October 17, 2019

2952 words 14 mins read

Paper Group ANR 866

Paper Group ANR 866

To Cluster, or Not to Cluster: An Analysis of Clusterability Methods. Entropy production rate as a criterion for inconsistency in decision theory. SAFE: Spectral Evolution Analysis Feature Extraction for Non-Stationary Time Series Prediction. Context-Aware Learning using Transferable Features for Classification of Breast Cancer Histology Images. Th …

To Cluster, or Not to Cluster: An Analysis of Clusterability Methods

Title To Cluster, or Not to Cluster: An Analysis of Clusterability Methods
Authors A. Adolfsson, M. Ackerman, N. C. Brownstein
Abstract Clustering is an essential data mining tool that aims to discover inherent cluster structure in data. For most applications, applying clustering is only appropriate when cluster structure is present. As such, the study of clusterability, which evaluates whether data possesses such structure, is an integral part of cluster analysis. However, methods for evaluating clusterability vary radically, making it challenging to select a suitable measure. In this paper, we perform an extensive comparison of measures of clusterability and provide guidelines that clustering users can reference to select suitable measures for their applications.
Tasks
Published 2018-08-24
URL http://arxiv.org/abs/1808.08317v1
PDF http://arxiv.org/pdf/1808.08317v1.pdf
PWC https://paperswithcode.com/paper/to-cluster-or-not-to-cluster-an-analysis-of
Repo
Framework

Entropy production rate as a criterion for inconsistency in decision theory

Title Entropy production rate as a criterion for inconsistency in decision theory
Authors Purushottam D. Dixit
Abstract Individual and group decisions are complex, often involving choosing an apt alternative from a multitude of options. Evaluating pairwise comparisons breaks down such complex decision problems into tractable ones. Pairwise comparison matrices (PCMs) are regularly used to solve multiple-criteria decision-making (MCDM) problems, for example, using Saaty’s analytic hierarchy process (AHP) framework. However, there are two significant drawbacks of using PCMs. First, humans evaluate PCMs in an inconsistent manner. Second, not all entries of a large PCM can be reliably filled by human decision makers. We address these two issues by first establishing a novel connection between PCMs and time-irreversible Markov processes. Specifically, we show that every PCM induces a family of dissipative maximum path entropy random walks (MERW) over the set of alternatives. We show that only `consistent’ PCMs correspond to detailed balanced MERWs. We identify the non-equilibrium entropy production in the induced MERWs as a metric of inconsistency of the underlying PCMs. Notably, the entropy production satisfies all of the recently laid out criteria for reasonable consistency indices. We also propose an approach to use incompletely filled PCMs in AHP. Potential future avenues are discussed as well. keywords: analytic hierarchy process, markov chains, maximum entropy |
Tasks Decision Making
Published 2018-01-05
URL http://arxiv.org/abs/1801.01733v2
PDF http://arxiv.org/pdf/1801.01733v2.pdf
PWC https://paperswithcode.com/paper/entropy-production-rate-as-a-criterion-for
Repo
Framework

SAFE: Spectral Evolution Analysis Feature Extraction for Non-Stationary Time Series Prediction

Title SAFE: Spectral Evolution Analysis Feature Extraction for Non-Stationary Time Series Prediction
Authors Arief Koesdwiady, Fakhri Karray
Abstract This paper presents a practical approach for detecting non-stationarity in time series prediction. This method is called SAFE and works by monitoring the evolution of the spectral contents of time series through a distance function. This method is designed to work in combination with state-of-the-art machine learning methods in real time by informing the online predictors to perform necessary adaptation when a non-stationarity presents. We also propose an algorithm to proportionally include some past data in the adaption process to overcome the Catastrophic Forgetting problem. To validate our hypothesis and test the effectiveness of our approach, we present comprehensive experiments in different elements of the approach involving artificial and real-world datasets. The experiments show that the proposed method is able to significantly save computational resources in term of processor or GPU cycles while maintaining high prediction performances.
Tasks Time Series, Time Series Prediction
Published 2018-03-04
URL http://arxiv.org/abs/1803.01364v2
PDF http://arxiv.org/pdf/1803.01364v2.pdf
PWC https://paperswithcode.com/paper/safe-spectral-evolution-analysis-feature
Repo
Framework

