October 16, 2019

1946 words 10 mins read

Paper Group NANR 28

Paper Group NANR 28

A Classification-Based Perspective on GAN Distributions. Analyzing the Quality of Counseling Conversations: the Tell-Tale Signs of High-quality Counseling. PAC-learning in the presence of adversaries. Building Evaluation Datasets for Cultural Microblog Retrieval. Creating Large-Scale Argumentation Structures for Dialogue Systems. Deformable Pose Tr …

A Classification-Based Perspective on GAN Distributions

Title A Classification-Based Perspective on GAN Distributions
Authors Shibani Santurkar, Ludwig Schmidt, Aleksander Madry
Abstract A fundamental, and still largely unanswered, question in the context of Generative Adversarial Networks (GANs) is whether GANs are actually able to capture the key characteristics of the datasets they are trained on. The current approaches to examining this issue require significant human supervision, such as visual inspection of sampled images, and often offer only fairly limited scalability. In this paper, we propose new techniques that employ classification-based perspective to evaluate synthetic GAN distributions and their capability to accurately reflect the essential properties of the training data. These techniques require only minimal human supervision and can easily be scaled and adapted to evaluate a variety of state-of-the-art GANs on large, popular datasets. They also indicate that GANs have significant problems in reproducing the more distributional properties of the training dataset. In particular, the diversity of such synthetic data is orders of magnitude smaller than that of the original data.
Tasks
Published 2018-01-01
URL https://openreview.net/forum?id=S1FQEfZA-
PDF https://openreview.net/pdf?id=S1FQEfZA-
PWC https://paperswithcode.com/paper/a-classification-based-perspective-on-gan
Repo
Framework

Analyzing the Quality of Counseling Conversations: the Tell-Tale Signs of High-quality Counseling

Title Analyzing the Quality of Counseling Conversations: the Tell-Tale Signs of High-quality Counseling
Authors Ver{'o}nica P{'e}rez-Rosas, Xuetong Sun, Christy Li, Yuchen Wang, Kenneth Resnicow, Rada Mihalcea
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1591/
PDF https://www.aclweb.org/anthology/L18-1591
PWC https://paperswithcode.com/paper/analyzing-the-quality-of-counseling
Repo
Framework

PAC-learning in the presence of adversaries

Title PAC-learning in the presence of adversaries
Authors Daniel Cullina, Arjun Nitin Bhagoji, Prateek Mittal
Abstract The existence of evasion attacks during the test phase of machine learning algorithms represents a significant challenge to both their deployment and understanding. These attacks can be carried out by adding imperceptible perturbations to inputs to generate adversarial examples and finding effective defenses and detectors has proven to be difficult. In this paper, we step away from the attack-defense arms race and seek to understand the limits of what can be learned in the presence of an evasion adversary. In particular, we extend the Probably Approximately Correct (PAC)-learning framework to account for the presence of an adversary. We first define corrupted hypothesis classes which arise from standard binary hypothesis classes in the presence of an evasion adversary and derive the Vapnik-Chervonenkis (VC)-dimension for these, denoted as the adversarial VC-dimension. We then show that sample complexity upper bounds from the Fundamental Theorem of Statistical learning can be extended to the case of evasion adversaries, where the sample complexity is controlled by the adversarial VC-dimension. We then explicitly derive the adversarial VC-dimension for halfspace classifiers in the presence of a sample-wise norm-constrained adversary of the type commonly studied for evasion attacks and show that it is the same as the standard VC-dimension, closing an open question. Finally, we prove that the adversarial VC-dimension can be either larger or smaller than the standard VC-dimension depending on the hypothesis class and adversary, making it an interesting object of study in its own right.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/7307-pac-learning-in-the-presence-of-adversaries
PDF http://papers.nips.cc/paper/7307-pac-learning-in-the-presence-of-adversaries.pdf
PWC https://paperswithcode.com/paper/pac-learning-in-the-presence-of-adversaries
Repo
Framework

