keyword
MENU ▼
Read by QxMD icon Read
search

Learning efficiency

keyword
https://www.readbyqxmd.com/read/28727565/danoc-an-efficient-algorithm-and-hardware-codesign-of-deep-neural-networks-on-chip
#1
Xichuan Zhou, Shengli Li, Fang Tang, Shengdong Hu, Zhi Lin, Lei Zhang
Deep neural networks (NNs) are the state-of-the-art models for understanding the content of images and videos. However, implementing deep NNs in embedded systems is a challenging task, e.g., a typical deep belief network could exhaust gigabytes of memory and result in bandwidth and computational bottlenecks. To address this challenge, this paper presents an algorithm and hardware codesign for efficient deep neural computation. A hardware-oriented deep learning algorithm, named the deep adaptive network, is proposed to explore the sparsity of neural connections...
July 18, 2017: IEEE Transactions on Neural Networks and Learning Systems
https://www.readbyqxmd.com/read/28727547/designing-and-implementation-of-stable-sinusoidal-rough-neural-identifier
#2
Ghasem Ahmadi, Mohammad Teshnehlab
A rough neuron is defined as a pair of conventional neurons that are called the upper and lower bound neurons. In this paper, the sinusoidal rough-neural networks (SR-NNs) are used to identify the discrete dynamic nonlinear systems (DDNSs) with or without noise in series-parallel configuration. In the identification of periodic nonlinear systems, sinusoidal activation functions provide more efficient neural networks than the sigmoidal activation functions. Based on the Lyapunov stability theory, an online learning algorithm is developed to train the SR-NNs...
August 2017: IEEE Transactions on Neural Networks and Learning Systems
https://www.readbyqxmd.com/read/28727421/shallow-representation-learning-via-kernel-pca-improves-qsar-modelability
#3
Stefano E Rensi, Russ B Altman
Linear models offer a robust, flexible, and computationally efficient set of tools for modeling quantitative structure activity relationships (QSAR), but have been eclipsed in performance by non-linear methods. Support vector machines (SVMs) and neural networks are currently among the most popular and accurate QSAR methods because they learn new representations of the data that greatly improve modelability. In this work we use shallow representation learning to improve the accuracy of L1 regularized logistic regression (LASSO) and meet the performance of Tanimoto SVM...
July 20, 2017: Journal of Chemical Information and Modeling
https://www.readbyqxmd.com/read/28726751/an-adaptive-feature-learning-model-for-sequential-radar-high-resolution-range-profile-recognition
#4
Xuan Peng, Xunzhang Gao, Yifan Zhang, Xiang Li
This paper proposes a new feature learning method for the recognition of radar high resolution range profile (HRRP) sequences. HRRPs from a period of continuous changing aspect angles are jointly modeled and discriminated by a single model named the discriminative infinite restricted Boltzmann machine (Dis-iRBM). Compared with the commonly used hidden Markov model (HMM)-based recognition method for HRRP sequences, which requires efficient preprocessing of the HRRP signal, the proposed method is an end-to-end method of which the input is the raw HRRP sequence, and the output is the label of the target...
July 20, 2017: Sensors
https://www.readbyqxmd.com/read/28726438/superior-pattern-detectors-efficiently-learn-activate-apply-and-update-social-stereotypes
#5
David J Lick, Adam L Alter, Jonathan B Freeman
Superior cognitive abilities are generally associated with positive outcomes such as academic achievement and social mobility. Here, we explore the darker side of cognitive ability, highlighting robust links between pattern detection and stereotyping. Across 6 studies, we find that superior pattern detectors efficiently learn and use stereotypes about social groups. This pattern holds across explicit (Studies 1 and 2), implicit (Studies 2 and 4), and behavioral measures of stereotyping (Study 3). We also find that superior pattern detectors readily update their stereotypes when confronted with new information (Study 5), making them particularly susceptible to counterstereotype training (Study 6)...
