October 19, 2019

2840 words 14 mins read

Paper Group ANR 290

Design of a nickel-base superalloy using a neural network. RNNs as psycholinguistic subjects: Syntactic state and grammatical dependency. Closed-form Marginal Likelihood in Gamma-Poisson Matrix Factorization. D$^2$: Decentralized Training over Decentralized Data. Detecting Deceptive Reviews using Generative Adversarial Networks. Physics-driven Fire …

Design of a nickel-base superalloy using a neural network


Title	Design of a nickel-base superalloy using a neural network
Authors	B. D. Conduit, N. G. Jones, H. J. Stone, G. J. Conduit
Abstract	A new computational tool has been developed to model, discover, and optimize new alloys that simultaneously satisfy up to eleven physical criteria. An artificial neural network is trained from pre-existing materials data that enables the prediction of individual material properties both as a function of composition and heat treatment routine, which allows it to optimize the material properties to search for the material with properties most likely to exceed a target criteria. We design a new polycrystalline nickel-base superalloy with the optimal combination of cost, density, gamma’ phase content and solvus, phase stability, fatigue life, yield stress, ultimate tensile strength, stress rupture, oxidation resistance, and tensile elongation. Experimental data demonstrates that the proposed alloy fulfills the computational predictions, possessing multiple physical properties, particularly oxidation resistance and yield stress, that exceed existing commercially available alloys.
Tasks
Published	2018-03-08
URL	http://arxiv.org/abs/1803.03039v1
PDF	http://arxiv.org/pdf/1803.03039v1.pdf
PWC	https://paperswithcode.com/paper/design-of-a-nickel-base-superalloy-using-a
Repo
Framework

RNNs as psycholinguistic subjects: Syntactic state and grammatical dependency


Title	RNNs as psycholinguistic subjects: Syntactic state and grammatical dependency
Authors	Richard Futrell, Ethan Wilcox, Takashi Morita, Roger Levy
Abstract	Recurrent neural networks (RNNs) are the state of the art in sequence modeling for natural language. However, it remains poorly understood what grammatical characteristics of natural language they implicitly learn and represent as a consequence of optimizing the language modeling objective. Here we deploy the methods of controlled psycholinguistic experimentation to shed light on to what extent RNN behavior reflects incremental syntactic state and grammatical dependency representations known to characterize human linguistic behavior. We broadly test two publicly available long short-term memory (LSTM) English sequence models, and learn and test a new Japanese LSTM. We demonstrate that these models represent and maintain incremental syntactic state, but that they do not always generalize in the same way as humans. Furthermore, none of our models learn the appropriate grammatical dependency configurations licensing reflexive pronouns or negative polarity items.
Tasks	Language Modelling
Published	2018-09-05
URL	http://arxiv.org/abs/1809.01329v1
PDF	http://arxiv.org/pdf/1809.01329v1.pdf
PWC	https://paperswithcode.com/paper/rnns-as-psycholinguistic-subjects-syntactic
Repo
Framework

Closed-form Marginal Likelihood in Gamma-Poisson Matrix Factorization


Title	Closed-form Marginal Likelihood in Gamma-Poisson Matrix Factorization
Authors	Louis Filstroff, Alberto Lumbreras, Cédric Févotte
Abstract	We present novel understandings of the Gamma-Poisson (GaP) model, a probabilistic matrix factorization model for count data. We show that GaP can be rewritten free of the score/activation matrix. This gives us new insights about the estimation of the topic/dictionary matrix by maximum marginal likelihood estimation. In particular, this explains the robustness of this estimator to over-specified values of the factorization rank, especially its ability to automatically prune irrelevant dictionary columns, as empirically observed in previous work. The marginalization of the activation matrix leads in turn to a new Monte Carlo Expectation-Maximization algorithm with favorable properties.
Tasks
Published	2018-01-05
URL	http://arxiv.org/abs/1801.01799v2
PDF	http://arxiv.org/pdf/1801.01799v2.pdf
PWC	https://paperswithcode.com/paper/closed-form-marginal-likelihood-in-gamma
Repo
Framework