Context-Aware Learning using Transferable Features for Classification of Breast Cancer Histology Images

Title Context-Aware Learning using Transferable Features for Classification of Breast Cancer Histology Images
Authors Ruqayya Awan, Navid Alemi Koohbanani, Muhammad Shaban, Anna Lisowska, Nasir Rajpoot
Abstract Convolutional neural networks (CNNs) have been recently used for a variety of histology image analysis. However, availability of a large dataset is a major prerequisite for training a CNN which limits its use by the computational pathology community. In previous studies, CNNs have demonstrated their potential in terms of feature generalizability and transferability accompanied with better performance. Considering these traits of CNN, we propose a simple yet effective method which leverages the strengths of CNN combined with the advantages of including contextual information, particularly designed for a small dataset. Our method consists of two main steps: first it uses the activation features of CNN trained for a patch-based classification and then it trains a separate classifier using features of overlapping patches to perform image-based classification using the contextual information. The proposed framework outperformed the state-of-the-art method for breast cancer classification.
Tasks Classification Of Breast Cancer Histology Images
Published 2018-02-12
URL http://arxiv.org/abs/1803.00386v2
PDF http://arxiv.org/pdf/1803.00386v2.pdf
PWC https://paperswithcode.com/paper/context-aware-learning-using-transferable
Repo
Framework

The FLUXCOM ensemble of global land-atmosphere energy fluxes

Title The FLUXCOM ensemble of global land-atmosphere energy fluxes
Authors Martin Jung, Sujan Koirala, Ulrich Weber, Kazuhito Ichii, Fabian Gans, Gustau-Camps-Valls, Dario Papale, Christopher Schwalm, Gianluca Tramontana, Markus Reichstein
Abstract Although a key driver of Earth’s climate system, global land-atmosphere energy fluxes are poorly constrained. Here we use machine learning to merge energy flux measurements from FLUXNET eddy covariance towers with remote sensing and meteorological data to estimate net radiation, latent and sensible heat and their uncertainties. The resulting FLUXCOM database comprises 147 global gridded products in two setups: (1) 0.0833${\deg}$ resolution using MODIS remote sensing data (RS) and (2) 0.5${\deg}$ resolution using remote sensing and meteorological data (RS+METEO). Within each setup we use a full factorial design across machine learning methods, forcing datasets and energy balance closure corrections. For RS and RS+METEO setups respectively, we estimate 2001-2013 global (${\pm}$ 1 standard deviation) net radiation as 75.8${\pm}$1.4 ${W\ m^{-2}}$ and 77.6${\pm}$2 ${W\ m^{-2}}$, sensible heat as 33${\pm}$4 ${W\ m^{-2}}$ and 36${\pm}$5 ${W\ m^{-2}}$, and evapotranspiration as 75.6${\pm}$10 ${\times}$ 10$^3$ ${km^3\ yr^{-1}}$ and 76${\pm}$6 ${\times}$ 10$^3$ ${km^3\ yr^{-1}}$. FLUXCOM products are suitable to quantify global land-atmosphere interactions and benchmark land surface model simulations.
Tasks
Published 2018-12-11
URL http://arxiv.org/abs/1812.04951v1
PDF http://arxiv.org/pdf/1812.04951v1.pdf
PWC https://paperswithcode.com/paper/the-fluxcom-ensemble-of-global-land
Repo
Framework

AutoML from Service Provider’s Perspective: Multi-device, Multi-tenant Model Selection with GP-EI

