检索结果-内蒙古大学图书馆

Algorithmic assurance: an active approach to algorithmic testing using Bayesian optimisation 18

学校读者我要写书评

暂无评论

Algorithmic assurance: an active approach to algorithmic tes...

Proceedings of the 32nd International Conference on Neural Information Processing Systems

作者： Shivapratap Gopakumar Sunil Gupta Santu Rana Vu Nguyen Svetha Venkatesh 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.

关键词：

Graph memory networks for molecular activity prediction

学校读者我要写书评

暂无评论

arXiv 2018年

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

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 *** 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. Copyright © 2018, The Authors. All rights reserved.

关键词： Molecules

Nonparametric online machine learning with kernels 26

学校读者我要写书评

暂无评论

Nonparametric online machine learning with kernels

26th International Joint Conference on Artificial Intelligence, IJCAI 2017

作者： Nguyen, Khanh Centre for Pattern Recognition and Data Analytics Deakin University Australia

ISBN: (纸本)9780999241103

Max-margin and kernel methods are dominant approaches to solve many tasks in machine learning. However, the paramount question is how to solve model selection problem in these methods. It becomes urgent in online learning context. Grid search is a common approach, but it turns out to be highly problematic in real-world applications. Our approach is to view max-margin and kernel methods under a Bayesian setting, then use Bayesian inference tools to learn model parameters and infer hyper-parameters in principle ways for both batch and online setting.

关键词： Bayesian networks

Dual discriminator generative adversarial nets 31

学校读者我要写书评

暂无评论

Dual discriminator generative adversarial nets

31st Annual Conference on Neural Information Processing Systems, NIPS 2017

作者： Nguyen, Tu Dinh Le, Trung Vu, Hung Phung, Dinh Deakin University Centre for Pattern Recognition and Data Analytics Geelong 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. © 2017 Neural information processing systems foundation. All rights reserved.

关键词： Generative adversarial networks

Deep learning to attend to risk in ICU 2

学校读者我要写书评

暂无评论

Deep learning to attend to risk in ICU

2nd International Workshop on Knowledge Discovery in Healthcare data, KDH at IJCAI 2017

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.

关键词： Deep learning

Bayesian functional optimisation with shape prior

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Vellanki, Pratibha Rana, Santu Gupta, Sunil de Celis Leal Alessandra Sutti, David Rubin Height, Murray Venkatesh, Svetha Centre for Pattern Recognition and Data Analytics Deakin University Geelong Australia Institute for Frontier Materials GTP Research Deakin University Geelong Australia

Real world experiments are expensive, and thus it is important to reach a target in minimum number of experiments. Experimental processes often involve control variables that changes over time. Such problems can be formulated as a functional optimisation problem. We develop a novel Bayesian optimisation framework for such functional optimisation of expensive black-box processes. We represent the control function using Bernstein polynomial basis and optimise in the coefficient space. We derive the theory and practice required to dynamically adjust the order of the polynomial degree, and show how prior information about shape can be integrated. We demonstrate the effectiveness of our approach for short polymer fibre design and optimising learning rate schedules for deep networks. Copyright © 2018, The Authors. All rights reserved.

关键词： Process control

The relationship between linguistic expression and symptoms of depression, anxiety, and suicidal thoughts: A longitudinal study of blog content

学校读者我要写书评

暂无评论

arXiv 2018年

作者： O'Dea, B. Boonstra, T.W. Larsen, M.E. Nguyen, T. Venkatesh, S. Christensen, H. Black Dog Institute Faculty of Medicine University of New South Wales NSW Australia Centre for Pattern Recognition and Data Analytics Deakin University Victoria Australia

Introduction: Due to its popularity and availability, social media data may present a new way to identify individuals who are experiencing mental illness. By analysing individuals' blog content, this study aimed to investigate the associations between linguistic features and symptoms of depression, generalised anxiety, and suicidal ideation. Methods: This study utilised a longitudinal study design. Individuals who blogged were invited to participate in a study in which they completed fortnightly mental health questionnaires (PHQ-9, GAD-7) for a period of 36 weeks. Linguistic features were extracted from blog data using the LIWC tool. Bivariate and multivariate analyses were performed to investigate the correlations between the linguistic features and mental health scores between subjects. We then used the multivariate regression model to predict longitudinal changes in mood within subjects. Results: A total of 153 participants consented to taking part, with 38 participants completing the required number of questionnaires and blog posts during the study period. Between-subject analysis revealed that several linguistic features, including tentativeness and non-fluencies, were significantly associated with depression and anxiety symptoms, but not suicidal thoughts. Within-subject analysis showed no robust correlations between linguistic features and changes in mental health score. Discussion: This study provides further support for the relationship between linguistic features within social media data and individuals' symptoms of depression and anxiety. The lack of robust within-subject correlations indicate that the relationship observed at the group level may not generalise to individual changes over time. Copyright © 2018, The Authors. All rights reserved.

关键词： Blogs

KGAN: How to break the minimax game in GAN

学校读者我要写书评

暂无评论

arXiv 2017年

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

Generative Adversarial Networks (GANs) were intuitively and attractively explained under the perspective of game theory, wherein two involving parties are a discriminator and a generator. In this game, the task of the discriminator is to discriminate the real and generated (i.e., fake) data, whilst the task of the generator is to generate the fake data that maximally confuses the discriminator. In this paper, we propose a new viewpoint for GANs, which is termed as the minimizing general loss viewpoint. This viewpoint shows a connection between the general loss of a classification problem regarding a convex loss function and a f-divergence between the true and fake data distributions. Mathematically, we proposed a setting for the classification problem of the true and fake data, wherein we can prove that the general loss of this classification problem is exactly the negative f-divergence for a certain convex function f. This allows us to interpret the problem of learning the generator for dismissing the f-divergence between the true and fake data distributions as that of maximizing the general loss which is equivalent to the min-max problem in GAN if the Logistic loss is used in the classification problem. However, this viewpoint strengthens GANs in two ways. First, it allows us to employ any convex loss function for the discriminator. Second, it suggests that rather than limiting ourselves in NN-based discriminators, we can alternatively utilize other powerful families. Bearing this viewpoint, we then propose using the kernel-based family for discriminators. This family has two appealing features: I) a powerful capacity in classifying non-linear nature data and ii) being convex in the feature space. Using the convexity of this family, we can further develop Fenchel duality to equivalently transform the max-min problem to the max-max dual problem. Copyright © 2017, The Authors. All rights reserved.

关键词： Generative adversarial networks

Analogical-based bayesian optimization

学校读者我要写书评

暂无评论

arXiv 2017年

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

Some real-world problems revolve to solve the optimization problem maxx€X f (x) where f (.) is a black-box function and X might be the set of non-vectorial objects (e.g., distributions) where we can only define a symmetric and non-negative similarity score on it. This setting requires a novel view for the standard framework of Bayesian Optimization that generalizes the core insightful spirit of this framework. With this spirit, in this paper, we propose Analogical-based Bayesian Optimization that can maximize black-box function over a domain where only a similarity score can be defined. Our pathway is as follows: we first base on the geometric view of Gaussian Processes (GP) to define the concept of influence level that allows us to analytically represent predictive means and variances of GP posteriors and base on that view to enable replacing kernel similarity by a more genetic similarity score. Furthermore, we also propose two strategies to find a batch of query points that can efficiently handle high dimensional data. Copyright © 2017, The Authors. All rights reserved.

关键词： Machine learning