D$^2$: Decentralized Training over Decentralized Data


Title	D$^2$: Decentralized Training over Decentralized Data
Authors	Hanlin Tang, Xiangru Lian, Ming Yan, Ce Zhang, Ji Liu
Abstract	While training a machine learning model using multiple workers, each of which collects data from their own data sources, it would be most useful when the data collected from different workers can be {\em unique} and {\em different}. Ironically, recent analysis of decentralized parallel stochastic gradient descent (D-PSGD) relies on the assumption that the data hosted on different workers are {\em not too different}. In this paper, we ask the question: {\em Can we design a decentralized parallel stochastic gradient descent algorithm that is less sensitive to the data variance across workers?} In this paper, we present D$^2$, a novel decentralized parallel stochastic gradient descent algorithm designed for large data variance \xr{among workers} (imprecisely, “decentralized” data). The core of D$^2$ is a variance blackuction extension of the standard D-PSGD algorithm, which improves the convergence rate from $O\left({\sigma \over \sqrt{nT}} + {(n\zeta^2)^{\frac{1}{3}} \over T^{2/3}}\right)$ to $O\left({\sigma \over \sqrt{nT}}\right)$ where $\zeta^{2}$ denotes the variance among data on different workers. As a result, D$^2$ is robust to data variance among workers. We empirically evaluated D$^2$ on image classification tasks where each worker has access to only the data of a limited set of labels, and find that D$^2$ significantly outperforms D-PSGD.
Tasks	Image Classification
Published	2018-03-19
URL	http://arxiv.org/abs/1803.07068v2
PDF	http://arxiv.org/pdf/1803.07068v2.pdf
PWC	https://paperswithcode.com/paper/d2-decentralized-training-over-decentralized-1
Repo
Framework

Detecting Deceptive Reviews using Generative Adversarial Networks


Title	Detecting Deceptive Reviews using Generative Adversarial Networks
Authors	Hojjat Aghakhani, Aravind Machiry, Shirin Nilizadeh, Christopher Kruegel, Giovanni Vigna
Abstract	In the past few years, consumer review sites have become the main target of deceptive opinion spam, where fictitious opinions or reviews are deliberately written to sound authentic. Most of the existing work to detect the deceptive reviews focus on building supervised classifiers based on syntactic and lexical patterns of an opinion. With the successful use of Neural Networks on various classification applications, in this paper, we propose FakeGAN a system that for the first time augments and adopts Generative Adversarial Networks (GANs) for a text classification task, in particular, detecting deceptive reviews. Unlike standard GAN models which have a single Generator and Discriminator model, FakeGAN uses two discriminator models and one generative model. The generator is modeled as a stochastic policy agent in reinforcement learning (RL), and the discriminators use Monte Carlo search algorithm to estimate and pass the intermediate action-value as the RL reward to the generator. Providing the generator model with two discriminator models avoids the mod collapse issue by learning from both distributions of truthful and deceptive reviews. Indeed, our experiments show that using two discriminators provides FakeGAN high stability, which is a known issue for GAN architectures. While FakeGAN is built upon a semi-supervised classifier, known for less accuracy, our evaluation results on a dataset of TripAdvisor hotel reviews show the same performance in terms of accuracy as of the state-of-the-art approaches that apply supervised machine learning. These results indicate that GANs can be effective for text classification tasks. Specifically, FakeGAN is effective at detecting deceptive reviews.
Tasks	Text Classification
Published	2018-05-25
URL	http://arxiv.org/abs/1805.10364v1
PDF	http://arxiv.org/pdf/1805.10364v1.pdf
PWC	https://paperswithcode.com/paper/detecting-deceptive-reviews-using-generative
Repo
Framework

