May 7, 2019

3166 words 15 mins read

Paper Group ANR 4

A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction. Tensor Graphical Model: Non-convex Optimization and Statistical Inference. The scarcity of crossing dependencies: a direct outcome of a specific constraint?. Adaptive Parameter Selection in Evolutionary Algorithms by Reinforcement Learning with Dyna …

A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction


Title	A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction
Authors	Eunhee Kang, Junhong Min, Jong Chul Ye
Abstract	Due to the potential risk of inducing cancers, radiation dose of X-ray CT should be reduced for routine patient scanning. However, in low-dose X-ray CT, severe artifacts usually occur due to photon starvation, beamhardening, etc, which decrease the reliability of diagnosis. Thus, high quality reconstruction from low-dose X-ray CT data has become one of the important research topics in CT community. Conventional model-based denoising approaches are, however, computationally very expensive, and image domain denoising approaches hardly deal with CT specific noise patterns. To address these issues, we propose an algorithm using a deep convolutional neural network (CNN), which is applied to wavelet transform coefficients of low-dose CT images. Specifically, by using a directional wavelet transform for extracting directional component of artifacts and exploiting the intra- and inter-band correlations, our deep network can effectively suppress CT specific noises. Moreover, our CNN is designed to have various types of residual learning architecture for faster network training and better denoising. Experimental results confirm that the proposed algorithm effectively removes complex noise patterns of CT images, originated from the reduced X-ray dose. In addition, we show that wavelet domain CNN is efficient in removing the noises from low-dose CT compared to an image domain CNN. Our results were rigorously evaluated by several radiologists and won the second place award in 2016 AAPM Low-Dose CT Grand Challenge. To the best of our knowledge, this work is the first deep learning architecture for low-dose CT reconstruction that has been rigorously evaluated and proven for its efficacy.
Tasks	Denoising, Low-Dose X-Ray Ct Reconstruction
Published	2016-10-31
URL	http://arxiv.org/abs/1610.09736v3
PDF	http://arxiv.org/pdf/1610.09736v3.pdf
PWC	https://paperswithcode.com/paper/a-deep-convolutional-neural-network-using
Repo
Framework

Tensor Graphical Model: Non-convex Optimization and Statistical Inference


Title	Tensor Graphical Model: Non-convex Optimization and Statistical Inference
Authors	Xiang Lyu, Will Wei Sun, Zhaoran Wang, Han Liu, Jian Yang, Guang Cheng
Abstract	We consider the estimation and inference of graphical models that characterize the dependency structure of high-dimensional tensor-valued data. To facilitate the estimation of the precision matrix corresponding to each way of the tensor, we assume the data follow a tensor normal distribution whose covariance has a Kronecker product structure. A critical challenge in the estimation and inference of this model is the fact that its penalized maximum likelihood estimation involves minimizing a non-convex objective function. To address it, this paper makes two contributions: (i) In spite of the non-convexity of this estimation problem, we prove that an alternating minimization algorithm, which iteratively estimates each sparse precision matrix while fixing the others, attains an estimator with an optimal statistical rate of convergence. (ii) We propose a de-biased statistical inference procedure for testing hypotheses on the true support of the sparse precision matrices, and employ it for testing a growing number of hypothesis with false discovery rate (FDR) control. The asymptotic normality of our test statistic and the consistency of FDR control procedure are established. Our theoretical results are backed up by thorough numerical studies and our real applications on neuroimaging studies of Autism spectrum disorder and users’ advertising click analysis bring new scientific findings and business insights. The proposed methods are encoded into a publicly available R package Tlasso.
Tasks
Published	2016-09-15
URL	http://arxiv.org/abs/1609.04522v2
PDF	http://arxiv.org/pdf/1609.04522v2.pdf
PWC	https://paperswithcode.com/paper/tensor-graphical-model-non-convex
Repo
Framework

The scarcity of crossing dependencies: a direct outcome of a specific constraint?