July 20, 2017: Journal of Experimental Psychology. General
https://www.readbyqxmd.com/read/28725993/are-young-children-able-to-learn-exploratory-strategies-by-observation
#6
Francesca Foti, Domenico Martone, Stefania Orrù, Simone Montuori, Esther Imperlini, Pasqualina Buono, Laura Petrosini, Laura Mandolesi
New competencies may be learned through active experience (experiential learning or learning by doing) or observation of others' experiences (learning by observation). Observing another person performing a complex action facilitates the observer's acquisition of the same action. The present research is aimed at analyzing if the observation of specific explorative strategies adopted in a constrained environment, such as the Radial Arm Maze (RAM), could help young children to explore the maze and to build a cognitive spatial map of the explored environment...
July 20, 2017: Psychological Research
https://www.readbyqxmd.com/read/28725883/efficient-learning-of-classification-models-from-soft-label-information-by-binning-and-ranking
#7
Yanbing Xue, Milos Hauskrecht
Construction of classification models from data in practice often requires additional human effort to annotate (label) observed data instances. However, this annotation effort may often be too costly and only a limited number of data instances may be feasibly labeled. The challenge is to find methods that let us reduce the number of the labeled instances but at the same time preserve the quality of the learned models. In this paper we study the idea of learning classification from soft label information in which each instance is associated with a soft-label further refining its class label...
May 2017: Proceedings of the ... International Florida AI Research Society Conference
https://www.readbyqxmd.com/read/28725882/group-based-active-learning-of-classification-models
#8
Zhipeng Luo, Milos Hauskrecht
Learning of classification models from real-world data often requires additional human expert effort to annotate the data. However, this process can be rather costly and finding ways of reducing the human annotation effort is critical for this task. The objective of this paper is to develop and study new ways of providing human feedback for efficient learning of classification models by labeling groups of examples. Briefly, unlike traditional active learning methods that seek feedback on individual examples, we develop a new group-based active learning framework that solicits label information on groups of multiple examples...
May 2017: Proceedings of the ... International Florida AI Research Society Conference
https://www.readbyqxmd.com/read/28725022/action-video-games-improve-reading-abilities-and-visual-to-auditory-attentional-shifting-in-english-speaking-children-with-dyslexia
#9
Sandro Franceschini, Piergiorgio Trevisan, Luca Ronconi, Sara Bertoni, Susan Colmar, Kit Double, Andrea Facoetti, Simone Gori
Dyslexia is characterized by difficulties in learning to read and there is some evidence that action video games (AVG), without any direct phonological or orthographic stimulation, improve reading efficiency in Italian children with dyslexia. However, the cognitive mechanism underlying this improvement and the extent to which the benefits of AVG training would generalize to deep English orthography, remain two critical questions. During reading acquisition, children have to integrate written letters with speech sounds, rapidly shifting their attention from visual to auditory modality...
July 19, 2017: Scientific Reports
https://www.readbyqxmd.com/read/28723559/kmt2a-and-kmt2b-mediate-memory-function-by-affecting-distinct-genomic-regions
#10
Cemil Kerimoglu, M Sadman Sakib, Gaurav Jain, Eva Benito, Susanne Burkhardt, Vincenzo Capece, Lalit Kaurani, Rashi Halder, Roberto Carlos Agís-Balboa, Roman Stilling, Hendrik Urbanke, Andrea Kranz, A Francis Stewart, Andre Fischer
Kmt2a and Kmt2b are H3K4 methyltransferases of the Set1/Trithorax class. We have recently shown the importance of Kmt2b for learning and memory. Here, we report that Kmt2a is also important in memory formation. We compare the decrease in H3K4 methylation and de-regulation of gene expression in hippocampal neurons of mice with knockdown of either Kmt2a or Kmt2b. Kmt2a and Kmt2b control largely distinct genomic regions and different molecular pathways linked to neuronal plasticity. Finally, we show that the decrease in H3K4 methylation resulting from Kmt2a knockdown partially recapitulates the pattern previously reported in CK-p25 mice, a model for neurodegeneration and memory impairment...