Building Evaluation Datasets for Cultural Microblog Retrieval

Title Building Evaluation Datasets for Cultural Microblog Retrieval
Authors Lorraine Goeuriot, Josiane Mothe, Philippe Mulhem, Eric SanJuan
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1594/
PDF https://www.aclweb.org/anthology/L18-1594
PWC https://paperswithcode.com/paper/building-evaluation-datasets-for-cultural
Repo
Framework

Creating Large-Scale Argumentation Structures for Dialogue Systems

Title Creating Large-Scale Argumentation Structures for Dialogue Systems
Authors Kazuki Sakai, Akari Inago, Ryuichiro Higashinaka, Yuichiro Yoshikawa, Hiroshi Ishiguro, Junji Tomita
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1627/
PDF https://www.aclweb.org/anthology/L18-1627
PWC https://paperswithcode.com/paper/creating-large-scale-argumentation-structures
Repo
Framework

Deformable Pose Traversal Convolution for 3D Action and Gesture Recognition

Title Deformable Pose Traversal Convolution for 3D Action and Gesture Recognition
Authors Junwu Weng, Mengyuan Liu, Xudong Jiang, Junsong Yuan
Abstract The representation of 3D pose plays a critical role for 3D body action and hand gesture recognition. Rather than directly representing the 3D pose using its joint locations, in this paper, we propose Deformable Pose Traversal Convolution which applies one-dimensional convolution to traverse the 3D pose to represent it. Instead of fixing the reception field when performing traversal convolution, it optimizes the convolutional kernel for each joint, by considering contextual joints with various weights. This deformable convolution can better utilize contextual joints for action and gesture recognition and is more robust to noisy joints. Moreover, by feeding the learned pose feature to a LSTM, we can perform end-to-end training which jointly optimizes 3D pose representation and temporal sequence recognition. Experiments on three benchmark datasets validate the competitive performance of our proposed method, as well as its efficiency and robustness to handle noisy pose.
Tasks Gesture Recognition, Hand Gesture Recognition, Hand-Gesture Recognition
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Junwu_Weng_Deformable_Pose_Traversal_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Junwu_Weng_Deformable_Pose_Traversal_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/deformable-pose-traversal-convolution-for-3d
Repo
Framework

Adaptive Quantization of Neural Networks

Title Adaptive Quantization of Neural Networks
Authors Soroosh Khoram, Jing Li
Abstract Despite the state-of-the-art accuracy of Deep Neural Networks (DNN) in various classification problems, their deployment onto resource constrained edge computing devices remains challenging due to their large size and complexity. Several recent studies have reported remarkable results in reducing this complexity through quantization of DNN models. However, these studies usually do not consider the changes in the loss function when performing quantization, nor do they take the different importances of DNN model parameters to the accuracy into account. We address these issues in this paper by proposing a new method, called adaptive quantization, which simplifies a trained DNN model by finding a unique, optimal precision for each network parameter such that the increase in loss is minimized. The optimization problem at the core of this method iteratively uses the loss function gradient to determine an error margin for each parameter and assigns it a precision accordingly. Since this problem uses linear functions, it is computationally cheap and, as we will show, has a closed-form approximate solution. Experiments on MNIST, CIFAR, and SVHN datasets showed that the proposed method can achieve near or better than state-of-the-art reduction in model size with similar error rates. Furthermore, it can achieve compressions close to floating-point model compression methods without loss of accuracy.
Tasks Model Compression, Quantization
Published 2018-01-01
URL https://openreview.net/forum?id=SyOK1Sg0W
PDF https://openreview.net/pdf?id=SyOK1Sg0W
PWC https://paperswithcode.com/paper/adaptive-quantization-of-neural-networks
Repo
Framework

Portable Spelling Corrector for a Less-Resourced Language: Amharic

Title Portable Spelling Corrector for a Less-Resourced Language: Amharic
Authors Andargachew Mekonnen Gezmu, Andreas N{"u}rnberger, Binyam Ephrem Seyoum
Abstract
Tasks Language Modelling, Spelling Correction, Transliteration
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1651/
PDF https://www.aclweb.org/anthology/L18-1651
PWC https://paperswithcode.com/paper/portable-spelling-corrector-for-a-less
Repo
Framework