Title	The scarcity of crossing dependencies: a direct outcome of a specific constraint?
Authors	Carlos Gómez-Rodríguez, Ramon Ferrer-i-Cancho
Abstract	The structure of a sentence can be represented as a network where vertices are words and edges indicate syntactic dependencies. Interestingly, crossing syntactic dependencies have been observed to be infrequent in human languages. This leads to the question of whether the scarcity of crossings in languages arises from an independent and specific constraint on crossings. We provide statistical evidence suggesting that this is not the case, as the proportion of dependency crossings of sentences from a wide range of languages can be accurately estimated by a simple predictor based on a null hypothesis on the local probability that two dependencies cross given their lengths. The relative error of this predictor never exceeds 5% on average, whereas the error of a baseline predictor assuming a random ordering of the words of a sentence is at least 6 times greater. Our results suggest that the low frequency of crossings in natural languages is neither originated by hidden knowledge of language nor by the undesirability of crossings per se, but as a mere side effect of the principle of dependency length minimization.
Tasks
Published	2016-01-13
URL	http://arxiv.org/abs/1601.03210v3
PDF	http://arxiv.org/pdf/1601.03210v3.pdf
PWC	https://paperswithcode.com/paper/the-scarcity-of-crossing-dependencies-a
Repo
Framework

Adaptive Parameter Selection in Evolutionary Algorithms by Reinforcement Learning with Dynamic Discretization of Parameter Range


Title	Adaptive Parameter Selection in Evolutionary Algorithms by Reinforcement Learning with Dynamic Discretization of Parameter Range
Authors	Arkady Rost, Irina Petrova, Arina Buzdalova
Abstract	Online parameter controllers for evolutionary algorithms adjust values of parameters during the run of an evolutionary algorithm. Recently a new efficient parameter controller based on reinforcement learning was proposed by Karafotias et al. In this method ranges of parameters are discretized into several intervals before the run. However, performing adaptive discretization during the run may increase efficiency of an evolutionary algorithm. Aleti et al. proposed another efficient controller with adaptive discretization. In the present paper we propose a parameter controller based on reinforcement learning with adaptive discretization. The proposed controller is compared with the existing parameter adjusting methods on several test problems using different configurations of an evolutionary algorithm. For the test problems, we consider four continuous functions, namely the sphere function, the Rosenbrock function, the Levi function and the Rastrigin function. Results show that the new controller outperforms the other controllers on most of the considered test problems.
Tasks
Published	2016-03-22
URL	http://arxiv.org/abs/1603.06788v1
PDF	http://arxiv.org/pdf/1603.06788v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-parameter-selection-in-evolutionary
Repo
Framework

Optimal rates for the regularized learning algorithms under general source condition


Title	Optimal rates for the regularized learning algorithms under general source condition
Authors	Abhishake Rastogi, Sivananthan Sampath
Abstract	We consider the learning algorithms under general source condition with the polynomial decay of the eigenvalues of the integral operator in vector-valued function setting. We discuss the upper convergence rates of Tikhonov regularizer under general source condition corresponding to increasing monotone index function. The convergence issues are studied for general regularization schemes by using the concept of operator monotone index functions in minimax setting. Further we also address the minimum possible error for any learning algorithm.
Tasks
Published	2016-11-07
URL	http://arxiv.org/abs/1611.01900v2
PDF	http://arxiv.org/pdf/1611.01900v2.pdf
PWC	https://paperswithcode.com/paper/optimal-rates-for-the-regularized-learning
Repo
Framework

Radio Transformer Networks: Attention Models for Learning to Synchronize in Wireless Systems


Title	Radio Transformer Networks: Attention Models for Learning to Synchronize in Wireless Systems
Authors	Timothy J O’Shea, Latha Pemula, Dhruv Batra, T. Charles Clancy
Abstract	We introduce learned attention models into the radio machine learning domain for the task of modulation recognition by leveraging spatial transformer networks and introducing new radio domain appropriate transformations. This attention model allows the network to learn a localization network capable of synchronizing and normalizing a radio signal blindly with zero knowledge of the signals structure based on optimization of the network for classification accuracy, sparse representation, and regularization. Using this architecture we are able to outperform our prior results in accuracy vs signal to noise ratio against an identical system without attention, however we believe such an attention model has implication far beyond the task of modulation recognition.
Tasks
Published	2016-05-03
URL	http://arxiv.org/abs/1605.00716v1
PDF	http://arxiv.org/pdf/1605.00716v1.pdf
PWC	https://paperswithcode.com/paper/radio-transformer-networks-attention-models
Repo
Framework