July 18, 2017: Cell Reports
https://www.readbyqxmd.com/read/28721120/effective-learning-environments-the-process-of-creating-and-maintaining-an-online-continuing-education-tool
#11
Sharon Davies, Gianni Roberto Lorello, Kristi Downey, Zeev Friedman
Continuing medical education (CME) is an indispensable part of maintaining physicians' competency. Since attending conferences requires clinical absenteeism and is not universally available, online learning has become popular. The purpose of this study is to conduct a retrospective analysis examining the creation process of an anesthesia website for adherence to the published guidelines and, in turn, provide an illustration of developing accredited online CME. Using Kern's guide to curriculum development, our website analysis confirmed each of the six steps was met...
2017: Advances in Medical Education and Practice
https://www.readbyqxmd.com/read/28720869/rapid-bayesian-optimisation-for-synthesis-of-short-polymer-fiber-materials
#12
Cheng Li, David Rubín de Celis Leal, Santu Rana, Sunil Gupta, Alessandra Sutti, Stewart Greenhill, Teo Slezak, Murray Height, Svetha Venkatesh
The discovery of processes for the synthesis of new materials involves many decisions about process design, operation, and material properties. Experimentation is crucial but as complexity increases, exploration of variables can become impractical using traditional combinatorial approaches. We describe an iterative method which uses machine learning to optimise process development, incorporating multiple qualitative and quantitative objectives. We demonstrate the method with a novel fluid processing platform for synthesis of short polymer fibers, and show how the synthesis process can be efficiently directed to achieve material and process objectives...
July 18, 2017: Scientific Reports
https://www.readbyqxmd.com/read/28720710/application-of-response-surface-methods-to-determine-conditions-for-optimal-genomic-prediction
#13
Réka Howard, Alicia L Carriquiry, William D Beavis
An epistatic genetic architecture can have a significant impact on prediction accuracies of genomic prediction (GP) methods. Machine learning methods predict traits composed of epistatic genetic architectures more accurately than statistical methods based on additive mixed linear models. The differences between these types of GP methods suggest a diagnostic for revealing genetic architectures underlying traits of interest. In addition to genetic architecture, the performance of GP methods may be influenced by the sample size of the training population, the number of QTL, and the proportion of phenotypic variability due to genotypic variability (heritability)...
July 18, 2017: G3: Genes—Genomes—Genetics
https://www.readbyqxmd.com/read/28720168/infant-statistical-learning-ability-is-related-to-real-time-language-processing
#14
Jill Lany, Amber Shoaib, Abbie Thompson, Katharine Graf Estes
Infants are adept at learning statistical regularities in artificial language materials, suggesting that the ability to learn statistical structure may support language development. Indeed, infants who perform better on statistical learning tasks tend to be more advanced in parental reports of infants' language skills. Work with adults suggests that one way statistical learning ability affects language proficiency is by facilitating real-time language processing. Here we tested whether 15-month-olds' ability to learn sequential statistical structure in artificial language materials is related to their ability to encode and interpret native-language speech...
July 19, 2017: Journal of Child Language
https://www.readbyqxmd.com/read/28720028/growth-of-word-and-pseudoword-reading-efficiency-in-alphabetic-orthographies-impact-of-consistency
#15
Markéta Caravolas
Word and pseudoword reading are related abilities fundamental to reading development in alphabetic orthographies. They are respectively assumed to index children's orthographic representations of words, which are in turn acquired through the underlying "self-teaching mechanism" of alphabetic pseudoword decoding. Little is known about concurrent growth trajectories of these skills in the early grades among children learning different alphabetic orthographies. In the present study, between- and within-group latent growth models of word and pseudoword reading efficiency were tested on data spanning Grades 1 and 2 from learners of the inconsistent English and consistent Czech and Slovak orthographies...
