October 16, 2019

3284 words 16 mins read

Paper Group ANR 1141

A Simple Quantum Neural Net with a Periodic Activation Function. 30m resolution Global Annual Burned Area Mapping based on Landsat images and Google Earth Engine. A Survey on Semantic Parsing. Universal Decision-Based Black-Box Perturbations: Breaking Security-Through-Obscurity Defenses. Cross Script Hindi English NER Corpus from Wikipedia. Augment …

A Simple Quantum Neural Net with a Periodic Activation Function


Title	A Simple Quantum Neural Net with a Periodic Activation Function
Authors	Ammar Daskin
Abstract	In this paper, we propose a simple neural net that requires only $O(nlog_2k)$ number of qubits and $O(nk)$ quantum gates: Here, $n$ is the number of input parameters, and $k$ is the number of weights applied to these parameters in the proposed neural net. We describe the network in terms of a quantum circuit, and then draw its equivalent classical neural net which involves $O(k^n)$ nodes in the hidden layer. Then, we show that the network uses a periodic activation function of cosine values of the linear combinations of the inputs and weights. The backpropagation is described through the gradient descent, and then iris and breast cancer datasets are used for the simulations. The numerical results indicate the network can be used in machine learning problems and it may provide exponential speedup over the same structured classical neural net.
Tasks
Published	2018-04-20
URL	http://arxiv.org/abs/1804.07633v3
PDF	http://arxiv.org/pdf/1804.07633v3.pdf
PWC	https://paperswithcode.com/paper/a-simple-quantum-neural-net-with-a-periodic
Repo
Framework

30m resolution Global Annual Burned Area Mapping based on Landsat images and Google Earth Engine


Title	30m resolution Global Annual Burned Area Mapping based on Landsat images and Google Earth Engine
Authors	Tengfei Long, Zhaoming Zhang, Guojin He, Weili Jiao, Chao Tang, Bingfang Wu, Xiaomei Zhang, Guizhou Wang, Ranyu Yin
Abstract	Heretofore, global burned area (BA) products are only available at coarse spatial resolution, since most of the current global BA products are produced with the help of active fire detection or dense time-series change analysis, which requires very high temporal resolution. In this study, however, we focus on automated global burned area mapping approach based on Landsat images. By utilizing the huge catalog of satellite imagery as well as the high-performance computing capacity of Google Earth Engine, we proposed an automated pipeline for generating 30-meter resolution global-scale annual burned area map from time-series of Landsat images, and a novel 30-meter resolution global annual burned area map of 2015 (GABAM 2015) is released. GABAM 2015 consists of spatial extent of fires that occurred during 2015 and not of fires that occurred in previous years. Cross-comparison with recent Fire_cci version 5.0 BA product found a similar spatial distribution and a strong correlation ($R^2=0.74$) between the burned areas from the two products, although differences were found in specific land cover categories (particularly in agriculture land). Preliminary global validation showed the commission and omission error of GABAM 2015 are 13.17% and 30.13%, respectively.
Tasks	Time Series
Published	2018-05-07
URL	http://arxiv.org/abs/1805.02579v1
PDF	http://arxiv.org/pdf/1805.02579v1.pdf
PWC	https://paperswithcode.com/paper/30m-resolution-global-annual-burned-area
Repo
Framework

A Survey on Semantic Parsing


Title	A Survey on Semantic Parsing
Authors	Aishwarya Kamath, Rajarshi Das
Abstract	A significant amount of information in today’s world is stored in structured and semi-structured knowledge bases. Efficient and simple methods to query them are essential and must not be restricted to only those who have expertise in formal query languages. The field of semantic parsing deals with converting natural language utterances to logical forms that can be easily executed on a knowledge base. In this survey, we examine the various components of a semantic parsing system and discuss prominent work ranging from the initial rule based methods to the current neural approaches to program synthesis. We also discuss methods that operate using varying levels of supervision and highlight the key challenges involved in the learning of such systems.
Tasks	Program Synthesis, Semantic Parsing
Published	2018-12-03
URL	https://arxiv.org/abs/1812.00978v3
PDF	https://arxiv.org/pdf/1812.00978v3.pdf
PWC	https://paperswithcode.com/paper/a-survey-on-semantic-parsing
Repo
Framework

Universal Decision-Based Black-Box Perturbations: Breaking Security-Through-Obscurity Defenses