Physics-driven Fire Modeling from Multi-view Images


Title	Physics-driven Fire Modeling from Multi-view Images
Authors	Garoe Dorta, Luca Benedetti, Dmitry Kit, Yong-Liang Yang
Abstract	Fire effects are widely used in various computer graphics applications such as visual effects and video games. Modeling the shape and appearance of fire phenomenon is challenging as the underlying effects are driven by complex laws of physics. State-of-the-art fire modeling techniques rely on sophisticated physical simulations which require intensive parameter tuning, or use simplifications which produce physically invalid results. In this paper, we present a novel method of reconstructing physically valid fire models from multi-view stereo images. Our method, for the first time, provides plausible estimation of physical properties (e.g., temperature, density) of a fire volume using RGB cameras. This allows for a number of novel phenomena such as global fire illumination effects. The effectiveness and usefulness of our method are tested by generating fire models from a variety of input data, and applying the reconstructed fire models for realistic illumination of virtual scenes.
Tasks	Physical Simulations
Published	2018-04-14
URL	http://arxiv.org/abs/1804.05261v1
PDF	http://arxiv.org/pdf/1804.05261v1.pdf
PWC	https://paperswithcode.com/paper/physics-driven-fire-modeling-from-multi-view
Repo
Framework

Evolution of Visual Odometry Techniques


Title	Evolution of Visual Odometry Techniques
Authors	Shashi Poddar, Rahul Kottath, Vinod Karar
Abstract	With rapid advancements in the area of mobile robotics and industrial automation, a growing need has arisen towards accurate navigation and localization of moving objects. Camera based motion estimation is one such technique which is gaining huge popularity owing to its simplicity and use of limited resources in generating motion path. In this paper, an attempt is made to introduce this topic for beginners covering different aspects of vision based motion estimation task. The evolution of VO schemes over last few decades is discussed under two broad categories, that is, geometric and non-geometric approaches. The geometric approaches are further detailed under three different classes, that is, feature-based, appearance-based, and a hybrid of feature and appearance based schemes. The non-geometric approach is one of the recent paradigm shift from conventional pose estimation technique and is thus discussed in a separate section. Towards the end, a list of different datasets for visual odometry and allied research areas are provided for a ready reference.
Tasks	Motion Estimation, Pose Estimation, Visual Odometry
Published	2018-04-30
URL	http://arxiv.org/abs/1804.11142v1
PDF	http://arxiv.org/pdf/1804.11142v1.pdf
PWC	https://paperswithcode.com/paper/evolution-of-visual-odometry-techniques
Repo
Framework

Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition


Title	Joint Modeling of Accents and Acoustics for Multi-Accent Speech Recognition
Authors	Xuesong Yang, Kartik Audhkhasi, Andrew Rosenberg, Samuel Thomas, Bhuvana Ramabhadran, Mark Hasegawa-Johnson
Abstract	The performance of automatic speech recognition systems degrades with increasing mismatch between the training and testing scenarios. Differences in speaker accents are a significant source of such mismatch. The traditional approach to deal with multiple accents involves pooling data from several accents during training and building a single model in multi-task fashion, where tasks correspond to individual accents. In this paper, we explore an alternate model where we jointly learn an accent classifier and a multi-task acoustic model. Experiments on the American English Wall Street Journal and British English Cambridge corpora demonstrate that our joint model outperforms the strong multi-task acoustic model baseline. We obtain a 5.94% relative improvement in word error rate on British English, and 9.47% relative improvement on American English. This illustrates that jointly modeling with accent information improves acoustic model performance.
Tasks	Speech Recognition
Published	2018-02-07
URL	http://arxiv.org/abs/1802.02656v1
PDF	http://arxiv.org/pdf/1802.02656v1.pdf
PWC	https://paperswithcode.com/paper/joint-modeling-of-accents-and-acoustics-for
Repo
Framework

Adversarial Deformation Regularization for Training Image Registration Neural Networks


