检索结果-内蒙古大学图书馆

6th International Conference on Educational Data Mining, EDM 2013

作者： Falakmasir, Mohammad H. Pardos, Zachary A. Gordon, Geoffrey J. Brusilovsky, Peter Intelligent Systems Program University of Pittsburgh 210 South Bouquet Street PittsburghPA United States Computer Science AI Lab Massachusetts Institute of Technology 77 Massachusetts Ave CambridgeMA02139 United States Machine Learning Department Carnegie Mellon University 5000 Forbes Avenue PittsburghPA15213 United States School of Information Sciences University of Pittsburgh 135 North Bellefield Ave. PittsburghPA15260 United States

ISBN: (纸本)9780983952527

Bayesian Knowledge Tracing (BKT) is a common way of determining student knowledge of skills in adaptive educational systems and cognitive tutors. The basic BKT is a Hidden Markov Model (HMM) that models student knowledge based on five parameters: prior, learn rate, forget, guess, and slip. Expectation Maximization (EM) is often used to learn these parameters from training data. However, EM is a time-consuming process, and is prone to converging to erroneous, implausible local optima depending on the initial values of the BKT parameters. In this paper we address these two problems by using spectral learning to learn a Predictive State Representation (PSR) that represents the BKT HMM. We then use a heuristic to extract the BKT parameters from the learned PSR using basic matrix operations. The spectral learning method is based on an approximate factorization of the estimated covariance of windows from students’ sequences of correct and incorrect responses;it is fast, local-optimum-free, and statistically consistent. In the past few years, spectral techniques have been used on real-world problems involving latent variables in dynamical systems, computer vision, and natural language processing. Our results suggest that the parameters learned by the spectral algorithm can replace the parameters learned by EM;the results of our study show that the spectral algorithm can improve knowledge tracing parameter-fitting time significantly while maintaining the same prediction accuracy, or help to improve accuracy while still keeping parameter-fitting time equivalent to EM. © 2013 International Educational Data Mining Society. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Enabling dynamic network analysis through visualization in TVNViewer

引用

BMC BIOINFORMATICS 2012年第1期13卷 1-13页

作者： Curtis, Ross E. Xiang, Jing Parikh, Ankur Kinnaird, Peter Xing, Eric P. Carnegie Mellon Univ Machine Learning Dept Pittsburgh PA 15213 USA Univ Pittsburgh PhD Program Computat Biol Pittsburgh PA USA Carnegie Mellon Univ Lane Ctr Computat Biol Pittsburgh PA 15213 USA Carnegie Mellon Univ Human Comp Interact Inst Pittsburgh PA 15213 USA

Background: Many biological processes are context-dependent or temporally specific. As a result, relationships between molecular constituents evolve across time and environments. While cutting-edge machine learning techniques can recover these networks, exploring and interpreting the rewiring behavior is challenging. Information visualization shines in this type of exploratory analysis, motivating the development of TVNViewer (http://***/tvnviewer), a visualization tool for dynamic network analysis. Results: In this paper, we demonstrate visualization techniques for dynamic network analysis by using TVNViewer to analyze yeast cell cycle and breast cancer progression datasets. Conclusions: TVNViewer is a powerful new visualization tool for the analysis of biological networks that change across time or space.

关键词： Visualization Dynamic network analysis Gene expression analysis

来源：评论

学校读者我要写书评

暂无评论

Enhancing the usability and performance of structured association mapping algorithms using automation, parallelization, and visualization in the GenAMap software system

引用

BMC GENETICS 2012年第1期13卷 1-10页

作者： Curtis, Ross E. Goyal, Anuj Xing, Eric P. Carnegie Mellon Univ Language Technol Inst Pittsburgh PA 15213 USA Carnegie Mellon Univ Joint Carnegie Mellon Univ Pittsburgh PhD Program Pittsburgh PA 15213 USA Carnegie Mellon Univ Lane Ctr Computat Biol Pittsburgh PA 15213 USA Carnegie Mellon Univ Machine Learning Dept Pittsburgh PA 15213 USA

