Paper Group ANR 429
Towards Crafting Text Adversarial Samples. Learning Implicit Generative Models Using Differentiable Graph Tests. Gaussian Kernel in Quantum Learning. Pyramidal RoR for Image Classification. An Integer Programming Model for Binary Knapsack Problem with Value-Related Dependencies among Elements. A Contemporary Overview of Probabilistic Latent Variabl …
Towards Crafting Text Adversarial Samples
| Title | Towards Crafting Text Adversarial Samples |
| Authors | Suranjana Samanta, Sameep Mehta |
| Abstract | Adversarial samples are strategically modified samples, which are crafted with the purpose of fooling a classifier at hand. An attacker introduces specially crafted adversarial samples to a deployed classifier, which are being mis-classified by the classifier. However, the samples are perceived to be drawn from entirely different classes and thus it becomes hard to detect the adversarial samples. Most of the prior works have been focused on synthesizing adversarial samples in the image domain. In this paper, we propose a new method of crafting adversarial text samples by modification of the original samples. Modifications of the original text samples are done by deleting or replacing the important or salient words in the text or by introducing new words in the text sample. Our algorithm works best for the datasets which have sub-categories within each of the classes of examples. While crafting adversarial samples, one of the key constraint is to generate meaningful sentences which can at pass off as legitimate from language (English) viewpoint. Experimental results on IMDB movie review dataset for sentiment analysis and Twitter dataset for gender detection show the efficiency of our proposed method. |
| Tasks | Adversarial Text, Sentiment Analysis |
| Published | 2017-07-10 |
| URL | http://arxiv.org/abs/1707.02812v1 |
| http://arxiv.org/pdf/1707.02812v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-crafting-text-adversarial-samples |
| Repo | |
| Framework | |
Learning Implicit Generative Models Using Differentiable Graph Tests
| Title | Learning Implicit Generative Models Using Differentiable Graph Tests |
| Authors | Josip Djolonga, Andreas Krause |
| Abstract | Recently, there has been a growing interest in the problem of learning rich implicit models - those from which we can sample, but can not evaluate their density. These models apply some parametric function, such as a deep network, to a base measure, and are learned end-to-end using stochastic optimization. One strategy of devising a loss function is through the statistics of two sample tests - if we can fool a statistical test, the learned distribution should be a good model of the true data. However, not all tests can easily fit into this framework, as they might not be differentiable with respect to the data points, and hence with respect to the parameters of the implicit model. Motivated by this problem, in this paper we show how two such classical tests, the Friedman-Rafsky and k-nearest neighbour tests, can be effectively smoothed using ideas from undirected graphical models - the matrix tree theorem and cardinality potentials. Moreover, as we show experimentally, smoothing can significantly increase the power of the test, which might of of independent interest. Finally, we apply our method to learn implicit models. |
| Tasks | Stochastic Optimization |
| Published | 2017-09-04 |
| URL | http://arxiv.org/abs/1709.01006v1 |
| http://arxiv.org/pdf/1709.01006v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-implicit-generative-models-using |
| Repo | |
| Framework | |
Gaussian Kernel in Quantum Learning
| Title | Gaussian Kernel in Quantum Learning |
| Authors | Arit Kumar Bishwas, Ashish Mani, Vasile Palade |
| Abstract | The Gaussian kernel is a very popular kernel function used in many machine learning algorithms, especially in support vector machines (SVMs). It is more often used than polynomial kernels when learning from nonlinear datasets, and is usually employed in formulating the classical SVM for nonlinear problems. In [3], Rebentrost et al. discussed an elegant quantum version of a least square support vector machine using quantum polynomial kernels, which is exponentially faster than the classical counterpart. This paper demonstrates a quantum version of the Gaussian kernel and analyzes its runtime complexity using the quantum random access memory (QRAM) in the context of quantum SVM. Our analysis shows that the runtime computational complexity of the quantum Gaussian kernel seems to be significantly faster as compared to its classical version. |
| Tasks | |
| Published | 2017-11-04 |
| URL | https://arxiv.org/abs/1711.01464v3 |
| https://arxiv.org/pdf/1711.01464v3.pdf | |
| PWC | https://paperswithcode.com/paper/gaussian-kernel-in-quantum-paradigm |
| Repo | |
| Framework | |
Pyramidal RoR for Image Classification
| Title | Pyramidal RoR for Image Classification |
| Authors | Ke Zhang, Liru Guo, Ce Gao, Zhenbing Zhao |