Title	Adversarial Deformation Regularization for Training Image Registration Neural Networks
Authors	Yipeng Hu, Eli Gibson, Nooshin Ghavami, Ester Bonmati, Caroline M. Moore, Mark Emberton, Tom Vercauteren, J. Alison Noble, Dean C. Barratt
Abstract	We describe an adversarial learning approach to constrain convolutional neural network training for image registration, replacing heuristic smoothness measures of displacement fields often used in these tasks. Using minimally-invasive prostate cancer intervention as an example application, we demonstrate the feasibility of utilizing biomechanical simulations to regularize a weakly-supervised anatomical-label-driven registration network for aligning pre-procedural magnetic resonance (MR) and 3D intra-procedural transrectal ultrasound (TRUS) images. A discriminator network is optimized to distinguish the registration-predicted displacement fields from the motion data simulated by finite element analysis. During training, the registration network simultaneously aims to maximize similarity between anatomical labels that drives image alignment and to minimize an adversarial generator loss that measures divergence between the predicted- and simulated deformation. The end-to-end trained network enables efficient and fully-automated registration that only requires an MR and TRUS image pair as input, without anatomical labels or simulated data during inference. 108 pairs of labelled MR and TRUS images from 76 prostate cancer patients and 71,500 nonlinear finite-element simulations from 143 different patients were used for this study. We show that, with only gland segmentation as training labels, the proposed method can help predict physically plausible deformation without any other smoothness penalty. Based on cross-validation experiments using 834 pairs of independent validation landmarks, the proposed adversarial-regularized registration achieved a target registration error of 6.3 mm that is significantly lower than those from several other regularization methods.
Tasks	Image Registration
Published	2018-05-27
URL	http://arxiv.org/abs/1805.10665v1
PDF	http://arxiv.org/pdf/1805.10665v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-deformation-regularization-for
Repo
Framework

No Modes left behind: Capturing the data distribution effectively using GANs


Title	No Modes left behind: Capturing the data distribution effectively using GANs
Authors	Shashank Sharma, Vinay P. Namboodiri
Abstract	Generative adversarial networks (GANs) while being very versatile in realistic image synthesis, still are sensitive to the input distribution. Given a set of data that has an imbalance in the distribution, the networks are susceptible to missing modes and not capturing the data distribution. While various methods have been tried to improve training of GANs, these have not addressed the challenges of covering the full data distribution. Specifically, a generator is not penalized for missing a mode. We show that these are therefore still susceptible to not capturing the full data distribution. In this paper, we propose a simple approach that combines an encoder based objective with novel loss functions for generator and discriminator that improves the solution in terms of capturing missing modes. We validate that the proposed method results in substantial improvements through its detailed analysis on toy and real datasets. The quantitative and qualitative results demonstrate that the proposed method improves the solution for the problem of missing modes and improves training of GANs.
Tasks	Image Generation
Published	2018-02-02
URL	http://arxiv.org/abs/1802.00771v1
PDF	http://arxiv.org/pdf/1802.00771v1.pdf
PWC	https://paperswithcode.com/paper/no-modes-left-behind-capturing-the-data
Repo
Framework

Statistical Optimal Transport via Factored Couplings


Title	Statistical Optimal Transport via Factored Couplings
Authors	Aden Forrow, Jan-Christian Hütter, Mor Nitzan, Philippe Rigollet, Geoffrey Schiebinger, Jonathan Weed
Abstract	We propose a new method to estimate Wasserstein distances and optimal transport plans between two probability distributions from samples in high dimension. Unlike plug-in rules that simply replace the true distributions by their empirical counterparts, our method promotes couplings with low transport rank, a new structural assumption that is similar to the nonnegative rank of a matrix. Regularizing based on this assumption leads to drastic improvements on high-dimensional data for various tasks, including domain adaptation in single-cell RNA sequencing data. These findings are supported by a theoretical analysis that indicates that the transport rank is key in overcoming the curse of dimensionality inherent to data-driven optimal transport.
Tasks	Domain Adaptation
Published	2018-06-19
URL	http://arxiv.org/abs/1806.07348v3
PDF	http://arxiv.org/pdf/1806.07348v3.pdf
PWC	https://paperswithcode.com/paper/statistical-optimal-transport-via-factored
Repo
Framework