Title	Universal Decision-Based Black-Box Perturbations: Breaking Security-Through-Obscurity Defenses
Authors	Thomas A. Hogan, Bhavya Kailkhura
Abstract	We study the problem of finding a universal (image-agnostic) perturbation to fool machine learning (ML) classifiers (e.g., neural nets, decision tress) in the hard-label black-box setting. Recent work in adversarial ML in the white-box setting (model parameters are known) has shown that many state-of-the-art image classifiers are vulnerable to universal adversarial perturbations: a fixed human-imperceptible perturbation that, when added to any image, causes it to be misclassified with high probability Kurakin et al. [2016], Szegedy et al. [2013], Chen et al. [2017a], Carlini and Wagner [2017]. This paper considers a more practical and challenging problem of finding such universal perturbations in an obscure (or black-box) setting. More specifically, we use zeroth order optimization algorithms to find such a universal adversarial perturbation when no model information is revealed-except that the attacker can make queries to probe the classifier. We further relax the assumption that the output of a query is continuous valued confidence scores for all the classes and consider the case where the output is a hard-label decision. Surprisingly, we found that even in these extremely obscure regimes, state-of-the-art ML classifiers can be fooled with a very high probability just by adding a single human-imperceptible image perturbation to any natural image. The surprising existence of universal perturbations in a hard-label black-box setting raises serious security concerns with the existence of a universal noise vector that adversaries can possibly exploit to break a classifier on most natural images.
Tasks
Published	2018-11-09
URL	http://arxiv.org/abs/1811.03733v2
PDF	http://arxiv.org/pdf/1811.03733v2.pdf
PWC	https://paperswithcode.com/paper/universal-decision-based-black-box
Repo
Framework

Cross Script Hindi English NER Corpus from Wikipedia


Title	Cross Script Hindi English NER Corpus from Wikipedia
Authors	Mohd Zeeshan Ansari, Tanvir Ahmad, Md Arshad Ali
Abstract	The text generated on social media platforms is essentially a mixed lingual text. The mixing of language in any form produces considerable amount of difficulty in language processing systems. Moreover, the advancements in language processing research depends upon the availability of standard corpora. The development of mixed lingual Indian Named Entity Recognition (NER) systems are facing obstacles due to unavailability of the standard evaluation corpora. Such corpora may be of mixed lingual nature in which text is written using multiple languages predominantly using a single script only. The motivation of our work is to emphasize the automatic generation such kind of corpora in order to encourage mixed lingual Indian NER. The paper presents the preparation of a Cross Script Hindi-English Corpora from Wikipedia category pages. The corpora is successfully annotated using standard CoNLL-2003 categories of PER, LOC, ORG, and MISC. Its evaluation is carried out on a variety of machine learning algorithms and favorable results are achieved.
Tasks	Named Entity Recognition
Published	2018-10-08
URL	http://arxiv.org/abs/1810.03430v1
PDF	http://arxiv.org/pdf/1810.03430v1.pdf
PWC	https://paperswithcode.com/paper/cross-script-hindi-english-ner-corpus-from
Repo
Framework

Augmented Skeleton Space Transfer for Depth-based Hand Pose Estimation


Title	Augmented Skeleton Space Transfer for Depth-based Hand Pose Estimation
Authors	Seungryul Baek, Kwang In Kim, Tae-Kyun Kim
Abstract	Crucial to the success of training a depth-based 3D hand pose estimator (HPE) is the availability of comprehensive datasets covering diverse camera perspectives, shapes, and pose variations. However, collecting such annotated datasets is challenging. We propose to complete existing databases by generating new database entries. The key idea is to synthesize data in the skeleton space (instead of doing so in the depth-map space) which enables an easy and intuitive way of manipulating data entries. Since the skeleton entries generated in this way do not have the corresponding depth map entries, we exploit them by training a separate hand pose generator (HPG) which synthesizes the depth map from the skeleton entries. By training the HPG and HPE in a single unified optimization framework enforcing that 1) the HPE agrees with the paired depth and skeleton entries; and 2) the HPG-HPE combination satisfies the cyclic consistency (both the input and the output of HPG-HPE are skeletons) observed via the newly generated unpaired skeletons, our algorithm constructs a HPE which is robust to variations that go beyond the coverage of the existing database. Our training algorithm adopts the generative adversarial networks (GAN) training process. As a by-product, we obtain a hand pose discriminator (HPD) that is capable of picking out realistic hand poses. Our algorithm exploits this capability to refine the initial skeleton estimates in testing, further improving the accuracy. We test our algorithm on four challenging benchmark datasets (ICVL, MSRA, NYU and Big Hand 2.2M datasets) and demonstrate that our approach outperforms or is on par with state-of-the-art methods quantitatively and qualitatively.
Tasks	Hand Pose Estimation, Pose Estimation
Published	2018-05-11
URL	http://arxiv.org/abs/1805.04497v1
PDF	http://arxiv.org/pdf/1805.04497v1.pdf
PWC	https://paperswithcode.com/paper/augmented-skeleton-space-transfer-for-depth
Repo
Framework

Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation


Title	Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation
Authors	Jiwoon Ahn, Suha Kwak
Abstract	The deficiency of segmentation labels is one of the main obstacles to semantic segmentation in the wild. To alleviate this issue, we present a novel framework that generates segmentation labels of images given their image-level class labels. In this weakly supervised setting, trained models have been known to segment local discriminative parts rather than the entire object area. Our solution is to propagate such local responses to nearby areas which belong to the same semantic entity. To this end, we propose a Deep Neural Network (DNN) called AffinityNet that predicts semantic affinity between a pair of adjacent image coordinates. The semantic propagation is then realized by random walk with the affinities predicted by AffinityNet. More importantly, the supervision employed to train AffinityNet is given by the initial discriminative part segmentation, which is incomplete as a segmentation annotation but sufficient for learning semantic affinities within small image areas. Thus the entire framework relies only on image-level class labels and does not require any extra data or annotations. On the PASCAL VOC 2012 dataset, a DNN learned with segmentation labels generated by our method outperforms previous models trained with the same level of supervision, and is even as competitive as those relying on stronger supervision.
Tasks	Semantic Segmentation, Weakly-Supervised Semantic Segmentation
Published	2018-03-28
URL	http://arxiv.org/abs/1803.10464v2
PDF	http://arxiv.org/pdf/1803.10464v2.pdf
PWC	https://paperswithcode.com/paper/learning-pixel-level-semantic-affinity-with
Repo
Framework

Articulatory information and Multiview Features for Large Vocabulary Continuous Speech Recognition


Title	Articulatory information and Multiview Features for Large Vocabulary Continuous Speech Recognition
Authors	Vikramjit Mitra, Wen Wang, Chris Bartels, Horacio Franco, Dimitra Vergyri
Abstract	This paper explores the use of multi-view features and their discriminative transforms in a convolutional deep neural network (CNN) architecture for a continuous large vocabulary speech recognition task. Mel-filterbank energies and perceptually motivated forced damped oscillator coefficient (DOC) features are used after feature-space maximum-likelihood linear regression (fMLLR) transforms, which are combined and fed as a multi-view feature to a single CNN acoustic model. Use of multi-view feature representation demonstrated significant reduction in word error rates (WERs) compared to the use of individual features by themselves. In addition, when articulatory information was used as an additional input to a fused deep neural network (DNN) and CNN acoustic model, it was found to demonstrate further reduction in WER for the Switchboard subset and the CallHome subset (containing partly non-native accented speech) of the NIST 2000 conversational telephone speech test set, reducing the error rate by 12% relative to the baseline in both cases. This work shows that multi-view features in association with articulatory information can improve speech recognition robustness to spontaneous and non-native speech.
Tasks	Large Vocabulary Continuous Speech Recognition, Speech Recognition
Published	2018-02-16
URL	http://arxiv.org/abs/1802.05853v1
PDF	http://arxiv.org/pdf/1802.05853v1.pdf
PWC	https://paperswithcode.com/paper/articulatory-information-and-multiview
Repo
Framework

Sparse component separation from Poisson measurements


Title	Sparse component separation from Poisson measurements
Authors	I. El Hamzaoui, J. Bobin
Abstract	Blind source separation (BSS) aims at recovering signals from mixtures. This problem has been extensively studied in cases where the mixtures are contaminated with additive Gaussian noise. However, it is not well suited to describe data that are corrupted with Poisson measurements such as in low photon count optics or in high-energy astronomical imaging (e.g. observations from the Chandra or Fermi telescopes). To that purpose, we propose a novel BSS algorithm coined pGMCA that specifically tackles the blind separation of sparse sources from Poisson measurements.
Tasks
Published	2018-12-11
URL	http://arxiv.org/abs/1812.04370v1
PDF	http://arxiv.org/pdf/1812.04370v1.pdf
PWC	https://paperswithcode.com/paper/sparse-component-separation-from-poisson
Repo
Framework

