检索结果-内蒙古大学图书馆

arXiv 2017年

作者： Nguyen, Tu Dinh Le, Trung Vu, Hung Phung, Dinh Centre for Pattern Recognition and Data Analytics Deakin University Australia

We propose in this paper a novel approach to tackle the problem of mode collapse encountered in generative adversarial network (GAN). Our idea is intuitive but proven to be very effective, especially in addressing some key limitations of GAN. In essence, it combines the Kullback-Leibler (KL) and reverse KL divergences into a unified objective function, thus it exploits the complementary statistical properties from these divergences to effectively diversify the estimated density in capturing multi-modes. We term our method dual discriminator generative adversarial nets (D2GAN) which, unlike GAN, has two discriminators;and together with a generator, it also has the analogy of a minimax game, wherein a discriminator rewards high scores for samples from data distribution whilst another discriminator, conversely, favoring data from the generator, and the generator produces data to fool both two discriminators. We develop theoretical analysis to show that, given the maximal discriminators, optimizing the generator of D2GAN reduces to minimizing both KL and reverse KL divergences between data distribution and the distribution induced from the data generated by the generator, hence effectively avoiding the mode collapsing problem. We conduct extensive experiments on synthetic and real-world large-scale datasets (MNIST, CIFAR-10, STL-10, ImageNet), where we have made our best effort to compare our D2GAN with the latest state-of-The-Art GAN's variants in comprehensive qualitative and quantitative evaluations. The experimental results demonstrate the competitive and superior performance of our approach in generating good quality and diverse samples over baselines, and the capability of our method to scale up to ImageNet database. Copyright © 2017, The Authors. All rights reserved.

关键词： Discriminators

来源：评论

学校读者我要写书评

暂无评论

Dirichlet Process Mixture Models with Pairwise Constraints for data Clustering

引用

Annals of data Science 2016年第2期3卷 205-223页

作者： Li, Cheng Rana, Santu Phung, Dinh Venkatesh, Svetha Centre for Pattern Recognition and Data Analytics Deakin University Geelong Australia

The Dirichlet process mixture (DPM) model, a typical Bayesian nonparametric model, can infer the number of clusters automatically, and thus performing priority in data clustering. This paper investigates the influence of pairwise constraints in the DPM model. The pairwise constraint, known as two types: must-link (ML) and cannot-link (CL) constraints, indicates the relationship between two data points. We have proposed two relevant models which incorporate pairwise constraints: the constrained DPM (C-DPM) and the constrained DPM with selected constraints (SC-DPM). In C-DPM, the concept of chunklet is introduced. ML constraints are compiled into chunklets and CL constraints exist between chunklets. We derive the Gibbs sampling of the C-DPM based on chunklets. We further propose a principled approach to select the most useful constraints, which will be incorporated into the SC-DPM. We evaluate the proposed models based on three real datasets: 20 Newsgroups dataset, NUS-WIDE image dataset and Facebook comments datasets we collected by ourselves. Our SC-DPM performs priority in data clustering. In addition, our SC-DPM can be potentially used for short-text clustering. © 2016, Springer-Verlag Berlin Heidelberg.

关键词： Mixtures

来源：评论

学校读者我要写书评

暂无评论

Deep learning to attend to risk in ICU

arXiv

引用

arXiv 2017年

作者： Nguyen, Phuoc Tran, Truyen Venkatesh, Svetha Centre for Pattern Recognition and Data Analytics Deakin University Geelong Australia

Modeling physiological time-series in ICU is of high clinical importance. However, data collected within ICU are irregular in time and often contain missing measurements. Since absence of a measure would signify its lack of importance, the missingness is indeed informative and might reflect the decision making by the clinician. Here we propose a deep learning architecture that can effectively handle these challenges for predicting ICU mortality outcomes. The model is based on Long Short-Term Memory, and has layered attention mechanisms. At the sensing layer, the model decides whether to observe and incorporate parts of the current measurements. At the reasoning layer, evidences across time steps are weighted and combined. The model is evaluated on the PhysioNet 2012 dataset showing competitive and interpretable results. Copyright © 2017, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Finding algebraic structure of care in time: A deep learning approach

arXiv

引用

arXiv 2017年

作者： Nguyen, Phuoc Tran, Truyen Venkatesh, Svetha Centre for Pattern Recognition and Data Analytics Deakin University Geelong Australia

Understanding the latent processes from Electronic Medical Records could be a game changer in modern healthcare. However, the processes are complex due to the interaction between at least three dynamic components: the illness, the care and the recording practice. Existing methods are inadequate in capturing the dynamic structure of care. We propose an end-to-end model that reads medical record and predicts future risk. The model adopts the algebraic view in that discrete medical objects are embedded into continuous vectors lying in the same space. The bag of disease and comorbidities recorded at each hospital visit are modeled as function of sets. The same holds for the bag of treatments. The interaction between diseases and treatments at a visit is modeled as the residual of the diseases minus the treatments. Finally, the health trajectory, which is a sequence of visits, is modeled using a recurrent neural network. We report preliminary results on chronic diseases - diabetes and mental health - for predicting unplanned readmission. Copyright © 2017, The Authors. All rights reserved.

