July 26, 2019

3159 words 15 mins read

Paper Group ANR 776

Native Language Identification on Text and Speech. Pipeline Generative Adversarial Networks for Facial Images Generation with Multiple Attributes. A Distributed Learning Dynamics in Social Groups. Biologically Inspired Feedforward Supervised Learning for Deep Self-Organizing Map Networks. BENCHIP: Benchmarking Intelligence Processors. “Attention” f …

Native Language Identification on Text and Speech


Title	Native Language Identification on Text and Speech
Authors	Marcos Zampieri, Alina Maria Ciobanu, Liviu P. Dinu
Abstract	This paper presents an ensemble system combining the output of multiple SVM classifiers to native language identification (NLI). The system was submitted to the NLI Shared Task 2017 fusion track which featured students essays and spoken responses in form of audio transcriptions and iVectors by non-native English speakers of eleven native languages. Our system competed in the challenge under the team name ZCD and was based on an ensemble of SVM classifiers trained on character n-grams achieving 83.58% accuracy and ranking 3rd in the shared task.
Tasks	Language Identification, Native Language Identification
Published	2017-07-22
URL	http://arxiv.org/abs/1707.07182v1
PDF	http://arxiv.org/pdf/1707.07182v1.pdf
PWC	https://paperswithcode.com/paper/native-language-identification-on-text-and
Repo
Framework

Pipeline Generative Adversarial Networks for Facial Images Generation with Multiple Attributes


Title	Pipeline Generative Adversarial Networks for Facial Images Generation with Multiple Attributes
Authors	Ziqiang Zheng, Zhibin Yu, Haiyong Zheng, Chao Wang, Nan Wang
Abstract	Generative Adversarial Networks are proved to be efficient on various kinds of image generation tasks. However, it is still a challenge if we want to generate images precisely. Many researchers focus on how to generate images with one attribute. But image generation under multiple attributes is still a tough work. In this paper, we try to generate a variety of face images under multiple constraints using a pipeline process. The Pip-GAN (Pipeline Generative Adversarial Network) we present employs a pipeline network structure which can generate a complex facial image step by step using a neutral face image. We applied our method on two face image databases and demonstrate its ability to generate convincing novel images of unseen identities under multiple conditions previously.
Tasks	Image Generation
Published	2017-11-29
URL	http://arxiv.org/abs/1711.10742v1
PDF	http://arxiv.org/pdf/1711.10742v1.pdf
PWC	https://paperswithcode.com/paper/pipeline-generative-adversarial-networks-for
Repo
Framework


Title	A Distributed Learning Dynamics in Social Groups
Authors	L. Elisa Celis, Peter M. Krafft, Nisheeth K. Vishnoi
Abstract	We study a distributed learning process observed in human groups and other social animals. This learning process appears in settings in which each individual in a group is trying to decide over time, in a distributed manner, which option to select among a shared set of options. Specifically, we consider a stochastic dynamics in a group in which every individual selects an option in the following two-step process: (1) select a random individual and observe the option that individual chose in the previous time step, and (2) adopt that option if its stochastic quality was good at that time step. Various instantiations of such distributed learning appear in nature, and have also been studied in the social science literature. From the perspective of an individual, an attractive feature of this learning process is that it is a simple heuristic that requires extremely limited computational capacities. But what does it mean for the group – could such a simple, distributed and essentially memoryless process lead the group as a whole to perform optimally? We show that the answer to this question is yes – this distributed learning is highly effective at identifying the best option and is close to optimal for the group overall. Our analysis also gives quantitative bounds that show fast convergence of these stochastic dynamics. Prior to our work the only theoretical work related to such learning dynamics has been either in deterministic special cases or in the asymptotic setting. Finally, we observe that our infinite population dynamics is a stochastic variant of the classic multiplicative weights update (MWU) method. Consequently, we arrive at the following interesting converse: the learning dynamics on a finite population considered here can be viewed as a novel distributed and low-memory implementation of the classic MWU method.
Tasks
Published	2017-05-08
URL	http://arxiv.org/abs/1705.03414v1
PDF	http://arxiv.org/pdf/1705.03414v1.pdf
PWC	https://paperswithcode.com/paper/a-distributed-learning-dynamics-in-social
Repo
Framework

