Paper Group ANR 247
Deconvolutional Feature Stacking for Weakly-Supervised Semantic Segmentation. Neighborhood Features Help Detecting Non-Technical Losses in Big Data Sets. Part-of-Speech Relevance Weights for Learning Word Embeddings. A supermartingale approach to Gaussian process based sequential design of experiments. Query Clustering using Segment Specific Contex …
Deconvolutional Feature Stacking for Weakly-Supervised Semantic Segmentation
| Title | Deconvolutional Feature Stacking for Weakly-Supervised Semantic Segmentation |
| Authors | Hyo-Eun Kim, Sangheum Hwang |
| Abstract | A weakly-supervised semantic segmentation framework with a tied deconvolutional neural network is presented. Each deconvolution layer in the framework consists of unpooling and deconvolution operations. ‘Unpooling’ upsamples the input feature map based on unpooling switches defined by corresponding convolution layer’s pooling operation. ‘Deconvolution’ convolves the input unpooled features by using convolutional weights tied with the corresponding convolution layer’s convolution operation. The unpooling-deconvolution combination helps to eliminate less discriminative features in a feature extraction stage, since output features of the deconvolution layer are reconstructed from the most discriminative unpooled features instead of the raw one. This results in reduction of false positives in a pixel-level inference stage. All the feature maps restored from the entire deconvolution layers can constitute a rich discriminative feature set according to different abstraction levels. Those features are stacked to be selectively used for generating class-specific activation maps. Under the weak supervision (image-level labels), the proposed framework shows promising results on lesion segmentation in medical images (chest X-rays) and achieves state-of-the-art performance on the PASCAL VOC segmentation dataset in the same experimental condition. |
| Tasks | Lesion Segmentation, Semantic Segmentation, Weakly-Supervised Semantic Segmentation |
| Published | 2016-02-16 |
| URL | http://arxiv.org/abs/1602.04984v3 |
| http://arxiv.org/pdf/1602.04984v3.pdf | |
| PWC | https://paperswithcode.com/paper/deconvolutional-feature-stacking-for-weakly |
| Repo | |
| Framework | |
Neighborhood Features Help Detecting Non-Technical Losses in Big Data Sets
| Title | Neighborhood Features Help Detecting Non-Technical Losses in Big Data Sets |
| Authors | Patrick Glauner, Jorge Meira, Lautaro Dolberg, Radu State, Franck Bettinger, Yves Rangoni, Diogo Duarte |
| Abstract | Electricity theft is a major problem around the world in both developed and developing countries and may range up to 40% of the total electricity distributed. More generally, electricity theft belongs to non-technical losses (NTL), which are losses that occur during the distribution of electricity in power grids. In this paper, we build features from the neighborhood of customers. We first split the area in which the customers are located into grids of different sizes. For each grid cell we then compute the proportion of inspected customers and the proportion of NTL found among the inspected customers. We then analyze the distributions of features generated and show why they are useful to predict NTL. In addition, we compute features from the consumption time series of customers. We also use master data features of customers, such as their customer class and voltage of their connection. We compute these features for a Big Data base of 31M meter readings, 700K customers and 400K inspection results. We then use these features to train four machine learning algorithms that are particularly suitable for Big Data sets because of their parallelizable structure: logistic regression, k-nearest neighbors, linear support vector machine and random forest. Using the neighborhood features instead of only analyzing the time series has resulted in appreciable results for Big Data sets for varying NTL proportions of 1%-90%. This work can therefore be deployed to a wide range of different regions around the world. |
| Tasks | Time Series |
| Published | 2016-07-04 |
| URL | http://arxiv.org/abs/1607.00872v2 |
| http://arxiv.org/pdf/1607.00872v2.pdf | |