关键词： Medical computing

来源：评论

学校读者我要写书评

暂无评论

Forward-Backward Smoothing for Hidden Markov Models of Point pattern data

Forward-Backward Smoothing for Hidden Markov Models of Point...

引用

International Conference on data Science and Advanced analytics (DSAA)

作者： Nhan Dam Dinh Phung Ba-Ngu Vo Viet Huynh Deakin University Centre for Pattern Recognition and Data Analytics Australia Curtin University Australia

This paper considers a discrete-time sequential latent model for point pattern data, specifically a hidden Markov model (HMM) where each observation is an instantiation of a random finite set (RFS). This so-called RFS-HMM is worthy of investigation since point pattern data are ubiquitous in artificial intelligence and data science. We address the three basic problems typically encountered in such a sequential latent model, namely likelihood computation, hidden state inference, and parameter estimation. Moreover, we develop algorithms for solving these problems including forward-backward smoothing for likelihood computation and hidden state inference, and expectation-maximisation for parameter estimation. Simulation studies are used to demonstrate key properties of RFS-HMM, whilst real data in the domain of human dynamics are used to demonstrate its applicability.

关键词： Hidden Markov models data models Radio frequency Maximum likelihood estimation Computational modeling Finite element analysis Smoothing methods

来源：评论

学校读者我要写书评

暂无评论

Dual space gradient descent for online learning 30

Dual space gradient descent for online learning

引用

30th Annual Conference on Neural Information Processing Systems, NIPS 2016

作者： Le, Trung Nguyen, Tu Dinh Nguyen, Vu Phung, Dinh Centre for Pattern Recognition and Data Analytics Deakin University Australia

One crucial goal in kernel online learning is to bound the model size. Common approaches employ budget maintenance procedures to restrict the model sizes using removal, projection, or merging strategies. Although projection and merging, in the literature, are known to be the most effective strategies, they demand extensive computation whilst removal strategy fails to retain information of the removed vectors. An alternative way to address the model size problem is to apply random features to approximate the kernel function. This allows the model to be maintained directly in the random feature space, hence effectively resolve the curse of kernelization. However, this approach still suffers from a serious shortcoming as it needs to use a high dimensional random feature space to achieve a sufficiently accurate kernel approximation. Consequently, it leads to a significant increase in the computational cost. To address all of these aforementioned challenges, we present in this paper the Dual Space Gradient Descent (DualSGD), a novel framework that utilizes random features as an auxiliary space to maintain information from data points removed during budget maintenance. Consequently, our approach permits the budget to be maintained in a simple, direct and elegant way while simultaneously mitigating the impact of the dimensionality issue on learning performance. We further provide convergence analysis and extensively conduct experiments on five real-world datasets to demonstrate the predictive performance and scalability of our proposed method in comparison with the state-of-the-art baselines. © 2016 NIPS Foundation - All Rights Reserved.

关键词： Merging

来源：评论

学校读者我要写书评

暂无评论

Stable clinical prediction using graph support vector machines 23

Stable clinical prediction using graph support vector machin...

引用

23rd International Conference on pattern recognition, ICPR 2016

作者： Kamkar, Iman Gupta, Sunil Li, Cheng Phung, Dinh Venkatesh, Svetha Centre for Pattern Recognition and Data Analytics Deakin University Australia

ISBN: (纸本)9781509048472

The stability matters in clinical prediction models because it makes the model to be interpretable and generalizable. It is paramount for high dimensional data, which employ sparse models with feature selection ability. We propose a new method to stabilize sparse support vector machines using intrinsic graph structure of the electronic medical records. The graph structure is exploited using the Jaccard similarity among features. Our method employs a convex function to penalize the pairwise l∞-norm of connected feature coefficients in the graph. We apply the alternating direction method of multipliers to solve the proposed formulation. Our experiments are conducted on a synthetic and three real-world hospital datasets. We show that our proposed method is more stable than the state-of-the-art feature selection and classification techniques in terms of three stability measures namely, Jaccard similarity measure, Spearman's rank correlation coefficient and Kuncheva index. We further show that our method has resulted in better classification performance compared to the baselines. © 2016 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

MCNC: Multi-Channel Nonparametric Clustering from heterogeneous data 23

MCNC: Multi-Channel Nonparametric Clustering from heterogene...

