检索结果-内蒙古大学图书馆

8th Asian Conference on Machine Learning, ACML 2016

作者： Nguyen, Vu Gupta, Sunil Rana, Santu Li, Cheng Venkatesh, Svetha Center for Pattern Recognition and Data Analytics Deakin University Australia

Many real-world applications require multi-label classification where multiple target labels are assigned to each instance. In multi-label classification, there exist the intrinsic correlations between the labels and features. These correlations are beneficial for multi-label classification task since they reflect the coexistence of the input and output spaces that can be exploited for prediction. Traditional classification methods have attempted to reveal these correlations in different ways. However, existing methods demand expensive computation complexity for finding such correlation structures. Furthermore, these approaches can not identify the suitable number of label-feature correlation patterns. In this paper, we propose a Bayesian nonparametric (BNP) framework for multi-label classification that can automatically learn and exploit the unknown number of multi-label correlation. We utilize the recent techniques in stochastic inference to derive the cheap (but efficient) posterior inference algorithm for the model. In addition, our model can naturally exploit the useful information from missing label samples. Furthermore, we extend the model to update parameters in an online fashion that highlights the flexibility of our model against the existing approaches. We compare our method with the state-of-the-art multi-label classification algorithms on real-world datasets using both complete and missing label settings. Our model achieves better classification accuracy while our running time is consistently much faster than the baselines in an order of magnitude. © 2016 V. Nguyen, S. Gupta, S. Rana, C. Li & S. Venkatesh.

关键词： Stochastic models

来源：评论

学校读者我要写书评

暂无评论

Faster training of very deep networks via p-norm gates 23

Faster training of very deep networks via p-norm gates

引用

23rd International Conference on pattern recognition, ICPR 2016

作者： Pham, Trang Tran, Truyen Phung, Dinh Venkatesh, Svetha Center for Pattern Recognition and Data Analytics Deakin University Geelong Australia

ISBN: (纸本)9781509048472

A major contributing factor to the recent advances in deep neural networks is structural units that let sensory information and gradients to propagate easily. Gating is one such structure that acts as a flow control. Gates are employed in many recent state-of-the-art recurrent models such as LSTM and GRU, and feedforward models such as Residual Nets and Highway Networks. This enables learning in very deep networks with hundred layers and helps achieve record-breaking results in vision (e.g., ImageNet with Residual Nets) and NLP (e.g., machine translation with GRU). However, there is limited work in analysing the role of gating in the learning process. In this paper, we propose a flexible p-norm gating scheme, which allows user-controllable flow and as a consequence, improve the learning speed. This scheme subsumes other existing gating schemes, including those in GRU, Highway Networks and Residual Nets as special cases. Experiments on large sequence and vector datasets demonstrate that the proposed gating scheme helps improve the learning speed significantly without extra overhead. © 2016 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Stabilizing linear prediction models using autoencoder 12th

Stabilizing linear prediction models using autoencoder

引用

12th International Conference on Advanced data Mining and Applications, ADMA 2016

作者： Gopakumar, Shivapratap Tran, Truyen Phung, Dinh Venkatesh, Svetha Center for Pattern Recognition and Data Analytics Deakin University Burwood Australia

ISBN: (纸本)9783319495859

To date, the instability of prognostic predictors in a sparse high dimensional model, which hinders their clinical adoption, has received little attention. Stable prediction is often overlooked in favour of performance. Yet, stability prevails as key when adopting models in critical areas as healthcare. Our study proposes a stabilization scheme by detecting higher order feature correlations. Using a linear model as basis for prediction, we achieve feature stability by regularizing latent correlation in features. Latent higher order correlation among features is modelled using an autoencoder network. Stability is enhanced by combining a recent technique that uses a feature graph, and augmenting external unlabelled data for training the autoencoder network. Our experiments are conducted on a heart failure cohort from an Australian hospital. Stability was measured using Consistency index for feature subsets and signal-to-noise ratio for model parameters. Our methods demonstrated significant improvement in feature stability and model estimation stability when compared to baselines. © Springer International Publishing AG 2016.

关键词： Stability

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

Graph classification via deep learning with virtual nodes

arXiv

引用

arXiv 2017年

作者： Pham, Trang Tran, Truyen Dam, Hoa Venkatesh, Svetha Centre for Pattern Recognition and Data Analytics Deakin University Geelong Australia School of Computing and Information Technology University of Wollongong Australia

Learning representation for graph classification turns a variable-size graph into a fixed-size vector (or matrix). Such a representation works nicely with algebraic manipulations. Here we introduce a simple method to augment an attributed graph with a virtual node that is bidirectionally connected to all existing nodes. The virtual node represents the latent aspects of the graph, which are not immediately available from the attributes and local connectivity structures. The expanded graph is then put through any node representation method. The representation of the virtual node is then the representation of the entire graph. In this paper, we use the recently introduced Column Network for the expanded graph, resulting in a new end-to-end graph classification model dubbed Virtual Column Network (VCN). The model is validated on two tasks: (i) predicting bioactivity of chemical compounds, and (ii) finding software vulnerability from source code. Results demonstrate that VCN is competitive against wellestablished rivals. Copyright © 2017, The Authors. All rights reserved.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Scalable Support Vector Clustering Using Budget

arXiv

引用

arXiv 2017年

作者： Pham, Tung Le, Trung Dang, Hang Faculty of Information Technology VNUHCM-University of Science Viet Nam Centre for Pattern Recognition and Data Analytics Deakin University Australia