| PWC | https://paperswithcode.com/paper/neighborhood-features-help-detecting-non |
| Repo | |
| Framework | |
Part-of-Speech Relevance Weights for Learning Word Embeddings
| Title | Part-of-Speech Relevance Weights for Learning Word Embeddings |
| Authors | Quan Liu, Zhen-Hua Ling, Hui Jiang, Yu Hu |
| Abstract | This paper proposes a model to learn word embeddings with weighted contexts based on part-of-speech (POS) relevance weights. POS is a fundamental element in natural language. However, state-of-the-art word embedding models fail to consider it. This paper proposes to use position-dependent POS relevance weighting matrices to model the inherent syntactic relationship among words within a context window. We utilize the POS relevance weights to model each word-context pairs during the word embedding training process. The model proposed in this paper paper jointly optimizes word vectors and the POS relevance matrices. Experiments conducted on popular word analogy and word similarity tasks all demonstrated the effectiveness of the proposed method. |
| Tasks | Learning Word Embeddings, Word Embeddings |
| Published | 2016-03-24 |
| URL | http://arxiv.org/abs/1603.07695v1 |
| http://arxiv.org/pdf/1603.07695v1.pdf | |
| PWC | https://paperswithcode.com/paper/part-of-speech-relevance-weights-for-learning |
| Repo | |
| Framework | |
A supermartingale approach to Gaussian process based sequential design of experiments
| Title | A supermartingale approach to Gaussian process based sequential design of experiments |
| Authors | Julien Bect, François Bachoc, David Ginsbourger |
| Abstract | Gaussian process (GP) models have become a well-established frameworkfor the adaptive design of costly experiments, and notably of computerexperiments. GP-based sequential designs have been found practicallyefficient for various objectives, such as global optimization(estimating the global maximum or maximizer(s) of a function),reliability analysis (estimating a probability of failure) or theestimation of level sets and excursion sets. In this paper, we studythe consistency of an important class of sequential designs, known asstepwise uncertainty reduction (SUR) strategies. Our approach relieson the key observation that the sequence of residual uncertaintymeasures, in SUR strategies, is generally a supermartingale withrespect to the filtration generated by the observations. Thisobservation enables us to establish generic consistency results for abroad class of SUR strategies. The consistency of several popularsequential design strategies is then obtained by means of this generalresult. Notably, we establish the consistency of two SUR strategiesproposed by Bect, Ginsbourger, Li, Picheny and Vazquez (Stat. Comp.,2012)—to the best of our knowledge, these are the first proofs ofconsistency for GP-based sequential design algorithms dedicated to theestimation of excursion sets and their measure. We also establish anew, more general proof of consistency for the expected improvementalgorithm for global optimization which, unlike previous results inthe literature, applies to any GP with continuous sample paths. |
| Tasks | |
| Published | 2016-08-03 |
| URL | http://arxiv.org/abs/1608.01118v3 |
| http://arxiv.org/pdf/1608.01118v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-supermartingale-approach-to-gaussian |
| Repo | |
| Framework | |
Query Clustering using Segment Specific Context Embeddings
| Title | Query Clustering using Segment Specific Context Embeddings |
| Authors | S. K Kolluru, Prasenjit Mukherjee |
| Abstract | This paper presents a novel query clustering approach to capture the broad interest areas of users querying search engines. We make use of recent advances in NLP - word2vec and extend it to get query2vec, vector representations of queries, based on query contexts, obtained from the top search results for the query and use a highly scalable Divide & Merge clustering algorithm on top of the query vectors, to get the clusters. We have tried this approach on a variety of segments, including Retail, Travel, Health, Phones and found the clusters to be effective in discovering user’s interest areas which have high monetization potential. |
| Tasks | |
| Published | 2016-08-03 |
| URL | http://arxiv.org/abs/1608.01247v2 |