Cross Domain Adaptation by Learning Partially Shared Classifiers and Weighting Source Data Points in the Shared Subspaces


Title	Cross Domain Adaptation by Learning Partially Shared Classifiers and Weighting Source Data Points in the Shared Subspaces
Authors	Hongqi Wang, Anfeng Xu, Shanshan Wang, Sunny Chughtai
Abstract	Transfer learning is a problem defined over two domains. These two domains share the same feature space and class label space, but have significantly different distributions. One domain has sufficient labels, named as source domain, and the other domain has few labels, named as target do- main. The problem is to learn a effective classifier for the target domain. In this paper, we propose a novel transfer learning method for this problem by learning a partially shared classifier for the target domain, and weighting the source domain data points. We learn some shared subspaces for both the data points of the two domains, and a shared classifier in the shared subspaces. We hope that in the shared subspaces, the distributions of two domain can match each other well, and to match the distributions, we weight the source domain data points with different weighting factors. Moreover, we adapt the shared classifier to each domain by learning different adaptation functions. To learn the subspace transformation matrices, the classifier parameters, and the adaptation parameters, we build a objective function with weighted clas- sification errors, parameter regularization, local reconstruction regularization, and distribution matching. This objective function is minimized by an itera- tive algorithm. Experiments show its effectiveness over benchmark data sets, including travel destination review data set, face expression data set, spam email data set, etc.
Tasks	Domain Adaptation, Transfer Learning
Published	2016-05-21
URL	http://arxiv.org/abs/1605.06673v1
PDF	http://arxiv.org/pdf/1605.06673v1.pdf
PWC	https://paperswithcode.com/paper/cross-domain-adaptation-by-learning-partially
Repo
Framework

Dense Associative Memory for Pattern Recognition


Title	Dense Associative Memory for Pattern Recognition
Authors	Dmitry Krotov, John J Hopfield
Abstract	A model of associative memory is studied, which stores and reliably retrieves many more patterns than the number of neurons in the network. We propose a simple duality between this dense associative memory and neural networks commonly used in deep learning. On the associative memory side of this duality, a family of models that smoothly interpolates between two limiting cases can be constructed. One limit is referred to as the feature-matching mode of pattern recognition, and the other one as the prototype regime. On the deep learning side of the duality, this family corresponds to feedforward neural networks with one hidden layer and various activation functions, which transmit the activities of the visible neurons to the hidden layer. This family of activation functions includes logistics, rectified linear units, and rectified polynomials of higher degrees. The proposed duality makes it possible to apply energy-based intuition from associative memory to analyze computational properties of neural networks with unusual activation functions - the higher rectified polynomials which until now have not been used in deep learning. The utility of the dense memories is illustrated for two test cases: the logical gate XOR and the recognition of handwritten digits from the MNIST data set.
Tasks
Published	2016-06-03
URL	http://arxiv.org/abs/1606.01164v2
PDF	http://arxiv.org/pdf/1606.01164v2.pdf
PWC	https://paperswithcode.com/paper/dense-associative-memory-for-pattern
Repo
Framework

Proceedings of the Second Summer School on Argumentation: Computational and Linguistic Perspectives (SSA’16)


Title	Proceedings of the Second Summer School on Argumentation: Computational and Linguistic Perspectives (SSA’16)
Authors	Sarah A. Gaggl, Matthias Thimm
Abstract	This volume contains the thesis abstracts presented at the Second Summer School on Argumentation: Computational and Linguistic Perspectives (SSA’2016) held on September 8-12 in Potsdam, Germany.
Tasks
Published	2016-08-03
URL	http://arxiv.org/abs/1608.02441v1
PDF	http://arxiv.org/pdf/1608.02441v1.pdf
PWC	https://paperswithcode.com/paper/proceedings-of-the-second-summer-school-on
Repo
Framework