Background: Structured association mapping is proving to be a powerful strategy to find genetic polymorphisms associated with disease. However, these algorithms are often distributed as command line implementations that require expertise and effort to customize and put into practice. Because of the difficulty required to use these cutting-edge techniques, geneticists often revert to simpler, less powerful methods. Results: To make structured association mapping more accessible to geneticists, we have developed an automatic processing system called Auto-SAM. Auto-SAM enables geneticists to run structured association mapping algorithms automatically, using parallelization. Auto-SAM includes algorithms to discover gene-networks and find population structure. Auto-SAM can also run popular association mapping algorithms, in addition to five structured association mapping algorithms. Conclusions: Auto-SAM is available through GenAMap, a front-end desktop visualization tool. GenAMap and Auto-SAM are implemented in JAVA;binaries for GenAMap can be downloaded from http://***/genamap.

关键词： Lasso Association Mapping Gene Expression Measurement Processing Pipeline Association Result

来源：评论

学校读者我要写书评

暂无评论

FINDING GENOME-TRANSCRIPTOME-PHENOME ASSOCIATION WITH STRUCTURED ASSOCIATION MAPPING AND VISUALIZATION IN GENAMAP 17

FINDING GENOME-TRANSCRIPTOME-PHENOME ASSOCIATION WITH STRUCT...

引用

17th Pacific Symposium on Biocomputing (PSB)

作者： Curtis, Ross E. Yin, Junming Kinnaird, Peter Xing, Eric P. Carnegie Mellon Univ Joint Carnegie Mellon Univ Pittsburgh PhD Program Pittsburgh PA 15213 USA Carnegie Mellon Univ Lane Ctr Computat Biol Pittsburgh PA 15213 USA Carnegie Mellon Univ Human Comp Interact Inst Pittsburgh PA 15213 USA Carnegie Mellon Univ Machine Learning Dept Pittsburgh PA 15213 USA

ISBN: (纸本)9789814366496

Despite the success of genome-wide association studies in detecting novel disease variants, we are still far from a complete understanding of the mechanisms through which variants cause disease. Most of previous studies have considered only genome-phenome associations. However, the integration of transcriptome data may help further elucidate the mechanisms through which genetic mutations lead to disease and uncover potential pathways to target for treatment. We present a novel structured association mapping strategy for finding genome-transcriptome-phenome associations when SNP, gene-expression, and phenotype data are available for the same cohort. We do so via a two-step procedure where genome-transcriptome associations are identified by GFlasso, a sparse regression technique presented previously. Transcriptome-phenome associations are then found by a novel proposed method called gGFlasso, which leverages structure inherent in the genes and phenotypic traits. Due to the complex nature of three-way association results, visualization tools can aid in the discovery of causal SNPs and regulatory mechanisms affecting diseases. Using well-grounded visualization techniques, we have designed new visualizations that filter through large three-way association results to detect interesting SNPs and associated genes and traits. The two-step GFlasso-gGFlasso algorithmic approach and new visualizations are integrated into GenAMap, a visual analytics system for structured association mapping. Results on simulated datasets show that our approach has the potential to increase the sensitivity and specificity of association studies, compared to existing procedures that do not exploit the full structural information of the data. We report results from an analysis on a publically available mouse dataset, showing that identified SNP-gene-trait associations are compatible with known biology.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

DataHigh: graphical user interface for visualizing and interacting with high-dimensional neural activity

引用

JOURNAL OF NEURAL ENGINEERING 2013年第6期10卷 066012页

作者： Cowley, Benjamin R. Kaufman, Matthew T. Butler, Zachary S. Churchland, Mark M. Ryu, Stephen I. Shenoy, Krishna V. Yu, Byron M. Carnegie Mellon Univ Dept Machine Learning Pittsburgh PA 15213 USA Carnegie Mellon Univ Ctr Neural Basis Cognit Pittsburgh PA 15213 USA Stanford Univ Neurosci Program Stanford CA 94305 USA Stanford Univ Dept Elect Engn Stanford CA 94305 USA Cold Spring Harbor Lab Cold Spring Harbor NY 11724 USA Grinnell Coll Dept Elect Engn Grinnell IA 50112 USA Univ Calif Irvine Dept Comp Sci Irvine CA USA Columbia Univ Sch Med Dept Neurosci New York NY USA Palo Alto Med Fdn Dept Neurosurg Palo Alto CA USA Stanford Univ Dept Bioengn Stanford CA 94305 USA Stanford Univ Dept Neurobiol Stanford CA 94305 USA Carnegie Mellon Univ Dept Elect & Comp Engn Pittsburgh PA 15213 USA Carnegie Mellon Univ Dept Biomed Engn Pittsburgh PA 15213 USA