| Abstract | The Residual Networks of Residual Networks (RoR) exhibits excellent performance in the image classification task, but sharply increasing the number of feature map channels makes the characteristic information transmission incoherent, which losses a certain of information related to classification prediction, limiting the classification performance. In this paper, a Pyramidal RoR network model is proposed by analysing the performance characteristics of RoR and combining with the PyramidNet. Firstly, based on RoR, the Pyramidal RoR network model with channels gradually increasing is designed. Secondly, we analysed the effect of different residual block structures on performance, and chosen the residual block structure which best favoured the classification performance. Finally, we add an important principle to further optimize Pyramidal RoR networks, drop-path is used to avoid over-fitting and save training time. In this paper, image classification experiments were performed on CIFAR-10/100 and SVHN datasets, and we achieved the current lowest classification error rates were 2.96%, 16.40% and 1.59%, respectively. Experiments show that the Pyramidal RoR network optimization method can improve the network performance for different data sets and effectively suppress the gradient disappearance problem in DCNN training. |
| Tasks | Image Classification |
| Published | 2017-10-01 |
| URL | http://arxiv.org/abs/1710.00307v1 |
| http://arxiv.org/pdf/1710.00307v1.pdf | |
| PWC | https://paperswithcode.com/paper/pyramidal-ror-for-image-classification |
| Repo | |
| Framework | |
An Integer Programming Model for Binary Knapsack Problem with Value-Related Dependencies among Elements
| Title | An Integer Programming Model for Binary Knapsack Problem with Value-Related Dependencies among Elements |
| Authors | Davoud Mougouei, David M. W. Powers, Asghar Moeini |
| Abstract | Binary Knapsack Problem (BKP) is to select a subset of an element (item) set with the highest value while keeping the total weight within the capacity of the knapsack. This paper presents an integer programming model for a variation of BKP where the value of each element may depend on selecting or ignoring other elements. Strengths of such Value-Related Dependencies are assumed to be imprecise and hard to specify. To capture this imprecision, we have proposed modeling value-related dependencies using fuzzy graphs and their algebraic structure. |
| Tasks | |
| Published | 2017-02-22 |
| URL | http://arxiv.org/abs/1702.06662v1 |
| http://arxiv.org/pdf/1702.06662v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-integer-programming-model-for-binary |
| Repo | |
| Framework | |
A Contemporary Overview of Probabilistic Latent Variable Models
| Title | A Contemporary Overview of Probabilistic Latent Variable Models |
| Authors | Rick Farouni |
| Abstract | In this paper we provide a conceptual overview of latent variable models within a probabilistic modeling framework, an overview that emphasizes the compositional nature and the interconnectedness of the seemingly disparate models commonly encountered in statistical practice. |
| Tasks | Latent Variable Models |
| Published | 2017-06-25 |
| URL | http://arxiv.org/abs/1706.08137v2 |
| http://arxiv.org/pdf/1706.08137v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-contemporary-overview-of-probabilistic |
| Repo | |
| Framework | |
Deep Learning with Lung Segmentation and Bone Shadow Exclusion Techniques for Chest X-Ray Analysis of Lung Cancer
| Title | Deep Learning with Lung Segmentation and Bone Shadow Exclusion Techniques for Chest X-Ray Analysis of Lung Cancer |
| Authors | Yu. Gordienko, Peng Gang, Jiang Hui, Wei Zeng, Yu. Kochura, O. Alienin, O. Rokovyi, S. Stirenko |
| Abstract | The recent progress of computing, machine learning, and especially deep learning, for image recognition brings a meaningful effect for automatic detection of various diseases from chest X-ray images (CXRs). Here efficiency of lung segmentation and bone shadow exclusion techniques is demonstrated for analysis of 2D CXRs by deep learning approach to help radiologists identify suspicious lesions and nodules in lung cancer patients. Training and validation was performed on the original JSRT dataset (dataset #01), BSE-JSRT dataset, i.e. the same JSRT dataset, but without clavicle and rib shadows (dataset #02), original JSRT dataset after segmentation (dataset #03), and BSE-JSRT dataset after segmentation (dataset #04). The results demonstrate the high efficiency and usefulness of the considered pre-processing techniques in the simplified configuration even. The pre-processed dataset without bones (dataset #02) demonstrates the much better accuracy and loss results in comparison to the other pre-processed datasets after lung segmentation (datasets #02 and #03). |
| Tasks | |
| Published | 2017-12-20 |
| URL | http://arxiv.org/abs/1712.07632v1 |
| http://arxiv.org/pdf/1712.07632v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-with-lung-segmentation-and-bone |
| Repo | |
| Framework | |
The Effects of Noisy Labels on Deep Convolutional Neural Networks for Music Tagging
| Title | The Effects of Noisy Labels on Deep Convolutional Neural Networks for Music Tagging |
| Authors | Keunwoo Choi, George Fazekas, Kyunghyun Cho, Mark Sandler |