Biologically Inspired Feedforward Supervised Learning for Deep Self-Organizing Map Networks


Title	Biologically Inspired Feedforward Supervised Learning for Deep Self-Organizing Map Networks
Authors	Takashi Shinozaki
Abstract	In this study, we propose a novel deep neural network and its supervised learning method that uses a feedforward supervisory signal. The method is inspired by the human visual system and performs human-like association-based learning without any backward error propagation. The feedforward supervisory signal that produces the correct result is preceded by the target signal and associates its confirmed label with the classification result of the target signal. It effectively uses a large amount of information from the feedforward signal, and forms a continuous and rich learning representation. The method is validated using visual recognition tasks on the MNIST handwritten dataset.
Tasks
Published	2017-10-26
URL	http://arxiv.org/abs/1710.09574v1
PDF	http://arxiv.org/pdf/1710.09574v1.pdf
PWC	https://paperswithcode.com/paper/biologically-inspired-feedforward-supervised
Repo
Framework

BENCHIP: Benchmarking Intelligence Processors


Title	BENCHIP: Benchmarking Intelligence Processors
Authors	Jinhua Tao, Zidong Du, Qi Guo, Huiying Lan, Lei Zhang, Shengyuan Zhou, Lingjie Xu, Cong Liu, Haifeng Liu, Shan Tang, Allen Rush, Willian Chen, Shaoli Liu, Yunji Chen, Tianshi Chen
Abstract	The increasing attention on deep learning has tremendously spurred the design of intelligence processing hardware. The variety of emerging intelligence processors requires standard benchmarks for fair comparison and system optimization (in both software and hardware). However, existing benchmarks are unsuitable for benchmarking intelligence processors due to their non-diversity and nonrepresentativeness. Also, the lack of a standard benchmarking methodology further exacerbates this problem. In this paper, we propose BENCHIP, a benchmark suite and benchmarking methodology for intelligence processors. The benchmark suite in BENCHIP consists of two sets of benchmarks: microbenchmarks and macrobenchmarks. The microbenchmarks consist of single-layer networks. They are mainly designed for bottleneck analysis and system optimization. The macrobenchmarks contain state-of-the-art industrial networks, so as to offer a realistic comparison of different platforms. We also propose a standard benchmarking methodology built upon an industrial software stack and evaluation metrics that comprehensively reflect the various characteristics of the evaluated intelligence processors. BENCHIP is utilized for evaluating various hardware platforms, including CPUs, GPUs, and accelerators. BENCHIP will be open-sourced soon.
Tasks
Published	2017-10-23
URL	http://arxiv.org/abs/1710.08315v2
PDF	http://arxiv.org/pdf/1710.08315v2.pdf
PWC	https://paperswithcode.com/paper/benchip-benchmarking-intelligence-processors
Repo
Framework

“Attention” for Detecting Unreliable News in the Information Age


Title	“Attention” for Detecting Unreliable News in the Information Age
Authors	Venkatesh Duppada
Abstract	An Unreliable news is any piece of information which is false or misleading, deliberately spread to promote political, ideological and financial agendas. Recently the problem of unreliable news has got a lot of attention as the number instances of using news and social media outlets for propaganda have increased rapidly. This poses a serious threat to society, which calls for technology to automatically and reliably identify unreliable news sources. This paper is an effort made in this direction to build systems for detecting unreliable news articles. In this paper, various NLP algorithms were built and evaluated on Unreliable News Data 2017 dataset. Variants of hierarchical attention networks (HAN) are presented for encoding and classifying news articles which achieve the best results of 0.944 ROC-AUC. Finally, Attention layer weights are visualized to understand and give insight into the decisions made by HANs. The results obtained are very promising and encouraging to deploy and use these systems in the real world to mitigate the problem of unreliable news.
Tasks
Published	2017-11-03
URL	http://arxiv.org/abs/1711.01362v1
PDF	http://arxiv.org/pdf/1711.01362v1.pdf
PWC	https://paperswithcode.com/paper/attention-for-detecting-unreliable-news-in
Repo
Framework