Title AutoML from Service Provider’s Perspective: Multi-device, Multi-tenant Model Selection with GP-EI
Authors Chen Yu, Bojan Karlas, Jie Zhong, Ce Zhang, Ji Liu
Abstract AutoML has become a popular service that is provided by most leading cloud service providers today. In this paper, we focus on the AutoML problem from the \emph{service provider’s perspective}, motivated by the following practical consideration: When an AutoML service needs to serve {\em multiple users} with {\em multiple devices} at the same time, how can we allocate these devices to users in an efficient way? We focus on GP-EI, one of the most popular algorithms for automatic model selection and hyperparameter tuning, used by systems such as Google Vizer. The technical contribution of this paper is the first multi-device, multi-tenant algorithm for GP-EI that is aware of \emph{multiple} computation devices and multiple users sharing the same set of computation devices. Theoretically, given $N$ users and $M$ devices, we obtain a regret bound of $O((\text{\bf {MIU}}(T,K) + M)\frac{N^2}{M})$, where $\text{\bf {MIU}}(T,K)$ refers to the maximal incremental uncertainty up to time $T$ for the covariance matrix $K$. Empirically, we evaluate our algorithm on two applications of automatic model selection, and show that our algorithm significantly outperforms the strategy of serving users independently. Moreover, when multiple computation devices are available, we achieve near-linear speedup when the number of users is much larger than the number of devices.
Tasks AutoML, Model Selection
Published 2018-03-17
URL http://arxiv.org/abs/1803.06561v3
PDF http://arxiv.org/pdf/1803.06561v3.pdf
PWC https://paperswithcode.com/paper/automl-from-service-providers-perspective
Repo
Framework

Artificial Intelligent Diagnosis and Monitoring in Manufacturing

Title Artificial Intelligent Diagnosis and Monitoring in Manufacturing
Authors Ye Yuan, Guijun Ma, Cheng Cheng, Beitong Zhou, Huan Zhao, Hai-Tao Zhang, Han Ding
Abstract The manufacturing sector is heavily influenced by artificial intelligence-based technologies with the extraordinary increases in computational power and data volumes. It has been reported that 35% of US manufacturers are currently collecting data from sensors for manufacturing processes enhancement. Nevertheless, many are still struggling to achieve the ‘Industry 4.0’, which aims to achieve nearly 50% reduction in maintenance cost and total machine downtime by proper health management. For increasing productivity and reducing operating costs, a central challenge lies in the detection of faults or wearing parts in machining operations. Here we propose a data-driven, end-to-end framework for monitoring of manufacturing systems. This framework, derived from deep learning techniques, evaluates fused sensory measurements to detect and even predict faults and wearing conditions. This work exploits the predictive power of deep learning to extract hidden degradation features from noisy data. We demonstrate the proposed framework on several representative experimental manufacturing datasets drawn from a wide variety of applications, ranging from mechanical to electrical systems. Results reveal that the framework performs well in all benchmark applications examined and can be applied in diverse contexts, indicating its potential for use as a critical corner stone in smart manufacturing.
Tasks
Published 2018-12-17
URL http://arxiv.org/abs/1901.02057v1
PDF http://arxiv.org/pdf/1901.02057v1.pdf
PWC https://paperswithcode.com/paper/artificial-intelligent-diagnosis-and
Repo
Framework

Primitive Fitting Using Deep Boundary Aware Geometric Segmentation

Title Primitive Fitting Using Deep Boundary Aware Geometric Segmentation
Authors Duanshun Li, Chen Feng
Abstract To identify and fit geometric primitives (e.g., planes, spheres, cylinders, cones) in a noisy point cloud is a challenging yet beneficial task for fields such as robotics and reverse engineering. As a multi-model multi-instance fitting problem, it has been tackled with different approaches including RANSAC, which however often fit inferior models in practice with noisy inputs of cluttered scenes. Inspired by the corresponding human recognition process, and benefiting from the recent advancements in image semantic segmentation using deep neural networks, we propose BAGSFit as a new framework addressing this problem. Firstly, through a fully convolutional neural network, the input point cloud is point-wisely segmented into multiple classes divided by jointly detected instance boundaries without any geometric fitting. Thus, segments can serve as primitive hypotheses with a probability estimation of associating primitive classes. Finally, all hypotheses are sent through a geometric verification to correct any misclassification by fitting primitives respectively. We performed training using simulated range images and tested it with both simulated and real-world point clouds. Quantitative and qualitative experiments demonstrated the superiority of BAGSFit.
Tasks Semantic Segmentation
Published 2018-10-03
URL http://arxiv.org/abs/1810.01604v1
PDF http://arxiv.org/pdf/1810.01604v1.pdf
PWC https://paperswithcode.com/paper/primitive-fitting-using-deep-boundary-aware
Repo
Framework