Owing to its application in solving the difficult and diverse clustering or outlier detection problem, support-based clustering has recently drawn plenty of attention. Support-based clustering method always undergoes two phases: finding the domain of novelty and performing clustering assignment. To find the domain of novelty, the training time given by the current solvers is typically over-quadratic in the training size, and hence precluding the usage of support-based clustering method for large-scale datasets. In this paper, we propose applying Stochastic Gradient Descent (SGD) framework to the first phase of support-based clustering for finding the domain of novelty and a new strategy to perform the clustering assignment. However, the direct application of SGD to the first phase of support-based clustering is vulnerable to the curse of kernelization, that is, the model size linearly grows up with the data size accumulated overtime. To address this issue, we invoke the budget approach which allows us to restrict the model size to a small budget. Our new strategy for clustering assignment enables a fast computation by means of reducing the task of clustering assignment on the full training set to the same task on a significantly smaller set. We also provide a rigorous theoretical analysis about the convergence rate for the proposed method. Finally, we validate our proposed method on the well-known datasets for clustering to show that the proposed method offers a comparable clustering quality while simultaneously achieving significant speedup in comparison with the baselines. Copyright © 2017, The Authors. All rights reserved.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Outlier detection on mixed-type data: An energy-based approach 12th

Outlier detection on mixed-type data: An energy-based approa...

引用

12th International Conference on Advanced data Mining and Applications, ADMA 2016

作者： Do, Kien Tran, Truyen Phung, Dinh Venkatesh, Svetha Centre for Pattern Recognition and Data Analytics Deakin University Geelong Australia

ISBN: (纸本)9783319495859

Outlier detection amounts to finding data points that differ significantly from the norm. Classic outlier detection methods are largely designed for single data type such as continuous or discrete. However, real world data is increasingly heterogeneous, where a data point can have both discrete and continuous attributes. Handling mixed-type data in a disciplined way remains a great challenge. In this paper, we propose a new unsupervised outlier detection method for mixed-type data based on Mixed-variate Restricted Boltzmann Machine (***). The *** is a principled probabilistic method that models data density. We propose to use free-energy derived from *** as outlier score to detect outliers as those data points lying in low density regions. The method is fast to learn and compute, is scalable to massive datasets. At the same time, the outlier score is identical to data negative log-density up-to an additive constant. We evaluate the proposed method on synthetic and real-world datasets and demonstrate that (a) a proper handling mixed-types is necessary in outlier detection, and (b) free-energy of *** is a powerful and efficient outlier scoring method, which is highly competitive against state-of-the-arts. © Springer International Publishing AG 2016.

关键词： Free energy

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

Differentially private multi-task learning 11th

Differentially private multi-task learning

引用

11th Pacific Asia Workshop on Intelligence and Security Informatics, PAISI 2016

作者： Gupta, Sunil Kumar Rana, Santu Venkatesh, Svetha Center for Pattern Recognition and Data Analytics Deakin University Geelong3216 Australia

ISBN: (纸本)9783319318622

Privacy restrictions of sensitive data repositories imply that the data analysis is performed in isolation at each data source. A prime example is the isolated nature of building prognosis models from hospital data and the associated challenge of dealing with small number of samples in risk classes (e.g. suicide) while doing so. Pooling knowledge from other hospitals, through multi-task learning, can alleviate this problem. However, if knowledge is to be shared unrestricted, privacy is breached. Addressing this, we propose a novel multi-task learning method that preserves privacy of data under the strong guarantees of differential privacy. Further, we develop a novel attribute-wise noise addition scheme that significantly lifts the utility of the proposed method. We demonstrate the effectiveness of our method with a synthetic and two real datasets. © Springer International Publishing Switzerland 2016.

关键词： Hospitals

来源：评论

学校读者我要写书评

暂无评论

Exceptional contrast set mining: Moving beyond the deluge of the obvious 29th

引用

29th Australasian Joint Conference on Artificial Intelligence, AI 2016

作者： Nguyen, Dang Luo, Wei Phung, Dinh Venkatesh, Svetha School of Information Technology Centre for Pattern Recognition and Data Analytics Deakin University Geelong Australia

ISBN: (纸本)9783319501260

data scientists, with access to fast growing data and computing power, constantly look for algorithms with greater detection power to discover "novel" knowledge. But more often than not, their algorithms give them too many outputs that are either highly speculative or simply confirming what the domain experts already know. To escape this dilemma, we need algorithms that move beyond the obvious association analyses and leverage domain analytic objectives (aka. KPIs) to look for higher order connections. We propose a new technique Exceptional Contrast Set Mining that first gathers a succinct collection of affirmative contrast sets based on the principle of redundant information elimination. Then it discovers exceptional contrast sets that contradict the affirmative contrast sets. The algorithm has been successfully applied to several analytic consulting projects. In particular, during an analysis of a state-wide cancer registry, it discovered a surprising regional difference in breast cancer screening. © Springer International Publishing AG 2016.

关键词： Diseases

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：