| http://arxiv.org/pdf/1608.01247v2.pdf | |
| PWC | https://paperswithcode.com/paper/query-clustering-using-segment-specific |
| Repo | |
| Framework | |
Learning Granger Causality for Hawkes Processes
| Title | Learning Granger Causality for Hawkes Processes |
| Authors | Hongteng Xu, Mehrdad Farajtabar, Hongyuan Zha |
| Abstract | Learning Granger causality for general point processes is a very challenging task. In this paper, we propose an effective method, learning Granger causality, for a special but significant type of point processes — Hawkes process. We reveal the relationship between Hawkes process’s impact function and its Granger causality graph. Specifically, our model represents impact functions using a series of basis functions and recovers the Granger causality graph via group sparsity of the impact functions’ coefficients. We propose an effective learning algorithm combining a maximum likelihood estimator (MLE) with a sparse-group-lasso (SGL) regularizer. Additionally, the flexibility of our model allows to incorporate the clustering structure event types into learning framework. We analyze our learning algorithm and propose an adaptive procedure to select basis functions. Experiments on both synthetic and real-world data show that our method can learn the Granger causality graph and the triggering patterns of the Hawkes processes simultaneously. |
| Tasks | Point Processes |
| Published | 2016-02-14 |
| URL | http://arxiv.org/abs/1602.04511v2 |
| http://arxiv.org/pdf/1602.04511v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-granger-causality-for-hawkes |
| Repo | |
| Framework | |
Input-Output Non-Linear Dynamical Systems applied to Physiological Condition Monitoring
| Title | Input-Output Non-Linear Dynamical Systems applied to Physiological Condition Monitoring |
| Authors | Konstantinos Georgatzis, Christopher K. I. Williams, Christopher Hawthorne |
| Abstract | We present a non-linear dynamical system for modelling the effect of drug infusions on the vital signs of patients admitted in Intensive Care Units (ICUs). More specifically we are interested in modelling the effect of a widely used anaesthetic drug (Propofol) on a patient’s monitored depth of anaesthesia and haemodynamics. We compare our approach with one from the Pharmacokinetics/Pharmacodynamics (PK/PD) literature and show that we can provide significant improvements in performance without requiring the incorporation of expert physiological knowledge in our system. |
| Tasks | |
| Published | 2016-07-31 |
| URL | http://arxiv.org/abs/1608.00242v2 |
| http://arxiv.org/pdf/1608.00242v2.pdf | |
| PWC | https://paperswithcode.com/paper/input-output-non-linear-dynamical-systems |
| Repo | |
| Framework | |
Multi-Level Analysis and Annotation of Arabic Corpora for Text-to-Sign Language MT
| Title | Multi-Level Analysis and Annotation of Arabic Corpora for Text-to-Sign Language MT |
| Authors | Abdelaziz Lakhfif, Mohammed T. Laskri, Eric Atwell |
| Abstract | In this paper, we present an ongoing effort in lexical semantic analysis and annotation of Modern Standard Arabic (MSA) text, a semi automatic annotation tool concerned with the morphologic, syntactic, and semantic levels of description. |
| Tasks | |
| Published | 2016-05-24 |
| URL | http://arxiv.org/abs/1605.07346v1 |
| http://arxiv.org/pdf/1605.07346v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-level-analysis-and-annotation-of-arabic |
| Repo | |
| Framework | |
Summarizing Decisions in Spoken Meetings
| Title | Summarizing Decisions in Spoken Meetings |
| Authors | Lu Wang, Claire Cardie |
| Abstract | This paper addresses the problem of summarizing decisions in spoken meetings: our goal is to produce a concise {\it decision abstract} for each meeting decision. We explore and compare token-level and dialogue act-level automatic summarization methods using both unsupervised and supervised learning frameworks. In the supervised summarization setting, and given true clusterings of decision-related utterances, we find that token-level summaries that employ discourse context can approach an upper bound for decision abstracts derived directly from dialogue acts. In the unsupervised summarization setting,we find that summaries based on unsupervised partitioning of decision-related utterances perform comparably to those based on partitions generated using supervised techniques (0.22 ROUGE-F1 using LDA-based topic models vs. 0.23 using SVMs). |