| Abstract | Deep neural networks (DNN) have been successfully applied to music classification including music tagging. However, there are several open questions regarding the training, evaluation, and analysis of DNNs. In this article, we investigate specific aspects of neural networks, the effects of noisy labels, to deepen our understanding of their properties. We analyse and (re-)validate a large music tagging dataset to investigate the reliability of training and evaluation. Using a trained network, we compute label vector similarities which is compared to groundtruth similarity. The results highlight several important aspects of music tagging and neural networks. We show that networks can be effective despite relatively large error rates in groundtruth datasets, while conjecturing that label noise can be the cause of varying tag-wise performance differences. Lastly, the analysis of our trained network provides valuable insight into the relationships between music tags. These results highlight the benefit of using data-driven methods to address automatic music tagging. |
| Tasks | Music Classification |
| Published | 2017-06-07 |
| URL | http://arxiv.org/abs/1706.02361v3 |
| http://arxiv.org/pdf/1706.02361v3.pdf | |
| PWC | https://paperswithcode.com/paper/the-effects-of-noisy-labels-on-deep |
| Repo | |
| Framework | |
Automatic Myocardial Segmentation by Using A Deep Learning Network in Cardiac MRI
| Title | Automatic Myocardial Segmentation by Using A Deep Learning Network in Cardiac MRI |
| Authors | Ariel H. Curiale, Flavio D. Colavecchia, Pablo Kaluza, Roberto A. Isoardi, German Mato |
| Abstract | Cardiac function is of paramount importance for both prognosis and treatment of different pathologies such as mitral regurgitation, ischemia, dyssynchrony and myocarditis. Cardiac behavior is determined by structural and functional features. In both cases, the analysis of medical imaging studies requires to detect and segment the myocardium. Nowadays, magnetic resonance imaging (MRI) is one of the most relevant and accurate non-invasive diagnostic tools for cardiac structure and function. In this work we propose to use a deep learning technique to assist the automatization of myocardial segmentation in cardiac MRI. We present several improvements to previous works in this paper: we propose to use the Jaccard distance as optimization objective function, we integrate a residual learning strategy into the code, and we introduce a batch normalization layer to train the fully convolutional neural network. Our results demonstrate that this architecture outperforms previous approaches based on a similar network architecture, and that provides a suitable approach for myocardial segmentation. Our benchmark shows that the automatic myocardial segmentation takes less than 22 seg. for a volume of 128~x~128~x~13 pixels in a 3.1 GHz intel core i7. |
| Tasks | |
| Published | 2017-08-24 |
| URL | http://arxiv.org/abs/1708.07452v1 |
| http://arxiv.org/pdf/1708.07452v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-myocardial-segmentation-by-using-a |
| Repo | |
| Framework | |
Learning Probabilistic Programs Using Backpropagation
| Title | Learning Probabilistic Programs Using Backpropagation |
| Authors | Avi Pfeffer |
| Abstract | Probabilistic modeling enables combining domain knowledge with learning from data, thereby supporting learning from fewer training instances than purely data-driven methods. However, learning probabilistic models is difficult and has not achieved the level of performance of methods such as deep neural networks on many tasks. In this paper, we attempt to address this issue by presenting a method for learning the parameters of a probabilistic program using backpropagation. Our approach opens the possibility to building deep probabilistic programming models that are trained in a similar way to neural networks. |
| Tasks | Probabilistic Programming |
| Published | 2017-05-15 |
| URL | http://arxiv.org/abs/1705.05396v1 |
| http://arxiv.org/pdf/1705.05396v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-probabilistic-programs-using |
| Repo | |
| Framework | |
Importance Sampled Stochastic Optimization for Variational Inference
| Title | Importance Sampled Stochastic Optimization for Variational Inference |
| Authors | Joseph Sakaya, Arto Klami |
| Abstract | Variational inference approximates the posterior distribution of a probabilistic model with a parameterized density by maximizing a lower bound for the model evidence. Modern solutions fit a flexible approximation with stochastic gradient descent, using Monte Carlo approximation for the gradients. This enables variational inference for arbitrary differentiable probabilistic models, and consequently makes variational inference feasible for probabilistic programming languages. In this work we develop more efficient inference algorithms for the task by considering importance sampling estimates for the gradients. We show how the gradient with respect to the approximation parameters can often be evaluated efficiently without needing to re-compute gradients of the model itself, and then proceed to derive practical algorithms that use importance sampled estimates to speed up computation.We present importance sampled stochastic gradient descent that outperforms standard stochastic gradient descent by a clear margin for a range of models, and provide a justifiable variant of stochastic average gradients for variational inference. |