Blocking and Other Enhancements for Bottom-Up Model Generation Methods


Title	Blocking and Other Enhancements for Bottom-Up Model Generation Methods
Authors	Peter Baumgartner, Renate A. Schmidt
Abstract	Model generation is a problem complementary to theorem proving and is important for fault analysis and debugging of formal specifications of security protocols, programs and terminological definitions. This paper discusses several ways of enhancing the paradigm of bottom-up model generation. The two main contributions are new, generalized blocking techniques and a new range-restriction transformation. The blocking techniques are based on simple transformations of the input set together with standard equality reasoning and redundancy elimination techniques. These provide general methods for finding small, finite models. The range-restriction transformation refines existing transformations to range-restricted clauses by carefully limiting the creation of domain terms. All possible combinations of the introduced techniques and classical range-restriction were tested on the clausal problems of the TPTP Version 6.0.0 with an implementation based on the SPASS theorem prover using a hyperresolution-like refinement. Unrestricted domain blocking gave best results for satisfiable problems showing it is a powerful technique indispensable for bottom-up model generation methods. Both in combination with the new range-restricting transformation, and the classical range-restricting transformation, good results have been obtained. Limiting the creation of terms during the inference process by using the new range restricting transformation has paid off, especially when using it together with a shifting transformation. The experimental results also show that classical range restriction with unrestricted blocking provides a useful complementary method. Overall, the results showed bottom-up model generation methods were good for disproving theorems and generating models for satisfiable problems, but less efficient than SPASS in auto mode for unsatisfiable problems.
Tasks	Automated Theorem Proving
Published	2016-11-28
URL	http://arxiv.org/abs/1611.09014v2
PDF	http://arxiv.org/pdf/1611.09014v2.pdf
PWC	https://paperswithcode.com/paper/blocking-and-other-enhancements-for-bottom-up
Repo
Framework

Using compatible shape descriptor for lexicon reduction of printed Farsi subwords


Title	Using compatible shape descriptor for lexicon reduction of printed Farsi subwords
Authors	Homa Davoudi, Ehsanollah Kabir
Abstract	This Paper presents a method for lexicon reduction of Printed Farsi subwords based on their holistic shape features. Because of the large number of Persian subwords variously shaped from a simple letter to a complex combination of several connected characters, it is not easy to find a fixed shape descriptor suitable for all subwords. In this paper, we propose to select the descriptor according to the input shape characteristics. To do this, a neural network is trained to predict the appropriate descriptor of the input image. This network is implemented in the proposed lexicon reduction system to decide on the descriptor used for comparison of the query image with the lexicon entries. Evaluating the proposed method on a dataset of Persian subwords allows one to attest the effectiveness of the proposed idea of dealing differently with various query shapes.
Tasks
Published	2016-01-23
URL	http://arxiv.org/abs/1601.06251v1
PDF	http://arxiv.org/pdf/1601.06251v1.pdf
PWC	https://paperswithcode.com/paper/using-compatible-shape-descriptor-for-lexicon
Repo
Framework

An Ontology of Preference-Based Multiobjective Metaheuristics


Title	An Ontology of Preference-Based Multiobjective Metaheuristics
Authors	Longmei Li, Iryna Yevseyeva, Vitor Basto-Fernandes, Heike Trautmann, Ning Jing, Michael Emmerich
Abstract	User preference integration is of great importance in multi-objective optimization, in particular in many objective optimization. Preferences have long been considered in traditional multicriteria decision making (MCDM) which is based on mathematical programming. Recently, it is integrated in multi-objective metaheuristics (MOMH), resulting in focus on preferred parts of the Pareto front instead of the whole Pareto front. The number of publications on preference-based multi-objective metaheuristics has increased rapidly over the past decades. There already exist various preference handling methods and MOMH methods, which have been combined in diverse ways. This article proposes to use the Web Ontology Language (OWL) to model and systematize the results developed in this field. A review of the existing work is provided, based on which an ontology is built and instantiated with state-of-the-art results. The OWL ontology is made public and open to future extension. Moreover, the usage of the ontology is exemplified for different use-cases, including querying for methods that match an engineering application, bibliometric analysis, checking existence of combinations of preference models and MOMH techniques, and discovering opportunities for new research and open research questions.
Tasks	Decision Making
Published	2016-09-26
URL	http://arxiv.org/abs/1609.08082v2
PDF	http://arxiv.org/pdf/1609.08082v2.pdf
PWC	https://paperswithcode.com/paper/an-ontology-of-preference-based
Repo
Framework

p-DLA: A Predictive System Model for Onshore Oil and Gas Pipeline Dataset Classification and Monitoring - Part 1