| Tasks | Topic Models |
| Published | 2016-06-25 |
| URL | http://arxiv.org/abs/1606.07965v1 |
| http://arxiv.org/pdf/1606.07965v1.pdf | |
| PWC | https://paperswithcode.com/paper/summarizing-decisions-in-spoken-meetings |
| Repo | |
| Framework | |
Combinatorial Inference for Graphical Models
| Title | Combinatorial Inference for Graphical Models |
| Authors | Matey Neykov, Junwei Lu, Han Liu |
| Abstract | We propose a new family of combinatorial inference problems for graphical models. Unlike classical statistical inference where the main interest is point estimation or parameter testing, combinatorial inference aims at testing the global structure of the underlying graph. Examples include testing the graph connectivity, the presence of a cycle of certain size, or the maximum degree of the graph. To begin with, we develop a unified theory for the fundamental limits of a large family of combinatorial inference problems. We propose new concepts including structural packing and buffer entropies to characterize how the complexity of combinatorial graph structures impacts the corresponding minimax lower bounds. On the other hand, we propose a family of novel and practical structural testing algorithms to match the lower bounds. We provide thorough numerical results on both synthetic graphical models and brain networks to illustrate the usefulness of these proposed methods. |
| Tasks | |
| Published | 2016-08-10 |
| URL | http://arxiv.org/abs/1608.03045v3 |
| http://arxiv.org/pdf/1608.03045v3.pdf | |
| PWC | https://paperswithcode.com/paper/combinatorial-inference-for-graphical-models |
| Repo | |
| Framework | |
PAG2ADMG: An Algorithm for the Complete Causal Enumeration of a Markov Equivalence Class
| Title | PAG2ADMG: An Algorithm for the Complete Causal Enumeration of a Markov Equivalence Class |
| Authors | Nishant Subramani |
| Abstract | Causal graphs, such as directed acyclic graphs (DAGs) and partial ancestral graphs (PAGs), represent causal relationships among variables in a model. Methods exist for learning DAGs and PAGs from data and for converting DAGs to PAGs. However, these methods are significantly limited in that they only output a single causal graph consistent with the independencies and dependencies (the Markov equivalence class $M$) estimated from the data. This is problematic and insufficient because many distinct graphs may be consistent with $M$. A data modeler may wish to select among these numerous consistent graphs using domain knowledge or other model selection algorithms. Enumeration of the set of consistent graphs is the bottleneck. In this paper, we present a method that makes this desired enumeration possible. We introduce PAG2ADMG, the first algorithm for enumerating all causal graphs consistent with $M$. PAG2ADMG converts a given PAG into the complete set of acyclic directed mixed graphs (ADMGs) consistent with $M$. We prove the correctness of the approach and demonstrate its efficiency relative to brute-force enumeration. |
| Tasks | Model Selection |
| Published | 2016-12-01 |
| URL | http://arxiv.org/abs/1612.00099v3 |
| http://arxiv.org/pdf/1612.00099v3.pdf | |
| PWC | https://paperswithcode.com/paper/pag2admg-an-algorithm-for-the-complete-causal |
| Repo | |
| Framework | |
Combining Random Walks and Nonparametric Bayesian Topic Model for Community Detection
| Title | Combining Random Walks and Nonparametric Bayesian Topic Model for Community Detection |
| Authors | Ruimin Zhu, Wenxin Jiang |
| Abstract | Community detection has been an active research area for decades. Among all probabilistic models, Stochastic Block Model has been the most popular one. This paper introduces a novel probabilistic model: RW-HDP, based on random walks and Hierarchical Dirichlet Process, for community extraction. In RW-HDP, random walks conducted in a social network are treated as documents; nodes are treated as words. By using Hierarchical Dirichlet Process, a nonparametric Bayesian model, we are not only able to cluster nodes into different communities, but also determine the number of communities automatically. We use Stochastic Variational Inference for our model inference, which makes our method time efficient and can be easily extended to an online learning algorithm. |