Verb Physics: Relative Physical Knowledge of Actions and Objects


Title	Verb Physics: Relative Physical Knowledge of Actions and Objects
Authors	Maxwell Forbes, Yejin Choi
Abstract	Learning commonsense knowledge from natural language text is nontrivial due to reporting bias: people rarely state the obvious, e.g., “My house is bigger than me.” However, while rarely stated explicitly, this trivial everyday knowledge does influence the way people talk about the world, which provides indirect clues to reason about the world. For example, a statement like, “Tyler entered his house” implies that his house is bigger than Tyler. In this paper, we present an approach to infer relative physical knowledge of actions and objects along five dimensions (e.g., size, weight, and strength) from unstructured natural language text. We frame knowledge acquisition as joint inference over two closely related problems: learning (1) relative physical knowledge of object pairs and (2) physical implications of actions when applied to those object pairs. Empirical results demonstrate that it is possible to extract knowledge of actions and objects from language and that joint inference over different types of knowledge improves performance.
Tasks
Published	2017-06-12
URL	http://arxiv.org/abs/1706.03799v2
PDF	http://arxiv.org/pdf/1706.03799v2.pdf
PWC	https://paperswithcode.com/paper/verb-physics-relative-physical-knowledge-of
Repo
Framework

Constrained Bayesian Active Learning of Interference Channels in Cognitive Radio Networks


Title	Constrained Bayesian Active Learning of Interference Channels in Cognitive Radio Networks
Authors	Anestis Tsakmalis, Symeon Chatzinotas, Björn Ottersten
Abstract	In this paper, a sequential probing method for interference constraint learning is proposed to allow a centralized Cognitive Radio Network (CRN) accessing the frequency band of a Primary User (PU) in an underlay cognitive scenario with a designed PU protection specification. The main idea is that the CRN probes the PU and subsequently eavesdrops the reverse PU link to acquire the binary ACK/NACK packet. This feedback indicates whether the probing-induced interference is harmful or not and can be used to learn the PU interference constraint. The cognitive part of this sequential probing process is the selection of the power levels of the Secondary Users (SUs) which aims to learn the PU interference constraint with a minimum number of probing attempts while setting a limit on the number of harmful probing-induced interference events or equivalently of NACK packet observations over a time window. This constrained design problem is studied within the Active Learning (AL) framework and an optimal solution is derived and implemented with a sophisticated, accurate and fast Bayesian Learning method, the Expectation Propagation (EP). The performance of this solution is also demonstrated through numerical simulations and compared with modified versions of AL techniques we developed in earlier work.
Tasks	Active Learning
Published	2017-10-23
URL	http://arxiv.org/abs/1710.08335v1
PDF	http://arxiv.org/pdf/1710.08335v1.pdf
PWC	https://paperswithcode.com/paper/constrained-bayesian-active-learning-of
Repo
Framework

Sparsity-Based Super Resolution for SEM Images


Title	Sparsity-Based Super Resolution for SEM Images
Authors	Shahar Tsiper, Or Dicker, Idan Kaizerman, Zeev Zohar, Mordechai Segev, Yonina C. Eldar
Abstract	The scanning electron microscope (SEM) produces an image of a sample by scanning it with a focused beam of electrons. The electrons interact with the atoms in the sample, which emit secondary electrons that contain information about the surface topography and composition. The sample is scanned by the electron beam point by point, until an image of the surface is formed. Since its invention in 1942, SEMs have become paramount in the discovery and understanding of the nanometer world, and today it is extensively used for both research and in industry. In principle, SEMs can achieve resolution better than one nanometer. However, for many applications, working at sub-nanometer resolution implies an exceedingly large number of scanning points. For exactly this reason, the SEM diagnostics of microelectronic chips is performed either at high resolution (HR) over a small area or at low resolution (LR) while capturing a larger portion of the chip. Here, we employ sparse coding and dictionary learning to algorithmically enhance LR SEM images of microelectronic chips up to the level of the HR images acquired by slow SEM scans, while considerably reducing the noise. Our methodology consists of two steps: an offline stage of learning a joint dictionary from a sequence of LR and HR images of the same region in the chip, followed by a fast-online super-resolution step where the resolution of a new LR image is enhanced. We provide several examples with typical chips used in the microelectronics industry, as well as a statistical study on arbitrary images with characteristic structural features. Conceptually, our method works well when the images have similar characteristics. This work demonstrates that employing sparsity concepts can greatly improve the performance of SEM, thereby considerably increasing the scanning throughput without compromising on analysis quality and resolution.
Tasks	Dictionary Learning, Super-Resolution
Published	2017-08-29
URL	http://arxiv.org/abs/1709.02235v1
PDF	http://arxiv.org/pdf/1709.02235v1.pdf
PWC	https://paperswithcode.com/paper/sparsity-based-super-resolution-for-sem
Repo
Framework