引用

23rd International Conference on pattern recognition, ICPR 2016

作者： Nguyen, Thanh-Binh Nguyen, Vu Venkatesh, Svetha Phung, Dinh Centre for Pattern Recognition and Data Analytics Deakin University Australia

ISBN: (纸本)9781509048472

Bayesian nonparametric (BNP) models have recently become popular due to their flexibility in identifying the unknown number of clusters. However, they have difficulties handling heterogeneous data from multiple sources. Existing BNP methods either treat each of these sources independently - hence do not get benefits from the correlating information between them, or require to explicitly specify data sources as primary and context channels. In this paper, we present a BNP framework, termed MCNC, which has the ability to (1) discover co-patterns from multiple sources;(2) explore multi-channel data simultaneously and treat them equally;(3) automatically identify a suitable number of patterns from data;and (4) handle missing data. The key idea is to utilize a richer base measure of a BNP model being a product-space. We demonstrate our framework on synthetic and real-world datasets to discover the identity-location-time (a.k.a who-where-when) patterns. The experimental results highlight the effectiveness of our MCNC framework in both cases of complete and missing data. © 2016 IEEE.

关键词： Ubiquitous computing

来源：评论

学校读者我要写书评

暂无评论

Animal recognition and Identification with Deep Convolutional Neural Networks for Automated Wildlife Monitoring

Animal Recognition and Identification with Deep Convolutiona...

引用

International Conference on data Science and Advanced analytics (DSAA)

作者： Hung Nguyen Sarah J. Maclagan Tu Dinh Nguyen Thin Nguyen Paul Flemons Kylie Andrews Euan G. Ritchie Dinh Phung Centre for Pattern Recognition and Data Analytics Deakin University Geelong VIC Australia Centre for Integrative Ecology Deakin University Burwood VIC Australia Centre for Pattern Recognition & Data Analytics Deakin University Burwood VIC Australia Australian Museum Research Institute Sydney NSW Australia ABC Radio National Australia

Efficient and reliable monitoring of wild animals in their natural habitats is essential to inform conservation and management decisions. Automatic covert cameras or "camera traps" are being an increasingly popular tool for wildlife monitoring due to their effectiveness and reliability in collecting data of wildlife unobtrusively, continuously and in large volume. However, processing such a large volume of images and videos captured from camera traps manually is extremely expensive, time-consuming and also monotonous. This presents a major obstacle to scientists and ecologists to monitor wildlife in an open environment. Leveraging on recent advances in deep learning techniques in computer vision, we propose in this paper a framework to build automated animal recognition in the wild, aiming at an automated wildlife monitoring system. In particular, we use a single-labeled dataset from Wildlife Spotter project, done by citizen scientists, and the state-of-the-art deep convolutional neural network architectures, to train a computational system capable of filtering animal images and identifying species automatically. Our experimental results achieved an accuracy at 96.6% for the task of detecting images containing animal, and 90.4% for identifying the three most common species among the set of images of wild animals taken in South-central Victoria, Australia, demonstrating the feasibility of building fully automated wildlife observation. This, in turn, can therefore speed up research findings, construct more efficient citizen sciencebased monitoring systems and subsequent management decisions, having the potential to make significant impacts to the world of ecology and trap camera images analysis.

关键词： Wildlife Cameras Monitoring Automation Australia

来源：评论

学校读者我要写书评

暂无评论

Software Abstraction for Casual Games Using Temporal Model: An Alloy-Based Approach

Software Abstraction for Casual Games Using Temporal Model: ...

引用

International Conference on Advanced Computing and Applications (ACOMP)

作者： Long-Phuoc Tôn Hoang-Anh Pham Bo Dao Faculty of Computer Science & Engineering HCMC University of Technology Vietnam Centre for Pattern Recognition and Data Analytics Deakin University Australia

Software abstraction plays an important role in both requirements engineering and software design. It facilitates the principle of separate of concerns while opening the door for software automation. This paper revisits the notion of software abstraction made for casual games where a single player accumulates her points by performing game activities under a set of rules. We propose to make software abstraction in Alloy - a lightweight, declarative language that is semantically based on first-order logic and syntactically being object-oriented. We show that casual games can be conceptually abstracted and semantically represented in Alloy. More specifically, game concepts (e.g., the main player, gold mine) are represented under Alloy signatures while game rules (e.g., game over, score upped/downed) as Alloy fact. To precisely specify game rules and make them simulatable, we need a mechanism for querying and updating the states of game concepts at different moments during the course of the game. To this end, we employ temporal modeling in making software abstraction for casual games.

关键词： Games Metals Tools Software design Object oriented modeling Requirements engineering

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：