Title	p-DLA: A Predictive System Model for Onshore Oil and Gas Pipeline Dataset Classification and Monitoring - Part 1
Authors	E. N. Osegi
Abstract	With the rise in militant activity and rogue behaviour in oil and gas regions around the world, oil pipeline disturbances is on the increase leading to huge losses to multinational operators and the countries where such facilities exist. However, this situation can be averted if adequate predictive monitoring schemes are put in place. We propose in the first part of this paper, an artificial intelligence predictive monitoring system capable of predictive classification and pattern recognition of pipeline datasets. The predictive system is based on a highly sparse predictive Deviant Learning Algorithm (p-DLA) designed to synthesize a sequence of memory predictive clusters for eventual monitoring, control and decision making. The DLA (p-DLA) is compared with a popular machine learning algorithm, the Long Short-Term Memory (LSTM) which is based on a temporal version of the standard feed-forward back-propagation trained artificial neural networks (ANNs). The results of simulations study show impressive results and validates the sparse memory predictive approach which favours the sub-synthesis of a highly compressed and low dimensional knowledge discovery and information prediction scheme. It also shows that the proposed new approach is competitive with a well-known and proven AI approach such as the LSTM.
Tasks	Decision Making
Published	2016-12-31
URL	http://arxiv.org/abs/1701.00040v1
PDF	http://arxiv.org/pdf/1701.00040v1.pdf
PWC	https://paperswithcode.com/paper/p-dla-a-predictive-system-model-for-onshore
Repo
Framework

A Paradigm for Situated and Goal-Driven Language Learning


Title	A Paradigm for Situated and Goal-Driven Language Learning
Authors	Jon Gauthier, Igor Mordatch
Abstract	A distinguishing property of human intelligence is the ability to flexibly use language in order to communicate complex ideas with other humans in a variety of contexts. Research in natural language dialogue should focus on designing communicative agents which can integrate themselves into these contexts and productively collaborate with humans. In this abstract, we propose a general situated language learning paradigm which is designed to bring about robust language agents able to cooperate productively with humans.
Tasks
Published	2016-10-12
URL	http://arxiv.org/abs/1610.03585v1
PDF	http://arxiv.org/pdf/1610.03585v1.pdf
PWC	https://paperswithcode.com/paper/a-paradigm-for-situated-and-goal-driven
Repo
Framework

Learning a Discriminative Null Space for Person Re-identification


Title	Learning a Discriminative Null Space for Person Re-identification
Authors	Li Zhang, Tao Xiang, Shaogang Gong
Abstract	Most existing person re-identification (re-id) methods focus on learning the optimal distance metrics across camera views. Typically a person’s appearance is represented using features of thousands of dimensions, whilst only hundreds of training samples are available due to the difficulties in collecting matched training images. With the number of training samples much smaller than the feature dimension, the existing methods thus face the classic small sample size (SSS) problem and have to resort to dimensionality reduction techniques and/or matrix regularisation, which lead to loss of discriminative power. In this work, we propose to overcome the SSS problem in re-id distance metric learning by matching people in a discriminative null space of the training data. In this null space, images of the same person are collapsed into a single point thus minimising the within-class scatter to the extreme and maximising the relative between-class separation simultaneously. Importantly, it has a fixed dimension, a closed-form solution and is very efficient to compute. Extensive experiments carried out on five person re-identification benchmarks including VIPeR, PRID2011, CUHK01, CUHK03 and Market1501 show that such a simple approach beats the state-of-the-art alternatives, often by a big margin.
Tasks	Dimensionality Reduction, Metric Learning, Person Re-Identification
Published	2016-03-07
URL	http://arxiv.org/abs/1603.02139v1
PDF	http://arxiv.org/pdf/1603.02139v1.pdf
PWC	https://paperswithcode.com/paper/learning-a-discriminative-null-space-for
Repo
Framework