Gaussian Quadrature for Kernel Features


Title	Gaussian Quadrature for Kernel Features
Authors	Tri Dao, Christopher De Sa, Christopher Ré
Abstract	Kernel methods have recently attracted resurgent interest, showing performance competitive with deep neural networks in tasks such as speech recognition. The random Fourier features map is a technique commonly used to scale up kernel machines, but employing the randomized feature map means that $O(\epsilon^{-2})$ samples are required to achieve an approximation error of at most $\epsilon$. We investigate some alternative schemes for constructing feature maps that are deterministic, rather than random, by approximating the kernel in the frequency domain using Gaussian quadrature. We show that deterministic feature maps can be constructed, for any $\gamma > 0$, to achieve error $\epsilon$ with $O(e^{e^\gamma} + \epsilon^{-1/\gamma})$ samples as $\epsilon$ goes to 0. Our method works particularly well with sparse ANOVA kernels, which are inspired by the convolutional layer of CNNs. We validate our methods on datasets in different domains, such as MNIST and TIMIT, showing that deterministic features are faster to generate and achieve accuracy comparable to the state-of-the-art kernel methods based on random Fourier features.
Tasks	Speech Recognition
Published	2017-09-08
URL	http://arxiv.org/abs/1709.02605v3
PDF	http://arxiv.org/pdf/1709.02605v3.pdf
PWC	https://paperswithcode.com/paper/gaussian-quadrature-for-kernel-features
Repo
Framework

Enhancing Robustness of Machine Learning Systems via Data Transformations


Title	Enhancing Robustness of Machine Learning Systems via Data Transformations
Authors	Arjun Nitin Bhagoji, Daniel Cullina, Chawin Sitawarin, Prateek Mittal
Abstract	We propose the use of data transformations as a defense against evasion attacks on ML classifiers. We present and investigate strategies for incorporating a variety of data transformations including dimensionality reduction via Principal Component Analysis and data `anti-whitening’ to enhance the resilience of machine learning, targeting both the classification and the training phase. We empirically evaluate and demonstrate the feasibility of linear transformations of data as a defense mechanism against evasion attacks using multiple real-world datasets. Our key findings are that the defense is (i) effective against the best known evasion attacks from the literature, resulting in a two-fold increase in the resources required by a white-box adversary with knowledge of the defense for a successful attack, (ii) applicable across a range of ML classifiers, including Support Vector Machines and Deep Neural Networks, and (iii) generalizable to multiple application domains, including image classification and human activity classification. \|
Tasks	Dimensionality Reduction, Image Classification
Published	2017-04-09
URL	http://arxiv.org/abs/1704.02654v4
PDF	http://arxiv.org/pdf/1704.02654v4.pdf
PWC	https://paperswithcode.com/paper/enhancing-robustness-of-machine-learning
Repo
Framework

Discrete approximations of the affine Gaussian derivative model for visual receptive fields


Title	Discrete approximations of the affine Gaussian derivative model for visual receptive fields
Authors	Tony Lindeberg
Abstract	The affine Gaussian derivative model can in several respects be regarded as a canonical model for receptive fields over a spatial image domain: (i) it can be derived by necessity from scale-space axioms that reflect structural properties of the world, (ii) it constitutes an excellent model for the receptive fields of simple cells in the primary visual cortex and (iii) it is covariant under affine image deformations, which enables more accurate modelling of image measurements under the local image deformations caused by the perspective mapping, compared to the more commonly used Gaussian derivative model based on derivatives of the rotationally symmetric Gaussian kernel. This paper presents a theory for discretizing the affine Gaussian scale-space concept underlying the affine Gaussian derivative model, so that scale-space properties hold also for the discrete implementation. Two ways of discretizing spatial smoothing with affine Gaussian kernels are presented: (i) by solving semi-discretized affine diffusion equation, which has derived by necessity from the requirements of a semi-group structure over scale as parameterized by a family of spatial covariance matrices and obeying non-creation of new structures from any finer to any coarser scale in terms of non-enhancement of local extrema and (ii) approximating these semi-discrete affine receptive fields by parameterized families of 3x3-kernels as obtained from an additional discretization along the scale direction. The latter discrete approach can be optionally complemented by spatial subsampling at coarser scales, leading to the notion of affine hybrid pyramids. Using these theoretical results, we outline hybrid architectures for discrete approximations of affine covariant receptive field families, to be used as a first processing layer for affine covariant and affine invariant visual operations at higher levels.
Tasks
Published	2017-01-09
URL	http://arxiv.org/abs/1701.02127v5
PDF	http://arxiv.org/pdf/1701.02127v5.pdf
PWC	https://paperswithcode.com/paper/discrete-approximations-of-the-affine
Repo
Framework