Objective. Analyzing and interpreting the activity of a heterogeneous population of neurons can be challenging, especially as the number of neurons, experimental trials, and experimental conditions increases. One approach is to extract a set of latent variables that succinctly captures the prominent co-fluctuation patterns across the neural population. A key problem is that the number of latent variables needed to adequately describe the population activity is often greater than 3, thereby preventing direct visualization of the latent space. By visualizing a small number of 2-d projections of the latent space or each latent variable individually, it is easy to miss salient features of the population activity. Approach. To address this limitation, we developed a Matlab graphical user interface (called DataHigh) that allows the user to quickly and smoothly navigate through a continuum of different 2-d projections of the latent space. We also implemented a suite of additional visualization tools (including playing out population activity timecourses as a movie and displaying summary statistics, such as covariance ellipses and average timecourses) and an optional tool for performing dimensionality reduction. Main results. To demonstrate the utility and versatility of DataHigh, we used it to analyze single-trial spike count and single-trial timecourse population activity recorded using a multi-electrode array, as well as trial-averaged population activity recorded using single electrodes. Significance. DataHigh was developed to fulfil a need for visualization in exploratory neural data analysis, which can provide intuition that is critical for building scientific hypotheses and models of population activity.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Feature Selection via Dependence Maximization

引用

JOURNAL OF machine learning RESEARCH 2012年 13卷 1393-1434页

作者： Song, Le Smola, Alex Gretton, Arthur Bedo, Justin Borgwardt, Karsten Georgia Inst Technol Atlanta GA 30332 USA Yahoo Res Santa Clara CA 95053 USA Gatsby Computat Neurosci Unit London WC1N 3AR England Natl ICT Australia Stat Machine Learning Program Canberra ACT 0200 Australia Max Planck Inst Machine Learning & Computat Biol Res Grp D-72076 Tubingen Germany Max Planck Inst Intelligent Syst Grp D-72076 Tubingen Germany Australian Natl Univ Canberra ACT 0200 Australia

We introduce a framework for feature selection based on dependence maximization between the selected features and the labels of an estimation problem, using the Hilbert-Schmidt Independence Criterion. The key idea is that good features should be highly dependent on the labels. Our approach leads to a greedy procedure for feature selection. We show that a number of existing feature selectors are special cases of this framework. Experiments on both artificial and real-world data show that our feature selector works well in practice.

关键词： kernel methods feature selection independence measure Hilbert-Schmidt independence criterion Hilbert space embedding of distribution

来源：评论

学校读者我要写书评

暂无评论

Empirically evaluating the application of reinforcement learning to the induction of effective and adaptive pedagogical strategies

引用

USER MODELING AND USER-ADAPTED INTERACTION 2011年第1-2期21卷 137-180页

作者： Chi, Min VanLehn, Kurt Litman, Diane Jordan, Pamela Carnegie Mellon Univ Machine Learning Dept Pittsburgh PA 15213 USA Arizona State Univ Sch Comp Informat & Decis Sci Engn Tempe AZ USA Univ Pittsburgh Dept Comp Sci Pittsburgh PA 15260 USA Univ Pittsburgh Intelligent Syst Program Pittsburgh PA 15260 USA Univ Pittsburgh Learning Res & Dev Ctr Pittsburgh PA 15260 USA

For many forms of e-learning environments, the system's behavior can be viewed as a sequential decision process wherein, at each discrete step, the system is responsible for selecting the next action to take. Pedagogical strategies are policies to decide the next system action when there are multiple ones available. In this project we present a Reinforcement learning (RL) approach for inducing effective pedagogical strategies and empirical evaluations of the induced strategies. This paper addresses the technical challenges in applying RL to Cordillera, a Natural Language Tutoring System teaching students introductory college physics. The algorithm chosen for this project is a model-based RL approach, Policy Iteration, and the training corpus for the RL approach is an exploratory corpus, which was collected by letting the system make random decisions when interacting with real students. Overall, our results show that by using a rather small training corpus, the RL-induced strategies indeed measurably improved the effectiveness of Cordillera in that the RL-induced policies improved students' learning gains significantly.