An LP-based hyperparameter optimization model for language modeling


Title	An LP-based hyperparameter optimization model for language modeling
Authors	Amir Hossein Akhavan Rahnama, Mehdi Toloo, Nezer Jacob Zaidenberg
Abstract	In order to find hyperparameters for a machine learning model, algorithms such as grid search or random search are used over the space of possible values of the models hyperparameters. These search algorithms opt the solution that minimizes a specific cost function. In language models, perplexity is one of the most popular cost functions. In this study, we propose a fractional nonlinear programming model that finds the optimal perplexity value. The special structure of the model allows us to approximate it by a linear programming model that can be solved using the well-known simplex algorithm. To the best of our knowledge, this is the first attempt to use optimization techniques to find perplexity values in the language modeling literature. We apply our model to find hyperparameters of a language model and compare it to the grid search algorithm. Furthermore, we illustrating that it results in lower perplexity values. We perform this experiment on a real-world dataset from SwiftKey to validate our proposed approach.
Tasks	Hyperparameter Optimization, Language Modelling
Published	2018-03-29
URL	http://arxiv.org/abs/1803.10927v1
PDF	http://arxiv.org/pdf/1803.10927v1.pdf
PWC	https://paperswithcode.com/paper/an-lp-based-hyperparameter-optimization-model
Repo
Framework

Structured low-rank matrix completion for forecasting in time series analysis


Title	Structured low-rank matrix completion for forecasting in time series analysis
Authors	Jonathan Gillard, Konstantin Usevich
Abstract	In this paper we consider the low-rank matrix completion problem with specific application to forecasting in time series analysis. Briefly, the low-rank matrix completion problem is the problem of imputing missing values of a matrix under a rank constraint. We consider a matrix completion problem for Hankel matrices and a convex relaxation based on the nuclear norm. Based on new theoretical results and a number of numerical and real examples, we investigate the cases when the proposed approach can work. Our results highlight the importance of choosing a proper weighting scheme for the known observations.
Tasks	Low-Rank Matrix Completion, Matrix Completion, Time Series, Time Series Analysis
Published	2018-02-22
URL	http://arxiv.org/abs/1802.08242v1
PDF	http://arxiv.org/pdf/1802.08242v1.pdf
PWC	https://paperswithcode.com/paper/structured-low-rank-matrix-completion-for
Repo
Framework

MsCGAN: Multi-scale Conditional Generative Adversarial Networks for Person Image Generation


Title	MsCGAN: Multi-scale Conditional Generative Adversarial Networks for Person Image Generation
Authors	Wei Tang, Gui Li, Xinyuan Bao, Teng Li
Abstract	To synthesize high-quality person images with arbitrary poses is challenging. In this paper, we propose a novel Multi-scale Conditional Generative Adversarial Networks (MsCGAN), aiming to convert the input conditional person image to a synthetic image of any given target pose, whose appearance and the texture are consistent with the input image. MsCGAN is a multi-scale adversarial network consisting of two generators and two discriminators. One generator transforms the conditional person image into a coarse image of the target pose globally, and the other is to enhance the detailed quality of the synthetic person image through a local reinforcement network. The outputs of the two generators are then merged into a synthetic, discriminant and high-resolution image. On the other hand, the synthetic image is downsampled to multiple resolutions as the input to multi-scale discriminator networks. The proposed multi-scale generators and discriminators handling different levels of visual features can benefit to synthesizing high-resolution person images with realistic appearance and texture. Experiments are conducted on the Market-1501 and DeepFashion datasets to evaluate the proposed model, and both qualitative and quantitative results demonstrate the superior performance of the proposed MsCGAN.
Tasks	Image Generation
Published	2018-10-19
URL	https://arxiv.org/abs/1810.08534v3
PDF	https://arxiv.org/pdf/1810.08534v3.pdf
PWC	https://paperswithcode.com/paper/mscgan-multi-scale-conditional-generative
Repo
Framework

