检索结果-内蒙古大学图书馆

24th International Conference on pattern recognition, ICPR 2018

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

ISBN: (纸本)9781538637883

Molecular activity prediction is critical in drug design. Machine learning techniques such as kernel methods and random forests have been successful for this task. These models require fixed-size feature vectors as input while the molecules are variable in size and structure. As a result, fixed-size fingerprint representation is poor in handling substructures for large molecules. Here we approach the problem through deep neural networks as they are flexible in modeling structured data such as grids, sequences and graphs. We train multiple BioAssays using a multi-task learning framework, which combines information from multiple sources to improve the performance of prediction, especially on small datasets. We propose Graph Memory Network (GraphMem), a memory-augmented neural network to model the graph structure in molecules. GraphMem consists of a recurrent controller coupled with an external memory whose cells dynamically interact and change through a multi-hop reasoning process. Applied to the molecules, the dynamic interactions enable an iterative refinement of the representation of molecular graphs with multiple bond types. GraphMem is capable of jointly training on multiple datasets by using a specific-task query fed to the controller as an input. We demonstrate the effectiveness of the proposed model for separately and jointly training on more than 100K measurements, spanning across 9 BioAssay activity tests. © 2018 IEEE.

关键词： Molecules

来源：评论

学校读者我要写书评

暂无评论

Resset: A Recurrent Model for Sequence of Sets with Applications to Electronic Medical Records

Resset: A Recurrent Model for Sequence of Sets with Applicat...

引用

2018 International Joint Conference on Neural Networks, IJCNN 2018

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

ISBN: (纸本)9781509060146

Modern healthcare is ripe for disruption by AI. A game changer would be automatic understanding the latent processes from electronic medical records, which are being collected for billions of people worldwide. However, these healthcare processes are complicated by the interaction between at least three dynamic components: The illness which involves multiple diseases, the care which involves multiple treatments, and the recording practice which is biased and erroneous. Existing methods are inadequate in capturing the dynamic structure of care. We propose Resset, an end-to-end recurrent 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. We formulate the problem as modeling sequences of sets, a novel setting that have rarely, if not, been addressed. Within Resset, the bag of diseases recorded at each clinic visit is modeled as function of sets. The same hold for the bag of treatments. The interaction between the disease bag and the treatment bag at a visit is modeled in several, one of which as residual of diseases minus the treatments. Finally, the health trajectory, which is a sequence of visits, is modeled using a recurrent neural network. We report results on over a hundred thousand hospital visits by patients suffered from two costly chronic diseases - diabetes and mental health. Resset shows promises in multiple predictive tasks such as readmission prediction, treatments recommendation and diseases progression. © 2018 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Algorithmic assurance: An Active Approach to Algorithmic Testing using Bayesian Optimisation 32

Algorithmic assurance: An Active Approach to Algorithmic Tes...

引用

32nd Conference on Neural Information Processing Systems, NeurIPS 2018

作者： Gopakumar, Shivapratap Gupta, Sunil Rana, Santu Nguyen, Vu Venkatesh, Svetha Centre for Pattern Recognition and Data Analytics Deakin University Geelong Australia

We introduce algorithmic assurance, the problem of testing whether machine learning algorithms are conforming to their intended design goal. We address this problem by proposing an efficient framework for algorithmic testing. To provide assurance, we need to efficiently discover scenarios where an algorithm decision deviates maximally from its intended gold standard. We mathematically formulate this task as an optimisation problem of an expensive, black-box function. We use an active learning approach based on Bayesian optimisation to solve this optimisation problem. We extend this framework to algorithms with vector-valued outputs by making appropriate modification in Bayesian optimisation via the EXP3 algorithm. We theoretically analyse our methods for convergence. Using two real-world applications, we demonstrate the efficiency of our methods. The significance of our problem formulation and initial solutions is that it will serve as the foundation in assuring humans about machines making complex decisions. © 2018 Curran Associates *** rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Learning graph representation via frequent subgraphs

Learning graph representation via frequent subgraphs

引用

2018 SIAM International Conference on data Mining, SDM 2018

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

We propose a novel approach to learn distributed representation for graph data. Our idea is to combine a recently introduced neural document embedding model with a traditional pattern mining technique, by treating a graph as a document and frequent subgraphs as atomic units for the embedding process. Compared to the latest graph embedding methods, our proposed method offers three key advantages: fully unsupervised learning, entire-graph embedding, and edge label leveraging. We demonstrate our method on several datasets in comparison with a comprehensive list of up-to-date stateof-the-art baselines where we show its advantages for both classification and clustering tasks. © 2018 by SIAM.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A privacy preserving bayesian optimization with high efficiency 22nd

A privacy preserving bayesian optimization with high efficie...