Organizing Multimedia Data in Video Surveillance Systems Based on Face Verification with Convolutional Neural Networks


Title	Organizing Multimedia Data in Video Surveillance Systems Based on Face Verification with Convolutional Neural Networks
Authors	Anastasiia D. Sokolova, Angelina S. Kharchevnikova, Andrey V. Savchenko
Abstract	In this paper we propose the two-stage approach of organizing information in video surveillance systems. At first, the faces are detected in each frame and a video stream is split into sequences of frames with face region of one person. Secondly, these sequences (tracks) that contain identical faces are grouped using face verification algorithms and hierarchical agglomerative clustering. Gender and age are estimated for each cluster (person) in order to facilitate the usage of the organized video collection. The particular attention is focused on the aggregation of features extracted from each frame with the deep convolutional neural networks. The experimental results of the proposed approach using YTF and IJB-A datasets demonstrated that the most accurate and fast solution is achieved for matching of normalized average of feature vectors of all frames in a track.
Tasks	Face Verification
Published	2017-09-17
URL	http://arxiv.org/abs/1709.05675v1
PDF	http://arxiv.org/pdf/1709.05675v1.pdf
PWC	https://paperswithcode.com/paper/organizing-multimedia-data-in-video
Repo
Framework

Possibilistic Fuzzy Local Information C-Means for Sonar Image Segmentation


Title	Possibilistic Fuzzy Local Information C-Means for Sonar Image Segmentation
Authors	Alina Zare, Nicholas Young, Daniel Suen, Thomas Nabelek, Aquila Galusha, James Keller
Abstract	Side-look synthetic aperture sonar (SAS) can produce very high quality images of the sea-floor. When viewing this imagery, a human observer can often easily identify various sea-floor textures such as sand ripple, hard-packed sand, sea grass and rock. In this paper, we present the Possibilistic Fuzzy Local Information C-Means (PFLICM) approach to segment SAS imagery into sea-floor regions that exhibit these various natural textures. The proposed PFLICM method incorporates fuzzy and possibilistic clustering methods and leverages (local) spatial information to perform soft segmentation. Results are shown on several SAS scenes and compared to alternative segmentation approaches.
Tasks	Semantic Segmentation
Published	2017-09-28
URL	http://arxiv.org/abs/1709.10180v1
PDF	http://arxiv.org/pdf/1709.10180v1.pdf
PWC	https://paperswithcode.com/paper/possibilistic-fuzzy-local-information-c-means
Repo
Framework

A Formal Framework to Characterize Interpretability of Procedures


Title	A Formal Framework to Characterize Interpretability of Procedures
Authors	Amit Dhurandhar, Vijay Iyengar, Ronny Luss, Karthikeyan Shanmugam
Abstract	We provide a novel notion of what it means to be interpretable, looking past the usual association with human understanding. Our key insight is that interpretability is not an absolute concept and so we define it relative to a target model, which may or may not be a human. We define a framework that allows for comparing interpretable procedures by linking it to important practical aspects such as accuracy and robustness. We characterize many of the current state-of-the-art interpretable methods in our framework portraying its general applicability.
Tasks
Published	2017-07-12
URL	http://arxiv.org/abs/1707.03886v1
PDF	http://arxiv.org/pdf/1707.03886v1.pdf
PWC	https://paperswithcode.com/paper/a-formal-framework-to-characterize
Repo
Framework