| Tasks | Community Detection |
| Published | 2016-07-19 |
| URL | http://arxiv.org/abs/1607.05573v2 |
| http://arxiv.org/pdf/1607.05573v2.pdf | |
| PWC | https://paperswithcode.com/paper/combining-random-walks-and-nonparametric |
| Repo | |
| Framework | |
Blind Modulation Classification based on MLP and PNN
| Title | Blind Modulation Classification based on MLP and PNN |
| Authors | Harishchandra Dubey, Nandita, Ashutosh Kumar Tiwari |
| Abstract | In this work, a pattern recognition system is investigated for blind automatic classification of digitally modulated communication signals. The proposed technique is able to discriminate the type of modulation scheme which is eventually used for demodulation followed by information extraction. The proposed system is composed of two subsystems namely feature extraction sub-system (FESS) and classifier sub-system (CSS). The FESS consists of continuous wavelet transform (CWT) for feature generation and principal component analysis (PCA) for selection of the feature subset which is rich in discriminatory information. The CSS uses the selected features to accurately classify the modulation class of the received signal. The proposed technique uses probabilistic neural network (PNN) and multilayer perceptron forward neural network (MLPFN) for comparative study of their recognition ability. PNN have been found to perform better in terms of classification accuracy as well as testing and training time than MLPFN. The proposed approach is robust to presence of phase offset and additive Gaussian noise. |
| Tasks | |
| Published | 2016-05-30 |
| URL | http://arxiv.org/abs/1605.09441v1 |
| http://arxiv.org/pdf/1605.09441v1.pdf | |
| PWC | https://paperswithcode.com/paper/blind-modulation-classification-based-on-mlp |
| Repo | |
| Framework | |
An Automated CNN Recommendation System for Image Classification Tasks
| Title | An Automated CNN Recommendation System for Image Classification Tasks |
| Authors | Song Wang, Li Sun, Wei Fan, Jun Sun, Satoshi Naoi, Koichi Shirahata, Takuya Fukagai, Yasumoto Tomita, Atsushi Ike |
| Abstract | Nowadays the CNN is widely used in practical applications for image classification task. However the design of the CNN model is very professional work and which is very difficult for ordinary users. Besides, even for experts of CNN, to select an optimal model for specific task may still need a lot of time (to train many different models). In order to solve this problem, we proposed an automated CNN recommendation system for image classification task. Our system is able to evaluate the complexity of the classification task and the classification ability of the CNN model precisely. By using the evaluation results, the system can recommend the optimal CNN model and which can match the task perfectly. The recommendation process of the system is very fast since we don’t need any model training. The experiment results proved that the evaluation methods are very accurate and reliable. |
| Tasks | Image Classification |
| Published | 2016-12-27 |
| URL | http://arxiv.org/abs/1612.08484v1 |
| http://arxiv.org/pdf/1612.08484v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-automated-cnn-recommendation-system-for |
| Repo | |
| Framework | |
Fuzzy Object-Oriented Dynamic Networks. I
| Title | Fuzzy Object-Oriented Dynamic Networks. I |
| Authors | D. A. Terletskyi, A. I. Provotar |
| Abstract | The concepts of fuzzy objects and their classes are described that make it possible to structurally represent knowledge about fuzzy and partially-defined objects and their classes. Operations over such objects and classes are also proposed that make it possible to obtain sets and new classes of fuzzy objects and also to model variations in object structures under the influence of external factors. |
| Tasks | |
| Published | 2016-01-07 |
| URL | http://arxiv.org/abs/1601.01635v2 |
| http://arxiv.org/pdf/1601.01635v2.pdf | |
| PWC | https://paperswithcode.com/paper/fuzzy-object-oriented-dynamic-networks-i |
| Repo | |
| Framework | |