Reference-Conditioned Super-Resolution by Neural Texture Transfer

Title Reference-Conditioned Super-Resolution by Neural Texture Transfer
Authors Zhifei Zhang, Zhaowen Wang, Zhe Lin, Hairong Qi
Abstract With the recent advancement in deep learning, we have witnessed a great progress in single image super-resolution. However, due to the significant information loss of the image downscaling process, it has become extremely challenging to further advance the state-of-the-art, especially for large upscaling factors. This paper explores a new research direction in super resolution, called reference-conditioned super-resolution, in which a reference image containing desired high-resolution texture details is provided besides the low-resolution image. We focus on transferring the high-resolution texture from reference images to the super-resolution process without the constraint of content similarity between reference and target images, which is a key difference from previous example-based methods. Inspired by recent work on image stylization, we address the problem via neural texture transfer. We design an end-to-end trainable deep model which generates detail enriched results by adaptively fusing the content from the low-resolution image with the texture patterns from the reference image. We create a benchmark dataset for the general research of reference-based super-resolution, which contains reference images paired with low-resolution inputs with varying degrees of similarity. Both objective and subjective evaluations demonstrate the great potential of using reference images as well as the superiority of our results over other state-of-the-art methods.
Tasks Image Stylization, Image Super-Resolution, Super-Resolution
Published 2018-04-10
URL http://arxiv.org/abs/1804.03360v1
PDF http://arxiv.org/pdf/1804.03360v1.pdf
PWC https://paperswithcode.com/paper/reference-conditioned-super-resolution-by
Repo
Framework

Predictive Uncertainty through Quantization

Title Predictive Uncertainty through Quantization
Authors Bastiaan S. Veeling, Rianne van den Berg, Max Welling
Abstract High-risk domains require reliable confidence estimates from predictive models. Deep latent variable models provide these, but suffer from the rigid variational distributions used for tractable inference, which err on the side of overconfidence. We propose Stochastic Quantized Activation Distributions (SQUAD), which imposes a flexible yet tractable distribution over discretized latent variables. The proposed method is scalable, self-normalizing and sample efficient. We demonstrate that the model fully utilizes the flexible distribution, learns interesting non-linearities, and provides predictive uncertainty of competitive quality.
Tasks Latent Variable Models, Quantization
Published 2018-10-12
URL http://arxiv.org/abs/1810.05500v1
PDF http://arxiv.org/pdf/1810.05500v1.pdf
PWC https://paperswithcode.com/paper/predictive-uncertainty-through-quantization
Repo
Framework
Title Effective Building Block Design for Deep Convolutional Neural Networks using Search
Authors Jayanta K Dutta, Jiayi Liu, Unmesh Kurup, Mohak Shah
Abstract Deep learning has shown promising results on many machine learning tasks but DL models are often complex networks with large number of neurons and layers, and recently, complex layer structures known as building blocks. Finding the best deep model requires a combination of finding both the right architecture and the correct set of parameters appropriate for that architecture. In addition, this complexity (in terms of layer types, number of neurons, and number of layers) also present problems with generalization since larger networks are easier to overfit to the data. In this paper, we propose a search framework for finding effective architectural building blocks for convolutional neural networks (CNN). Our approach is much faster at finding models that are close to state-of-the-art in performance. In addition, the models discovered by our approach are also smaller than models discovered by similar techniques. We achieve these twin advantages by designing our search space in such a way that it searches over a reduced set of state-of-the-art building blocks for CNNs including residual block, inception block, inception-residual block, ResNeXt block and many others. We apply this technique to generate models for multiple image datasets and show that these models achieve performance comparable to state-of-the-art (and even surpassing the state-of-the-art in one case). We also show that learned models are transferable between datasets.
Tasks
Published 2018-01-25
URL http://arxiv.org/abs/1801.08577v1
PDF http://arxiv.org/pdf/1801.08577v1.pdf
PWC https://paperswithcode.com/paper/effective-building-block-design-for-deep
Repo
Framework

Bi-Directional Differentiable Input Reconstruction for Low-Resource Neural Machine Translation