引用

22nd Pacific-Asia Conference on Advances in Knowledge Discovery and data Mining, PAKDD 2018

作者： Nguyen, Thanh Dai Gupta, Sunil Rana, Santu Venkatesh, Svetha Center for Pattern Recognition and Data Analytics Deakin University Waurn Ponds3216 Australia

ISBN: (纸本)9783319930398

Bayesian optimization is a powerful machine learning technique for solving experimental design problems. With its use in industrial design optimization, time and cost of industrial processes can be reduced significantly. However, often the experimenters in industries may not have the expertise of optimization techniques and may require help from third-party optimization services. This can cause privacy concerns as the optimized design of an industrial process typically needs to be kept secret to retain its competitive advantages. To this end, we propose a novel Bayesian optimization algorithm that can allow the experimenters from an industry to utilize the expertise of a third-party optimization service in privacy preserving manner. Privacy of our proposed algorithm is guaranteed under a modern privacy preserving framework called Error Preserving Privacy, especially designed to maintain high utility even under the privacy restrictions. Using several benchmark optimization problems as well as optimization problems from real-world industrial processes, we demonstrate that the optimization efficiency of our algorithm is comparable to the non-private Bayesian optimization algorithm and significantly better than its differential privacy counterpart. © Springer International Publishing AG, part of Springer Nature 2018.

关键词： Product design

来源：评论

学校读者我要写书评

暂无评论

Trans2Vec: Learning transaction embedding via items and frequent itemsets 22nd

Trans2Vec: Learning transaction embedding via items and freq...

引用

22nd Pacific-Asia Conference on Advances in Knowledge Discovery and data Mining, PAKDD 2018

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

ISBN: (纸本)9783319930398

Learning meaningful and effective representations for transaction data is a crucial prerequisite for transaction classification and clustering tasks. Traditional methods which use frequent itemsets (FIs) as features often suffer from the data sparsity and high-dimensionality problems. Several supervised methods based on discriminative FIs have been proposed to address these disadvantages, but they require transaction labels, thus rendering them inapplicable to real-world applications where labels are not given. In this paper, we propose an unsupervised method which learns low-dimensional continuous vectors for transactions based on information of both singleton items and FIs. We demonstrate the superior performance of our proposed method in classifying transactions on four datasets compared with several state-of-the-art baselines. © Springer International Publishing AG, part of Springer Nature 2018.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A novel embedding model for knowledge base completion based on convolutional neural network

A novel embedding model for knowledge base completion based ...

引用

2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018

作者： Nguyen, Dai Quoc Nguyen, Tu Dinh Nguyen, Dat Quoc Phung, Dinh Deakin University Geelong Australia Centre for Pattern Recognition and Data Analytics University of Melbourne Melbourne Australia

ISBN: (纸本)9781948087292

In this paper, we propose a novel embedding model, named ConvKB, for knowledge base completion. Our model ConvKB advances state-of-the-art models by employing a convolutional neural network, so that it can capture global relationships and transitional characteristics between entities and relations in knowledge bases. In ConvKB, each triple (head entity, relation, tail entity) is represented as a 3- column matrix where each column vector represents a triple element. This 3-column matrix is then fed to a convolution layer where multiple filters are operated on the matrix to generate different feature maps. These feature maps are then concatenated into a single feature vector representing the input triple. The feature vector is multiplied with a weight vector via a dot product to return a score. This score is then used to predict whether the triple is valid or not. Experiments show that ConvKB achieves better link prediction performance than previous state-of-the-art embedding models on two benchmark datasets WN18RR and FB15k-237. © 2018 Association for Computational Linguistics.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Rigid and non-rigid motion compensation in weight-bearing cone-beam CT of the knee using (noisy) inertial measurements

arXiv

引用

arXiv 2021年

作者： Maier, Jennifer Nitschke, Marlies Choi, Jang-Hwan Gold, Garry Fahrig, Rebecca Eskofier, Bjoern M. Maier, Andreas Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany Machine Learning and Data Analytics Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany Division of Mechanical and Biomedical Engineering Ewha Womans University Seoul Korea Republic of Department of Radiology School of Medicine Stanford University StanfordCA United States Innovation Advanced Therapies Siemens Healthcare GmbH Forchheim Germany