July 1, 2017: Journal of Learning Disabilities
https://www.readbyqxmd.com/read/28719743/machine-learning-on-samdi-mass-spectrometry-signal-to-noise-ratio-improves-peptide-array-designs
#16
Albert Yan Xue, Lindsey C Szymczak, Milan Mrksich, Neda Bagheri
Emerging peptide array technologies are able to profile molecular activities within cell lysates. However, the structural diversity of peptides leads to inherent differences in peptide signal to noise ratios (S/N). These complex effects can lead to potentially unrepresentative signal intensities and can bias subsequent analyses. Within mass spectrometry-based peptide technologies, the relation between a peptide's amino acid sequence and S/N remains largely non-quantitative. To address this challenge, we present a method to quantify and analyze mass spectrometry S/N of two peptide arrays, and we use this analysis to portray quality of data and to design future arrays for SAMDI mass spectrometry...
July 18, 2017: Analytical Chemistry
https://www.readbyqxmd.com/read/28719206/direct-quantum-dynamics-using-grid-based-wavefunction-propagation-and-machine-learned-potential-energy-surfaces
#17
Gareth W Richings, Scott Habershon
We describe a method for performing nuclear quantum dynamics calculations using standard, grid-based algorithms, including the multi configurational time-dependent Hartree (MCTDH) method, where the potential energy surface (PES) is calculated ``on-the-fly''. The method of Gaussian process regression (GPR) is used to construct a global representation of the PES using values of the energy at points distributed in molecular configuration space during the course of the wavepacket propagation. We demonstrate this direct dynamics approach for both an analytical PES function describing 3-dimensional proton transfer dynamics in malonaldehyde, and for 2- and 6-dimensional quantum dynamics simulations of proton transfer in salicylaldimine...
July 18, 2017: Journal of Chemical Theory and Computation
https://www.readbyqxmd.com/read/28715341/an-automatic-detection-system-of-lung-nodule-based-on-multi-group-patch-based-deep-learning-network
#18
Hongyang Jiang, He Ma, Wei Qian, Mengdi Gao, Yan Li
High-efficiency lung nodule detection dramatically contributes to the risk assessment of lung cancer. It is a significant and challenging task to quickly locate the exact positions of lung nodules. Extensive work has been done by researchers around this domain for approximately two decades. However, previous computer aided detection (CADe) schemes are mostly intricate and time-consuming since they may require more image processing modules, such as the computed tomography (CT) image transformation, the lung nodule segmentation and the feature extraction, to construct a whole CADe system...
July 14, 2017: IEEE Journal of Biomedical and Health Informatics
https://www.readbyqxmd.com/read/28715326/joint-multi-leaf-segmentation-alignment-and-tracking-from-fluorescence-plant-videos
#19
Xi Yin, Xiaoming Liu, Jin Chen, David M Kramer
This paper proposes a novel framework for fluorescence plant video processing. The plant research community is interested in the leaf-level photosynthetic analysis within a plant. A prerequisite for such analysis is to segment all leaves, estimate their structures, and track them over time. We identify this as a joint multi-leaf segmentation, alignment, and tracking problem. First, leaf segmentation and alignment are applied on the last frame of a plant video to find a number of well-aligned leaf candidates...
July 17, 2017: IEEE Transactions on Pattern Analysis and Machine Intelligence
https://www.readbyqxmd.com/read/28715325/inference-based-similarity-search-in-randomized-montgomery-domains-for-privacy-preserving-biometric-identification
#20
Yi Wang, Jianwu Wan, Jun Guo, Yiu-Ming Cheung, Pong C Yuen
Similarity search is essential to many important applications and often involves searching at scale on high-dimensional data based on their similarity to a query. In biometric applications, recent vulnerability studies have shown that adversarial machine learning can compromise biometric recognition systems by exploiting the biometric similarity information. Existing methods for biometric privacy protection are in general based on pairwise matching of secured biometric templates and have inherent limitations in search efficiency and scalability...
July 14, 2017: IEEE Transactions on Pattern Analysis and Machine Intelligence
keyword
keyword
116446
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"