October 17, 2019

2682 words 13 mins read

Paper Group ANR 687

Paper Group ANR 687

Feedforward Neural Network for Time Series Anomaly Detection. A randomized gradient-free attack on ReLU networks. A General Family of Robust Stochastic Operators for Reinforcement Learning. Action Quality Assessment Across Multiple Actions. A Learning-Based Framework for Line-Spectra Super-resolution. Answering Hindsight Queries with Lifted Dynamic …

Feedforward Neural Network for Time Series Anomaly Detection

Title Feedforward Neural Network for Time Series Anomaly Detection
Authors Zhang Rong, Dong Shandong, Nie Xin, Xiao Shiguang
Abstract Time series anomaly detection is usually formulated as finding outlier data points relative to some usual data, which is also an important problem in industry and academia. To ensure systems working stably, internet companies, banks and other companies need to monitor time series, which is called KPI (Key Performance Indicators), such as CPU used, number of orders, number of online users and so on. However, millions of time series have several shapes (e.g. seasonal KPIs, KPIs of timed tasks and KPIs of CPU used), so that it is very difficult to use a simple statistical model to detect anomaly for all kinds of time series. Although some anomaly detectors have developed many years and some supervised models are also available in this field, we find many methods have their own disadvantages. In this paper, we present our system, which is based on deep feedforward neural network and detect anomaly points of time series. The main difference between our system and other systems based on supervised models is that we do not need feature engineering of time series to train deep feedforward neural network in our system, which is essentially an end-to-end system.
Tasks Anomaly Detection, Feature Engineering, Time Series
Published 2018-12-20
URL http://arxiv.org/abs/1812.08389v2
PDF http://arxiv.org/pdf/1812.08389v2.pdf
PWC https://paperswithcode.com/paper/feedforward-neural-network-for-time-series
Repo
Framework

A randomized gradient-free attack on ReLU networks

Title A randomized gradient-free attack on ReLU networks
Authors Francesco Croce, Matthias Hein
Abstract It has recently been shown that neural networks but also other classifiers are vulnerable to so called adversarial attacks e.g. in object recognition an almost non-perceivable change of the image changes the decision of the classifier. Relatively fast heuristics have been proposed to produce these adversarial inputs but the problem of finding the optimal adversarial input, that is with the minimal change of the input, is NP-hard. While methods based on mixed-integer optimization which find the optimal adversarial input have been developed, they do not scale to large networks. Currently, the attack scheme proposed by Carlini and Wagner is considered to produce the best adversarial inputs. In this paper we propose a new attack scheme for the class of ReLU networks based on a direct optimization on the resulting linear regions. In our experimental validation we improve in all except one experiment out of 18 over the Carlini-Wagner attack with a relative improvement of up to 9%. As our approach is based on the geometrical structure of ReLU networks, it is less susceptible to defences targeting their functional properties.
Tasks Object Recognition
Published 2018-11-28
URL http://arxiv.org/abs/1811.11493v1
PDF http://arxiv.org/pdf/1811.11493v1.pdf
PWC https://paperswithcode.com/paper/a-randomized-gradient-free-attack-on-relu
Repo
Framework

A General Family of Robust Stochastic Operators for Reinforcement Learning

Title A General Family of Robust Stochastic Operators for Reinforcement Learning
Authors Yingdong Lu, Mark S. Squillante, Chai Wah Wu
Abstract We consider a new family of operators for reinforcement learning with the goal of alleviating the negative effects and becoming more robust to approximation or estimation errors. Various theoretical results are established, which include showing on a sample path basis that our family of operators preserve optimality and increase the action gap. Our empirical results illustrate the strong benefits of our family of operators, significantly outperforming the classical Bellman operator and recently proposed operators.
Tasks
Published 2018-05-21
URL https://arxiv.org/abs/1805.08122v2
PDF https://arxiv.org/pdf/1805.08122v2.pdf
PWC https://paperswithcode.com/paper/a-general-family-of-robust-stochastic
Repo
Framework