Title Bi-Directional Differentiable Input Reconstruction for Low-Resource Neural Machine Translation
Authors Xing Niu, Weijia Xu, Marine Carpuat
Abstract We aim to better exploit the limited amounts of parallel text available in low-resource settings by introducing a differentiable reconstruction loss for neural machine translation (NMT). This loss compares original inputs to reconstructed inputs, obtained by back-translating translation hypotheses into the input language. We leverage differentiable sampling and bi-directional NMT to train models end-to-end, without introducing additional parameters. This approach achieves small but consistent BLEU improvements on four language pairs in both translation directions, and outperforms an alternative differentiable reconstruction strategy based on hidden states.
Tasks Low-Resource Neural Machine Translation, Machine Translation
Published 2018-11-02
URL http://arxiv.org/abs/1811.01116v2
PDF http://arxiv.org/pdf/1811.01116v2.pdf
PWC https://paperswithcode.com/paper/bi-directional-differentiable-input
Repo
Framework

End-to-End Content and Plan Selection for Data-to-Text Generation

Title End-to-End Content and Plan Selection for Data-to-Text Generation
Authors Sebastian Gehrmann, Falcon Z. Dai, Henry Elder, Alexander M. Rush
Abstract Learning to generate fluent natural language from structured data with neural networks has become an common approach for NLG. This problem can be challenging when the form of the structured data varies between examples. This paper presents a survey of several extensions to sequence-to-sequence models to account for the latent content selection process, particularly variants of copy attention and coverage decoding. We further propose a training method based on diverse ensembling to encourage models to learn distinct sentence templates during training. An empirical evaluation of these techniques shows an increase in the quality of generated text across five automated metrics, as well as human evaluation.
Tasks Data-to-Text Generation, Text Generation
Published 2018-10-10
URL http://arxiv.org/abs/1810.04700v1
PDF http://arxiv.org/pdf/1810.04700v1.pdf
PWC https://paperswithcode.com/paper/end-to-end-content-and-plan-selection-for
Repo
Framework

Broad Learning for Healthcare

Title Broad Learning for Healthcare
Authors Bokai Cao
Abstract A broad spectrum of data from different modalities are generated in the healthcare domain every day, including scalar data (e.g., clinical measures collected at hospitals), tensor data (e.g., neuroimages analyzed by research institutes), graph data (e.g., brain connectivity networks), and sequence data (e.g., digital footprints recorded on smart sensors). Capability for modeling information from these heterogeneous data sources is potentially transformative for investigating disease mechanisms and for informing therapeutic interventions. Our works in this thesis attempt to facilitate healthcare applications in the setting of broad learning which focuses on fusing heterogeneous data sources for a variety of synergistic knowledge discovery and machine learning tasks. We are generally interested in computer-aided diagnosis, precision medicine, and mobile health by creating accurate user profiles which include important biomarkers, brain connectivity patterns, and latent representations. In particular, our works involve four different data mining problems with application to the healthcare domain: multi-view feature selection, subgraph pattern mining, brain network embedding, and multi-view sequence prediction.
Tasks Feature Selection, Network Embedding
Published 2018-03-23
URL http://arxiv.org/abs/1803.08978v1
PDF http://arxiv.org/pdf/1803.08978v1.pdf
PWC https://paperswithcode.com/paper/broad-learning-for-healthcare
Repo
Framework

Unpaired Image Captioning by Language Pivoting

Title Unpaired Image Captioning by Language Pivoting
Authors Jiuxiang Gu, Shafiq Joty, Jianfei Cai, Gang Wang
Abstract Image captioning is a multimodal task involving computer vision and natural language processing, where the goal is to learn a mapping from the image to its natural language description. In general, the mapping function is learned from a training set of image-caption pairs. However, for some language, large scale image-caption paired corpus might not be available. We present an approach to this unpaired image captioning problem by language pivoting. Our method can effectively capture the characteristics of an image captioner from the pivot language (Chinese) and align it to the target language (English) using another pivot-target (Chinese-English) sentence parallel corpus. We evaluate our method on two image-to-English benchmark datasets: MSCOCO and Flickr30K. Quantitative comparisons against several baseline approaches demonstrate the effectiveness of our method.
Tasks Image Captioning
Published 2018-03-14
URL http://arxiv.org/abs/1803.05526v2
PDF http://arxiv.org/pdf/1803.05526v2.pdf
PWC https://paperswithcode.com/paper/unpaired-image-captioning-by-language
Repo
Framework
comments powered by Disqus