Involuntary subject motion is the main source of artifacts in weight-bearing cone-beam CT of the knee. To achieve image quality for clinical diagnosis, the motion needs to be compensated. We propose to use inertial measurement units (IMUs) attached to the leg for motion estimation. We perform a simulation study using real motion recorded with an optical tracking system. Three IMU-based correction approaches are evaluated, namely rigid motion correction, non-rigid 2D projection deformation and non-rigid 3D dynamic reconstruction. We present an initialization process based on the system geometry. With an IMU noise simulation, we investigate the applicability of the proposed methods in real applications. All proposed IMU-based approaches correct motion at least as good as a state-of-the-art marker-based approach. The structural similarity index and the root mean squared error between motion-free and motion corrected volumes are improved by 24-35% and 78-85%, respectively, compared with the uncorrected case. The noise analysis shows that the noise levels of commercially available IMUs need to be improved by a factor of 105 which is currently only achieved by specialized hardware not robust enough for the application. The presented study confirms the feasibility of this novel approach and defines improvements necessary for a real application. Copyright © 2021, The Authors. All rights reserved.

关键词： Motion compensation

来源：评论

学校读者我要写书评

暂无评论

Geometric enclosing networks 27

Geometric enclosing networks

引用

27th International Joint Conference on Artificial Intelligence, IJCAI 2018

作者： Le, Trung Vu, Hung Nguyen, Tu Dinh Phung, Dinh Faculty of Information Technology Monash University Australia Center for Pattern Recognition and Data Analytics Deakin University Australia

ISBN: (纸本)9780999241127

Training model to generate data has increasingly attracted research attention and become important in modern world applications. We propose in this paper a new geometry-based optimization approach to address this problem. Orthogonal to current state-of-the-art density-based approaches, most notably VAE and GAN, we present a fresh new idea that borrows the principle of minimal enclosing ball to train a generator G (z) in such a way that both training and generated data, after being mapped to the feature space, are enclosed in the same sphere. We develop theory to guarantee that the mapping is bijective so that its inverse from feature space to data space results in expressive nonlinear contours to describe the data manifold, hence ensuring data generated are also lying on the data manifold learned from training data. Our model enjoys a nice geometric interpretation, hence termed Geometric Enclosing Networks (GEN), and possesses some key advantages over its rivals, namely simple and easy-to-control optimization formulation, avoidance of mode collapsing and efficiently learn data manifold representation in a completely unsupervised manner. We conducted extensive experiments on synthesis and real-world datasets to illustrate the behaviors, strength and weakness of our proposed GEN, in particular its ability to handle multi-modal data and quality of generated data. © 2018 International Joint Conferences on Artificial Intelligence. All right reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Batch Normalized Deep Boltzmann Machines 10

Batch Normalized Deep Boltzmann Machines

引用

10th Asian Conference on Machine Learning, ACML 2018

作者： Vu, Hung Nguyen, Tu Dinh Le, Trung Luo, Wei Phung, Dinh Center for Pattern Recognition and Data Analytics Deakin University Geelong Australia Monash University ClaytonVIC3800 Australia

Training Deep Boltzmann Machines (DBMs) is a challenging task in deep generative model studies. The careless training usually leads to a divergence or a useless model. We discover that this phenomenon is due to the change of DBM layers’ input signals during model parameter updates, similar to other deterministic deep networks such as Convolutional Neural Networks (CNNs) or Recurrent Neural Networks (RNNs). The change of layers’ input distributions not only complicates the learning process but also causes redundant neurons that simply imitate the others’ behaviors. Although this phenomenon can be coped using batch normalization in deep learning, integrating this technique into the probabilistic network of DBMs is a challenging problem since it has to satisfy two conditions of energy function and conditional probabilities. In this paper, we introduce Batch Normalized Deep Boltzmann Machines (BNDBMs) that meet both aforementioned conditions and successfully combine batch normalization and DBMs into the same framework. However, unlike CNNs, due to the probabilistic nature of DBMs, training DBMs with batch normalization has some differences: i) fixing shift parameters β but learning scale parameters γ;ii) avoiding normalizing the first hidden layer and iii) maintaining multiple pairs of population means and variances per neuron rather than one pair in CNNs. We observe that our proposed BNDBMs can stabilize the input signals of network layers and facilitate the training process as well as improve the model quality. More interestingly, BNDBMs can be trained successfully without pretraining, which is usually a mandatory step in most existing DBMs. The experimental results in MNIST, Fashion-MNIST and Caltech 101 Silhouette datasets show that our BNDBMs outperform DBMs and centered DBMs in terms of feature representation and classification accuracy (3.98% and 5.84% average improvement for pretraining and no pretraining respectively). © 2018 H. Vu, T.D. Nguyen, T. Le, W. Luo &

关键词： Network layers

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：