Action Quality Assessment Across Multiple Actions

Title Action Quality Assessment Across Multiple Actions
Authors Paritosh Parmar, Brendan Tran Morris
Abstract Can learning to measure the quality of an action help in measuring the quality of other actions? If so, can consolidated samples from multiple actions help improve the performance of current approaches? In this paper, we carry out experiments to see if knowledge transfer is possible in the action quality assessment (AQA) setting. Experiments are carried out on our newly released AQA dataset (http://rtis.oit.unlv.edu/datasets.html) consisting of 1106 action samples from seven actions with quality scores as measured by expert human judges. Our experimental results show that there is utility in learning a single model across multiple actions.
Tasks Transfer Learning
Published 2018-12-15
URL http://arxiv.org/abs/1812.06367v2
PDF http://arxiv.org/pdf/1812.06367v2.pdf
PWC https://paperswithcode.com/paper/action-quality-assessment-across-multiple
Repo
Framework

A Learning-Based Framework for Line-Spectra Super-resolution

Title A Learning-Based Framework for Line-Spectra Super-resolution
Authors Gautier Izacard, Brett Bernstein, Carlos Fernandez-Granda
Abstract We propose a learning-based approach for estimating the spectrum of a multisinusoidal signal from a finite number of samples. A neural-network is trained to approximate the spectra of such signals on simulated data. The proposed methodology is very flexible: adapting to different signal and noise models only requires modifying the training data accordingly. Numerical experiments show that the approach performs competitively with classical methods designed for additive Gaussian noise at a range of noise levels, and is also effective in the presence of impulsive noise.
Tasks Super-Resolution
Published 2018-11-14
URL https://arxiv.org/abs/1811.05844v2
PDF https://arxiv.org/pdf/1811.05844v2.pdf
PWC https://paperswithcode.com/paper/a-learning-based-framework-for-line-spectra
Repo
Framework

Answering Hindsight Queries with Lifted Dynamic Junction Trees

Title Answering Hindsight Queries with Lifted Dynamic Junction Trees
Authors Marcel Gehrke, Tanya Braun, Ralf Möller
Abstract The lifted dynamic junction tree algorithm (LDJT) efficiently answers filtering and prediction queries for probabilistic relational temporal models by building and then reusing a first-order cluster representation of a knowledge base for multiple queries and time steps. We extend LDJT to (i) solve the smoothing inference problem to answer hindsight queries by introducing an efficient backward pass and (ii) discuss different options to instantiate a first-order cluster representation during a backward pass. Further, our relational forward backward algorithm makes hindsight queries to the very beginning feasible. LDJT answers multiple temporal queries faster than the static lifted junction tree algorithm on an unrolled model, which performs smoothing during message passing.
Tasks
Published 2018-07-02
URL http://arxiv.org/abs/1807.01586v1
PDF http://arxiv.org/pdf/1807.01586v1.pdf
PWC https://paperswithcode.com/paper/answering-hindsight-queries-with-lifted
Repo
Framework

Soft Concept Analysis

Title Soft Concept Analysis
Authors Robert E. Kent
Abstract In this chapter we discuss soft concept analysis, a study which identifies an enriched notion of “conceptual scale” as developed in formal concept analysis with an enriched notion of “linguistic variable” as discussed in fuzzy logic. The identification “enriched conceptual scale” = “enriched linguistic variable” was made in a previous paper (Enriched interpretation, Robert E. Kent). In this chapter we offer further arguments for the importance of this identification by discussing the philosophy, spirit, and practical application of conceptual scaling to the discovery, conceptual analysis, interpretation, and categorization of networked information resources. We argue that a linguistic variable, which has been defined at just the right generalization of valuated categories, provides a natural definition for the process of soft conceptual scaling. This enrichment using valuated categories models the relation of indiscernability, a notion of central importance in rough set theory. At a more fundamental level for soft concept analysis, it also models the derivation of formal concepts, a process of central importance in formal concept analysis. Soft concept analysis is synonymous with enriched concept analysis. From one viewpoint, the study of soft concept analysis that is initiated here extends formal concept analysis to soft computational structures. From another viewpoint, soft concept analysis provides a natural foundation for soft computation by unifying and explaining notions from soft computation in terms of suitably generalized notions from formal concept analysis, rough set theory and fuzzy set theory.
Tasks
Published 2018-10-21
URL http://arxiv.org/abs/1810.09036v1
PDF http://arxiv.org/pdf/1810.09036v1.pdf
PWC https://paperswithcode.com/paper/soft-concept-analysis
Repo
Framework

Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Data

Title Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Data
Authors Aayush Prakash, Shaad Boochoon, Mark Brophy, David Acuna, Eric Cameracci, Gavriel State, Omer Shapira, Stan Birchfield
Abstract We present structured domain randomization (SDR), a variant of domain randomization (DR) that takes into account the structure and context of the scene. In contrast to DR, which places objects and distractors randomly according to a uniform probability distribution, SDR places objects and distractors randomly according to probability distributions that arise from the specific problem at hand. In this manner, SDR-generated imagery enables the neural network to take the context around an object into consideration during detection. We demonstrate the power of SDR for the problem of 2D bounding box car detection, achieving competitive results on real data after training only on synthetic data. On the KITTI easy, moderate, and hard tasks, we show that SDR outperforms other approaches to generating synthetic data (VKITTI, Sim 200k, or DR), as well as real data collected in a different domain (BDD100K). Moreover, synthetic SDR data combined with real KITTI data outperforms real KITTI data alone.
Tasks
Published 2018-10-23
URL http://arxiv.org/abs/1810.10093v1
PDF http://arxiv.org/pdf/1810.10093v1.pdf
PWC https://paperswithcode.com/paper/structured-domain-randomization-bridging-the
Repo
Framework

Natural Language Generation for Electronic Health Records

Title Natural Language Generation for Electronic Health Records
Authors Scott Lee
Abstract A variety of methods existing for generating synthetic electronic health records (EHRs), but they are not capable of generating unstructured text, like emergency department (ED) chief complaints, history of present illness or progress notes. Here, we use the encoder-decoder model, a deep learning algorithm that features in many contemporary machine translation systems, to generate synthetic chief complaints from discrete variables in EHRs, like age group, gender, and discharge diagnosis. After being trained end-to-end on authentic records, the model can generate realistic chief complaint text that preserves much of the epidemiological information in the original data. As a side effect of the model’s optimization goal, these synthetic chief complaints are also free of relatively uncommon abbreviation and misspellings, and they include none of the personally-identifiable information (PII) that was in the training data, suggesting it may be used to support the de-identification of text in EHRs. When combined with algorithms like generative adversarial networks (GANs), our model could be used to generate fully-synthetic EHRs, facilitating data sharing between healthcare providers and researchers and improving our ability to develop machine learning methods tailored to the information in healthcare data.
Tasks Machine Translation, Text Generation
Published 2018-06-01
URL http://arxiv.org/abs/1806.01353v1
PDF http://arxiv.org/pdf/1806.01353v1.pdf
PWC https://paperswithcode.com/paper/natural-language-generation-for-electronic
Repo
Framework

Applying Distributional Compositional Categorical Models of Meaning to Language Translation

Title Applying Distributional Compositional Categorical Models of Meaning to Language Translation
Authors Brian Tyrrell
Abstract The aim of this paper is twofold: first we will use vector space distributional compositional categorical models of meaning to compare the meaning of sentences in Irish and in English (and thus ascertain when a sentence is the translation of another sentence) using the cosine similarity score. Then we shall outline a procedure which translates nouns by understanding their context, using a conceptual space model of cognition. We shall use metrics on the category ConvexRel to determine the distance between concepts (and determine when a noun is the translation of another noun). This paper will focus on applications to Irish, a member of the Gaelic family of languages.
Tasks
Published 2018-11-08
URL http://arxiv.org/abs/1811.03274v1
PDF http://arxiv.org/pdf/1811.03274v1.pdf
PWC https://paperswithcode.com/paper/applying-distributional-compositional
Repo
Framework

Specificity measures and reference

Title Specificity measures and reference
Authors Albert Gatt, Nicolás Marín, Gustavo Rivas-Gervilla, Daniel Sánchez
Abstract In this paper we study empirically the validity of measures of referential success for referring expressions involving gradual properties. More specifically, we study the ability of several measures of referential success to predict the success of a user in choosing the right object, given a referring expression. Experimental results indicate that certain fuzzy measures of success are able to predict human accuracy in reference resolution. Such measures are therefore suitable for the estimation of the success or otherwise of a referring expression produced by a generation algorithm, especially in case the properties in a domain cannot be assumed to have crisp denotations.
Tasks
Published 2018-09-30
URL http://arxiv.org/abs/1810.00333v1
PDF http://arxiv.org/pdf/1810.00333v1.pdf
PWC https://paperswithcode.com/paper/specificity-measures-and-reference
Repo
Framework