A Mathematical Framework for Superintelligent Machines


Title	A Mathematical Framework for Superintelligent Machines
Authors	Daniel J. Buehrer
Abstract	We describe a class calculus that is expressive enough to describe and improve its own learning process. It can design and debug programs that satisfy given input/output constraints, based on its ontology of previously learned programs. It can improve its own model of the world by checking the actual results of the actions of its robotic activators. For instance, it could check the black box of a car crash to determine if it was probably caused by electric failure, a stuck electronic gate, dark ice, or some other condition that it must add to its ontology in order to meet its sub-goal of preventing such crashes in the future. Class algebra basically defines the eval/eval-1 Galois connection between the residuated Boolean algebras of 1. equivalence classes and super/sub classes of class algebra type expressions, and 2. a residual Boolean algebra of biclique relationships. It distinguishes which formulas are equivalent, entailed, or unrelated, based on a simplification algorithm that may be thought of as producing a unique pair of Karnaugh maps that describe the rough sets of maximal bicliques of relations. Such maps divide the n-dimensional space of up to 2n-1 conjunctions of up to n propositions into clopen (i.e. a closed set of regions and their boundaries) causal sets. This class algebra is generalized to type-2 fuzzy class algebra by using relative frequencies as probabilities. It is also generalized to a class calculus involving assignments that change the states of programs. INDEX TERMS 4-valued Boolean Logic, Artificial Intelligence, causal sets, class algebra, consciousness, intelligent design, IS-A hierarchy, mathematical logic, meta-theory, pointless topological space, residuated lattices, rough sets, type-2 fuzzy sets
Tasks
Published	2018-04-10
URL	http://arxiv.org/abs/1804.03301v1
PDF	http://arxiv.org/pdf/1804.03301v1.pdf
PWC	https://paperswithcode.com/paper/a-mathematical-framework-for-superintelligent
Repo
Framework

Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter


Title	Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter
Authors	Lijun Wu, Xu Tan, Di He, Fei Tian, Tao Qin, Jianhuang Lai, Tie-Yan Liu
Abstract	Neural machine translation usually adopts autoregressive models and suffers from exposure bias as well as the consequent error propagation problem. Many previous works have discussed the relationship between error propagation and the \emph{accuracy drop} (i.e., the left part of the translated sentence is often better than its right part in left-to-right decoding models) problem. In this paper, we conduct a series of analyses to deeply understand this problem and get several interesting findings. (1) The role of error propagation on accuracy drop is overstated in the literature, although it indeed contributes to the accuracy drop problem. (2) Characteristics of a language play a more important role in causing the accuracy drop: the left part of the translation result in a right-branching language (e.g., English) is more likely to be more accurate than its right part, while the right part is more accurate for a left-branching language (e.g., Japanese). Our discoveries are confirmed on different model structures including Transformer and RNN, and in other sequence generation tasks such as text summarization.
Tasks	Machine Translation, Text Summarization
Published	2018-09-01
URL	http://arxiv.org/abs/1809.00120v2
PDF	http://arxiv.org/pdf/1809.00120v2.pdf
PWC	https://paperswithcode.com/paper/beyond-error-propagation-in-neural-machine
Repo
Framework

Generalizing Bottleneck Problems


Title	Generalizing Bottleneck Problems
Authors	Hsiang Hsu, Shahab Asoodeh, Salman Salamatian, Flavio P. Calmon
Abstract	Given a pair of random variables $(X,Y)\sim P_{XY}$ and two convex functions $f_1$ and $f_2$, we introduce two bottleneck functionals as the lower and upper boundaries of the two-dimensional convex set that consists of the pairs $\left(I_{f_1}(W; X), I_{f_2}(W; Y)\right)$, where $I_f$ denotes $f$-information and $W$ varies over the set of all discrete random variables satisfying the Markov condition $W \to X \to Y$. Applying Witsenhausen and Wyner’s approach, we provide an algorithm for computing boundaries of this set for $f_1$, $f_2$, and discrete $P_{XY}$. In the binary symmetric case, we fully characterize the set when (i) $f_1(t)=f_2(t)=t\log t$, (ii) $f_1(t)=f_2(t)=t^2-1$, and (iii) $f_1$ and $f_2$ are both $\ell^\beta$ norm function for $\beta \geq 2$. We then argue that upper and lower boundaries in (i) correspond to Mrs. Gerber’s Lemma and its inverse (which we call Mr. Gerber’s Lemma), in (ii) correspond to estimation-theoretic variants of Information Bottleneck and Privacy Funnel, and in (iii) correspond to Arimoto Information Bottleneck and Privacy Funnel.
Tasks
Published	2018-02-16
URL	http://arxiv.org/abs/1802.05861v3
PDF	http://arxiv.org/pdf/1802.05861v3.pdf
PWC	https://paperswithcode.com/paper/generalizing-bottleneck-problems
Repo
Framework