关键词： Reinforcement learning Pedagogical strategy machine learning Human learning

来源：评论

学校读者我要写书评

暂无评论

A Virtual Map to Support People Who Are Blind in Navigation Through Real Spaces

引用

JOURNAL OF SPECIAL EDUCATION TECHNOLOGY 2011年第4期26卷 41-57页

作者： Lahav, Orly Schloerb, David W. Kumar, Siddarth Srinivasan, Mandayam A. Tel Aviv Univ Sch Educ Dept Educ Math Sci & Technol Technol & Learning Program Tel Aviv Israel MIT Elect Res Lab Lab Human & Machine Hapt Cambridge MA 02139 USA

Most of the spatial information needed by sighted people to construct cognitive maps of spaces is gathered through the visual channel. Unfortunately, people who are blind lack the ability to collect the required spatial information in advance. The use of virtual reality as a learning and rehabilitation tool for people with disabilities has been on the rise in recent years. This research is based on the hypothesis that the advance supply of appropriate spatial information (perceptual and conceptual) through compensatory sensorial channels within a virtual environment may assist people who are blind in their anticipatory exploration and cognitive mapping of the unknown space. In this long-term research we developed and tested the BlindAid system that combines 3D audio with a Phantom (R) haptic interface to allow the user to explore a virtual map through a hand held stylus. The main goals of this research were to study the cognitive mapping process of people who are blind when exploring complex virtual maps and how they apply this spatial knowledge later in real space. The findings supply strong evidence that interaction with the BlindAid system by people who are blind provides a robust foundation for the participants' development of comprehensive cognitive maps of unknown real spaces.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Common genetic variants associated with cognitive performance identified using the proxy-phenotype method

引用

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA 2014年第38期111卷 13790-13794页

作者： Rietveld, Cornelius A. Esko, Tonu Davies, Gail Pers, Tune H. Turley, Patrick Benyamin, Beben Chabris, Christopher F. Emilsson, Valur Johnson, Andrew D. Lee, James J. de Leeuw, Christiaan Marioni, Riccardo E. Medland, Sarah E. Miller, Michael B. Rostapshova, Olga van der Lee, Sven J. Vinkhuyzen, Anna A. E. Amin, Najaf Conley, Dalton Derringer, Jaime van Duijn, Cornelia M. Fehrmann, Rudolf Franke, Lude Glaeser, Edward L. Hansell, Narelle K. Hayward, Caroline Iacono, William G. Ibrahim-Verbaas, Carla Jaddoe, Vincent Karjalainen, Juha Laibson, David Lichtenstein, Paul Liewald, David C. Magnusson, Patrik K. E. Martin, Nicholas G. McGue, Matt McMahon, George Pedersen, Nancy L. Pinker, Steven Porteous, David J. Posthuma, Danielle Rivadeneira, Fernando Smith, Blair H. Starr, John M. Tiemeier, Henning Timpson, Nicholas J. Trzaskowski, Maciej Uitterlinden, Andre G. Verhulst, Frank C. Ward, Mary E. Wright, Margaret J. Smith, George Davey Deary, Ian J. Johannesson, Magnus Plomin, Robert Visscher, Peter M. Benjamin, Daniel J. Cesarini, David Koellinger, Philipp D. Erasmus Univ Erasmus Sch Econ Dept Appl Econ NL-3000 DR Rotterdam Netherlands Erasmus MC Dept Epidemiol NL-3000 CA Rotterdam Netherlands Erasmus MC Dept Neurol NL-3000 CA Rotterdam Netherlands Erasmus MC Dept Internal Med NL-3000 CA Rotterdam Netherlands Erasmus MC Dept Epidemiol & Biostat Genet Epidemiol Unit NL-3000 CA Rotterdam Netherlands Erasmus MC Generat Study Grp R NL-3000 CA Rotterdam Netherlands Boston Childrens Hosp Div Genet & Endocrinol Boston MA 02115 USA Broad Inst Massachusetts Inst Technol & Harvard Program Med & Populat Genet Cambridge MA 02142 USA Harvard Univ Sch Med Dept Genet Boston MA 02115 USA Univ Tartu Estonian Genome Ctr EE-51010 Tartu Estonia Univ Edinburgh Ctr Cognit Ageing & Cognit Epidemiol Edinburgh EH8 9JZ Midlothian Scotland Univ Edinburgh Dept Psychol Edinburgh EH8 9JZ Midlothian Scotland Univ Edinburgh Alzheimer Scotland Dementia Res Ctr Edinburgh EH8 9JZ Midlothian Scotland Harvard Univ Dept Econ Cambridge MA 02138 USA Harvard Univ Dept Psychol Cambridge MA 02138 USA Univ Queensland Queensland Brain Inst Brisbane Qld 4072 Australia Union Coll Dept Psychol Schenectady NY 12308 USA Iceland Heart Assoc IS-201 Kopavogur Iceland Univ Iceland Fac Pharmaceut Sci IS-107 Reykjavik Iceland NHLBI Framingham Heart Study Framingham MA 01702 USA Univ Minnesota Dept Psychol Minneapolis MN 55455 USA Vrije Univ Amsterdam Dept Complex Trait Genet NL-1081 HV Amsterdam Netherlands Vrije Univ Amsterdam Med Ctr NL-1081 HV Amsterdam Netherlands Radboud Univ Nijmegen Fac Sci Inst Comp & Informat Sci Machine Learning Grp NL-6500 GL Nijmegen Netherlands Univ Edinburgh Ctr Genom & Expt Med Edinburgh EH4 2XU Midlothian Scotland Univ Edinburgh Inst Genet & Mol Med Human Genet Unit MRC Edinburgh EH4 2XU Midlothian Scotland QIMR Berghofer Med Res Inst Quantitat Genet Lab Brisbane Qld 4029 Australia QIMR Berghofer Med Res Inst Genet Epidemiol Lab Brisbane Qld 4029 Australia Harvard Univ Kennedy Sch Cambridge M