| Tasks | Probabilistic Programming, Stochastic Optimization |
| Published | 2017-04-19 |
| URL | http://arxiv.org/abs/1704.05786v2 |
| http://arxiv.org/pdf/1704.05786v2.pdf | |
| PWC | https://paperswithcode.com/paper/importance-sampled-stochastic-optimization |
| Repo | |
| Framework | |
Joint Modeling of Content and Discourse Relations in Dialogues
| Title | Joint Modeling of Content and Discourse Relations in Dialogues |
| Authors | Kechen Qin, Lu Wang, Joseph Kim |
| Abstract | We present a joint modeling approach to identify salient discussion points in spoken meetings as well as to label the discourse relations between speaker turns. A variation of our model is also discussed when discourse relations are treated as latent variables. Experimental results on two popular meeting corpora show that our joint model can outperform state-of-the-art approaches for both phrase-based content selection and discourse relation prediction tasks. We also evaluate our model on predicting the consistency among team members’ understanding of their group decisions. Classifiers trained with features constructed from our model achieve significant better predictive performance than the state-of-the-art. |
| Tasks | |
| Published | 2017-05-14 |
| URL | http://arxiv.org/abs/1705.05039v1 |
| http://arxiv.org/pdf/1705.05039v1.pdf | |
| PWC | https://paperswithcode.com/paper/joint-modeling-of-content-and-discourse |
| Repo | |
| Framework | |
Personalized Fuzzy Text Search Using Interest Prediction and Word Vectorization
| Title | Personalized Fuzzy Text Search Using Interest Prediction and Word Vectorization |
| Authors | Yun Liu, Tianmeng Gao, Baolin Song, Chengwei Huang |
| Abstract | In this paper we study the personalized text search problem. The keyword based search method in conventional algorithms has a low efficiency in understanding users’ intention since the semantic meaning, user profile, user interests are not always considered. Firstly, we propose a novel text search algorithm using a inverse filtering mechanism that is very efficient for label based item search. Secondly, we adopt the Bayesian network to implement the user interest prediction for an improved personalized search. According to user input, it searches the related items using keyword information, predicted user interest. Thirdly, the word vectorization is used to discover potential targets according to the semantic meaning. Experimental results show that the proposed search engine has an improved efficiency and accuracy and it can operate on embedded devices with very limited computational resources. |
| Tasks | |
| Published | 2017-10-01 |
| URL | http://arxiv.org/abs/1710.00310v1 |
| http://arxiv.org/pdf/1710.00310v1.pdf | |
| PWC | https://paperswithcode.com/paper/personalized-fuzzy-text-search-using-interest |
| Repo | |
| Framework | |
Satellite Imagery Feature Detection using Deep Convolutional Neural Network: A Kaggle Competition
| Title | Satellite Imagery Feature Detection using Deep Convolutional Neural Network: A Kaggle Competition |
| Authors | Vladimir Iglovikov, Sergey Mushinskiy, Vladimir Osin |
| Abstract | This paper describes our approach to the DSTL Satellite Imagery Feature Detection challenge run by Kaggle. The primary goal of this challenge is accurate semantic segmentation of different classes in satellite imagery. Our approach is based on an adaptation of fully convolutional neural network for multispectral data processing. In addition, we defined several modifications to the training objective and overall training pipeline, e.g. boundary effect estimation, also we discuss usage of data augmentation strategies and reflectance indices. Our solution scored third place out of 419 entries. Its accuracy is comparable to the first two places, but unlike those solutions, it doesn’t rely on complex ensembling techniques and thus can be easily scaled for deployment in production as a part of automatic feature labeling systems for satellite imagery analysis. |
| Tasks | Data Augmentation, Semantic Segmentation |
| Published | 2017-06-19 |
| URL | http://arxiv.org/abs/1706.06169v1 |
| http://arxiv.org/pdf/1706.06169v1.pdf | |
| PWC | https://paperswithcode.com/paper/satellite-imagery-feature-detection-using |
| Repo | |
| Framework | |
Nintendo Super Smash Bros. Melee: An “Untouchable” Agent
| Title | Nintendo Super Smash Bros. Melee: An “Untouchable” Agent |
| Authors | Ben Parr, Deepak Dilipkumar, Yuan Liu |
| Abstract | Nintendo’s Super Smash Bros. Melee fighting game can be emulated on modern hardware allowing us to inspect internal memory states, such as character positions. We created an AI that avoids being hit by training using these internal memory states and outputting controller button presses. After training on a month’s worth of Melee matches, our best agent learned to avoid the toughest AI built into the game for a full minute 74.6% of the time. |
| Tasks | |
| Published | 2017-12-08 |
| URL | http://arxiv.org/abs/1712.03280v1 |
| http://arxiv.org/pdf/1712.03280v1.pdf | |
| PWC | https://paperswithcode.com/paper/nintendo-super-smash-bros-melee-an |
| Repo | |
| Framework | |