Seeing Colors: Learning Semantic Text Encoding for Classification

Title Seeing Colors: Learning Semantic Text Encoding for Classification
Authors Shah Nawaz, Alessandro Calefati, Muhammad Kamran Janjua, Ignazio Gallo
Abstract The question we answer with this work is: can we convert a text document into an image to exploit best image classification models to classify documents? To answer this question we present a novel text classification method which converts a text document into an encoded image, using word embedding and capabilities of Convolutional Neural Networks (CNNs), successfully employed in image classification. We evaluate our approach by obtaining promising results on some well-known benchmark datasets for text classification. This work allows the application of many of the advanced CNN architectures developed for Computer Vision to Natural Language Processing. We test the proposed approach on a multi-modal dataset, proving that it is possible to use a single deep model to represent text and image in the same feature space.
Tasks Image Classification, Text Classification
Published 2018-08-31
URL http://arxiv.org/abs/1808.10822v1
PDF http://arxiv.org/pdf/1808.10822v1.pdf
PWC https://paperswithcode.com/paper/seeing-colors-learning-semantic-text-encoding
Repo
Framework

How clever is the FiLM model, and how clever can it be?

Title How clever is the FiLM model, and how clever can it be?
Authors Alexander Kuhnle, Huiyuan Xie, Ann Copestake
Abstract The FiLM model achieves close-to-perfect performance on the diagnostic CLEVR dataset and is distinguished from other such models by having a comparatively simple and easily transferable architecture. In this paper, we investigate in more detail the ability of FiLM to learn various linguistic constructions. Our main results show that (a) FiLM is not able to learn relational statements straight away except for very simple instances, (b) training on a broader set of instances as well as pretraining on simpler instance types can help alleviate these learning difficulties, (c) mixing is less robust than pretraining and very sensitive to the compositional structure of the dataset. Overall, our results suggest that the approach of big all-encompassing datasets and the paradigm of “the effectiveness of data” may have fundamental limitations.
Tasks
Published 2018-09-09
URL http://arxiv.org/abs/1809.03044v1
PDF http://arxiv.org/pdf/1809.03044v1.pdf
PWC https://paperswithcode.com/paper/how-clever-is-the-film-model-and-how-clever
Repo
Framework

Firearms and Tigers are Dangerous, Kitchen Knives and Zebras are Not: Testing whether Word Embeddings Can Tell

Title Firearms and Tigers are Dangerous, Kitchen Knives and Zebras are Not: Testing whether Word Embeddings Can Tell
Authors Pia Sommerauer, Antske Fokkens
Abstract This paper presents an approach for investigating the nature of semantic information captured by word embeddings. We propose a method that extends an existing human-elicited semantic property dataset with gold negative examples using crowd judgments. Our experimental approach tests the ability of supervised classifiers to identify semantic features in word embedding vectors and com- pares this to a feature-identification method based on full vector cosine similarity. The idea behind this method is that properties identified by classifiers, but not through full vector comparison are captured by embeddings. Properties that cannot be identified by either method are not. Our results provide an initial indication that semantic properties relevant for the way entities interact (e.g. dangerous) are captured, while perceptual information (e.g. colors) is not represented. We conclude that, though preliminary, these results show that our method is suitable for identifying which properties are captured by embeddings.
Tasks Word Embeddings
Published 2018-09-05
URL http://arxiv.org/abs/1809.01375v1
PDF http://arxiv.org/pdf/1809.01375v1.pdf
PWC https://paperswithcode.com/paper/firearms-and-tigers-are-dangerous-kitchen
Repo
Framework

Peeking the Impact of Points of Interests on Didi

Title Peeking the Impact of Points of Interests on Didi
Authors Yonghong Tian, Zeyu Li, Zhiwei Xu, Xuying Meng, Bing Zheng
Abstract Recently, the online car-hailing service, Didi, has emerged as a leader in the sharing economy. Used by passengers and drivers extensive, it becomes increasingly important for the car-hailing service providers to minimize the waiting time of passengers and optimize the vehicle utilization, thus to improve the overall user experience. Therefore, the supply-demand estimation is an indispensable ingredient of an efficient online car-hailing service. To improve the accuracy of the estimation results, we analyze the implicit relationships between the points of Interest (POI) and the supply-demand gap in this paper. The different categories of POIs have positive or negative effects on the estimation, we propose a POI selection scheme and incorporate it into XGBoost [1] to achieve more accurate estimation results. Our experiment demonstrates our method provides more accurate estimation results and more stable estimation results than the existing methods.
Tasks
Published 2018-04-06
URL http://arxiv.org/abs/1804.04176v1
PDF http://arxiv.org/pdf/1804.04176v1.pdf
PWC https://paperswithcode.com/paper/peeking-the-impact-of-points-of-interests-on
Repo
Framework
comments powered by Disqus