We identify common genetic variants associated with cognitive performance using a two-stage approach, which we call the proxy-phenotype method. First, we conduct a genome-wide association study of educational attainment in a large sample (n = 106,736), which produces a set of 69 education-associated SNPs. Second, using independent samples (n = 24,189), we measure the association of these education-associated SNPs with cognitive performance. Three SNPs (rs1487441, rs7923609, and rs2721173) are significantly associated with cognitive performance after correction for multiple hypothesis testing. In an independent sample of older Americans (n = 8,652), we also show that a polygenic score derived from the education-associated SNPs is associated with memory and absence of dementia. Convergent evidence from a set of bioinformatics analyses implicates four specific genes (KNCMA1, NRXN1, POU2F3, and SCRT). All of these genes are associated with a particular neurotransmitter pathway involved in synaptic plasticity, the main cellular mechanism for learning and memory.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GenAMap: Visualization strategies for structured association mapping

GenAMap: Visualization strategies for structured association...

引用

1st IEEE Symposium on Biological Data Visualization, BioVis 2011

作者： Curtis, Ross E. Kinnaird, Peter Xing, Eric P. Joint Carnegie Mellon-University of Pittsburgh Program for Computational Biology United States Human Computer Interaction Institute Carnegie Mellon University United States Machine Learning Department Carnegie Mellon University United States

ISBN: (纸本)9781467300025

Association mapping studies promise to link DNA mutations to gene expression data, possibly leading to innovative treatments for diseases. One challenge in large-scale association mapping studies is exploring the results of the computational analysis to find relevant and interesting associations. Although many association mapping studies find associations from a genome-wide collection of genomic data to hundreds or thousands of traits, current visualization software only allow these associations to be explored one trait at a time. The inability to explore the association of a genomic location to multiple traits hides the inherent interaction between traits in the analysis. Additionally, researchers must rely on collections of in-house scripts and multiple tools to perform an analysis, adding time and effort to find interesting associations. In this paper, we present a novel visual analytics system called GenAMap. GenAMap replaces the time-consuming analysis of large-scale association mapping studies with exploratory visualization tools that give geneticists an overview of the data and lead them to relevant information. We present the results of a preliminary evaluation that validated our basic approach. © 2011 IEEE.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：