Don’t only Feel Read: Using Scene text to understand advertisements


Title	Don’t only Feel Read: Using Scene text to understand advertisements
Authors	Arka Ujjal Dey, Suman K. Ghosh, Ernest Valveny
Abstract	We propose a framework for automated classification of Advertisement Images, using not just Visual features but also Textual cues extracted from embedded text. Our approach takes inspiration from the assumption that Ad images contain meaningful textual content, that can provide discriminative semantic interpretetion, and can thus aid in classifcation tasks. To this end, we develop a framework using off-the-shelf components, and demonstrate the effectiveness of Textual cues in semantic Classfication tasks.
Tasks
Published	2018-06-21
URL	https://arxiv.org/abs/1806.08279v3
PDF	https://arxiv.org/pdf/1806.08279v3.pdf
PWC	https://paperswithcode.com/paper/dont-only-feel-read-using-scene-text-to
Repo
Framework

Hinted Networks


Title	Hinted Networks
Authors	Joel Lamy-Poirier, Anqi Xu
Abstract	We present Hinted Networks: a collection of architectural transformations for improving the accuracies of neural network models for regression tasks, through the injection of a prior for the output prediction (i.e. a hint). We ground our investigations within the camera relocalization domain, and propose two variants, namely the Hinted Embedding and Hinted Residual networks, both applied to the PoseNet base model for regressing camera pose from an image. Our evaluations show practical improvements in localization accuracy for standard outdoor and indoor localization datasets, without using additional information. We further assess the range of accuracy gains within an aerial-view localization setup, simulated across vast areas at different times of the year.
Tasks	Camera Relocalization
Published	2018-12-15
URL	http://arxiv.org/abs/1812.06297v1
PDF	http://arxiv.org/pdf/1812.06297v1.pdf
PWC	https://paperswithcode.com/paper/hinted-networks
Repo
Framework

FairGAN: Fairness-aware Generative Adversarial Networks


Title	FairGAN: Fairness-aware Generative Adversarial Networks
Authors	Depeng Xu, Shuhan Yuan, Lu Zhang, Xintao Wu
Abstract	Fairness-aware learning is increasingly important in data mining. Discrimination prevention aims to prevent discrimination in the training data before it is used to conduct predictive analysis. In this paper, we focus on fair data generation that ensures the generated data is discrimination free. Inspired by generative adversarial networks (GAN), we present fairness-aware generative adversarial networks, called FairGAN, which are able to learn a generator producing fair data and also preserving good data utility. Compared with the naive fair data generation models, FairGAN further ensures the classifiers which are trained on generated data can achieve fair classification on real data. Experiments on a real dataset show the effectiveness of FairGAN.
Tasks
Published	2018-05-28
URL	http://arxiv.org/abs/1805.11202v1
PDF	http://arxiv.org/pdf/1805.11202v1.pdf
PWC	https://paperswithcode.com/paper/fairgan-fairness-aware-generative-adversarial
Repo
Framework

A Deep Learning Model with Hierarchical LSTMs and Supervised Attention for Anti-Phishing


Title	A Deep Learning Model with Hierarchical LSTMs and Supervised Attention for Anti-Phishing
Authors	Minh Nguyen, Toan Nguyen, Thien Huu Nguyen
Abstract	Anti-phishing aims to detect phishing content/documents in a pool of textual data. This is an important problem in cybersecurity that can help to guard users from fraudulent information. Natural language processing (NLP) offers a natural solution for this problem as it is capable of analyzing the textual content to perform intelligent recognition. In this work, we investigate state-of-the-art techniques for text categorization in NLP to address the problem of anti-phishing for emails (i.e, predicting if an email is phishing or not). These techniques are based on deep learning models that have attracted much attention from the community recently. In particular, we present a framework with hierarchical long short-term memory networks (H-LSTMs) and attention mechanisms to model the emails simultaneously at the word and the sentence level. Our expectation is to produce an effective model for anti-phishing and demonstrate the effectiveness of deep learning for problems in cybersecurity.
Tasks	Text Categorization
Published	2018-05-03
URL	http://arxiv.org/abs/1805.01554v1
PDF	http://arxiv.org/pdf/1805.01554v1.pdf
PWC	https://paperswithcode.com/paper/a-deep-learning-model-with-hierarchical-lstms
Repo
Framework