection-a-structured-regression-approach
#15
Yuanpu Xie, Fuyong Xing, Xiaoshuang Shi, Xiangfei Kong, Hai Su, Lin Yang
Efficient and robust cell detection serves as a critical prerequisite for many subsequent biomedical image analysis methods and computer-aided diagnosis (CAD). It remains a challenging task due to touching cells, inhomogeneous background noise, and large variations in cell sizes and shapes. In addition, the ever-increasing amount of available datasets and the high resolution of whole-slice scanned images pose a further demand for efficient processing algorithms. In this paper, we present a novel structured regression model based on a proposed fully residual convolutional neural network for efficient cell detection...
July 26, 2017: Medical Image Analysis
https://www.readbyqxmd.com/read/28797096/prediction-of-n-linked-glycosylation-sites-using-position-relative-features-and-statistical-moments
#16
Muhammad Aizaz Akmal, Nouman Rasool, Yaser Daanial Khan
Glycosylation is one of the most complex post translation modification in eukaryotic cells. Almost 50% of the human proteome is glycosylated as glycosylation plays a vital role in various biological functions such as antigen's recognition, cell-cell communication, expression of genes and protein folding. It is a significant challenge to identify glycosylation sites in protein sequences as experimental methods are time taking and expensive. A reliable computational method is desirable for the identification of glycosylation sites...
2017: PloS One
https://www.readbyqxmd.com/read/28797034/unsupervised-learning-of-temporal-features-for-word-categorization-in-a-spiking-neural-network-model-of-the-auditory-brain
#17
Irina Higgins, Simon Stringer, Jan Schnupp
The nature of the code used in the auditory cortex to represent complex auditory stimuli, such as naturally spoken words, remains a matter of debate. Here we argue that such representations are encoded by stable spatio-temporal patterns of firing within cell assemblies known as polychronous groups, or PGs. We develop a physiologically grounded, unsupervised spiking neural network model of the auditory brain with local, biologically realistic, spike-time dependent plasticity (STDP) learning, and show that the plastic cortical layers of the network develop PGs which convey substantially more information about the speaker independent identity of two naturally spoken word stimuli than does rate encoding that ignores the precise spike timings...
2017: PloS One
https://www.readbyqxmd.com/read/28796627/automated-breast-ultrasound-lesions-detection-using-convolutional-neural-networks
#18
Moi Hoon Yap, Gerard Pons, Joan Marti, Sergi Ganau, Melcior Sentis, Reyer Zwiggelaar, Adrian K Davison, Robert Marti
Breast lesion detection using ultrasound imaging is considered an important step of Computer-Aided Diagnosis systems. Over the past decade, researchers have demonstrated the possibilities to automate the initial lesion detection. However, the lack of a common dataset impedes research when comparing the performance of such algorithms. This paper proposes the use of deep learning approaches for breast ultrasound lesion detection and investigates three different methods: a Patch-based LeNet, a U-Net, and a transfer learning approach with a pretrained FCN-AlexNet...
August 7, 2017: IEEE Journal of Biomedical and Health Informatics
https://www.readbyqxmd.com/read/28796619/unsupervised-t-distributed-video-hashing-and-its-deep-hashing-extension
#19
Yanbin Hao, Tingting Mu, John Y Goulermas, Jianguo Jiang, Richang Hong, Meng Wang
In this work, a novel unsupervised hashing algorithm, referred to as t-USMVH, and its extension to unsupervised deep hashing, referred to as t-UDH, are proposed to support large-scale video-to-video retrieval. To improve robustness of the unsupervised learning, t-USMVH combines multiple types of feature representations and effectively fuses them by examining a continuous relevance score based on a Gaussian estimation over pairwise distances, and also a discrete neighbor score based on the cardinality of reciprocal neighbors...
August 7, 2017: IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society
https://www.readbyqxmd.com/read/28796610/deep-learning-markov-random-field-for-semantic-segmentation
#20
Ziwei Liu, Xiaoxiao Li, Ping Luo, Chen Change Loy, Xiaoou Tang
Semantic segmentation tasks can be well modeled by Markov Random Field (MRF). This paper addresses semantic segmentation by incorporating high-order relations and mixture of label contexts into MRF. Unlike previous works that optimized MRFs using iterative algorithm, we solve MRF by proposing a Convolutional Neural Network (CNN), namely Deep Parsing Network (DPN), which enables deterministic end-to-end computation in a single forward pass. Specifically, DPN extends a contemporary CNN to model unary terms and additional layers are devised to approximate the mean field (MF) algorithm for pairwise terms...
August 9, 2017: IEEE Transactions on Pattern Analysis and Machine Intelligence
keyword
keyword
56842
1
2
Fetch more papers »
Fetching more papers... Fetching...
Read by QxMD. Sign in or create an account to discover new knowledge that matter to you.
Remove bar
Read by QxMD icon Read
×

Search Tips

Use Boolean operators: AND/OR

diabetic AND foot
diabetes OR diabetic

Exclude a word using the 'minus' sign

Virchow -triad

Use Parentheses

water AND (cup OR glass)

Add an asterisk (*) at end of a word to include word stems

Neuro* will search for Neurology, Neuroscientist, Neurological, and so on

Use quotes to search for an exact phrase

"primary prevention of cancer"
(heart or cardiac or cardio*) AND arrest -"American Heart Association"