The loss surface and expressivity of deep convolutional neural networks

Title The loss surface and expressivity of deep convolutional neural networks
Authors Quynh Nguyen, Matthias Hein
Abstract We analyze the expressiveness and loss surface of practical deep convolutional neural networks (CNNs) with shared weights and max pooling layers. We show that such CNNs produce linearly independent features at a “wide” layer which has more neurons than the number of training samples. This condition holds e.g. for the VGG network. Furthermore, we provide for such wide CNNs necessary and sufficient conditions for global minima with zero training error. For the case where the wide layer is followed by a fully connected layer we show that almost every critical point of the empirical loss is a global minimum with zero training error. Our analysis suggests that both depth and width are very important in deep learning. While depth brings more representational power and allows the network to learn high level features, width smoothes the optimization landscape of the loss function in the sense that a sufficiently wide network has a well-behaved loss surface with almost no bad local minima.
Tasks
Published 2018-01-01
URL https://openreview.net/forum?id=BJjquybCW
PDF https://openreview.net/pdf?id=BJjquybCW
PWC https://paperswithcode.com/paper/the-loss-surface-and-expressivity-of-deep
Repo
Framework

Multi-View Harmonized Bilinear Network for 3D Object Recognition

Title Multi-View Harmonized Bilinear Network for 3D Object Recognition
Authors Tan Yu, Jingjing Meng, Junsong Yuan
Abstract View-based methods have achieved considerable success in $3$D object recognition tasks. Different from existing view-based methods pooling the view-wise features, we tackle this problem from the perspective of patches-to-patches similarity measurement. By exploiting the relationship between polynomial kernel and bilinear pooling, we obtain an effective $3$D object representation by aggregating local convolutional features through bilinear pooling. Meanwhile, we harmonize different components inherited in the pooled bilinear feature to obtain a more discriminative representation for a $3$D object. To achieve an end-to-end trainable framework, we incorporate the harmonized bilinear pooling operation as a layer of a network, constituting the proposed Multi-view Harmonized Bilinear Network (MHBN). Systematic experiments conducted on two public benchmark datasets demonstrate the efficacy of the proposed methods in $3$D object recognition.
Tasks 3D Object Recognition, Object Recognition
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Yu_Multi-View_Harmonized_Bilinear_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Yu_Multi-View_Harmonized_Bilinear_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/multi-view-harmonized-bilinear-network-for-3d
Repo
Framework

The WAW Corpus: The First Corpus of Interpreted Speeches and their Translations for English and Arabic

Title The WAW Corpus: The First Corpus of Interpreted Speeches and their Translations for English and Arabic
Authors Ahmed Abdelali, Irina Temnikova, Samy Hedaya, Stephan Vogel
Abstract
Tasks Machine Translation, Speech Recognition
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1336/
PDF https://www.aclweb.org/anthology/L18-1336
PWC https://paperswithcode.com/paper/the-waw-corpus-the-first-corpus-of
Repo
Framework

AET: Web-based Adjective Exploration Tool for German

Title AET: Web-based Adjective Exploration Tool for German
Authors Tatiana Bladier, Esther Seyffarth, Oliver Hellwig, Wiebke Petersen
Abstract
Tasks Machine Translation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1343/
PDF https://www.aclweb.org/anthology/L18-1343
PWC https://paperswithcode.com/paper/aet-web-based-adjective-exploration-tool-for
Repo
Framework

Building Universal Dependency Treebanks in Korean

Title Building Universal Dependency Treebanks in Korean
Authors Jayeol Chun, Na-Rae Han, Jena D. Hwang, Jinho D. Choi
Abstract
Tasks Dependency Parsing
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1347/
PDF https://www.aclweb.org/anthology/L18-1347
PWC https://paperswithcode.com/paper/building-universal-dependency-treebanks-in
Repo
Framework

Using context to identify the language of face-saving

Title Using context to identify the language of face-saving
Authors Nona Naderi, Graeme Hirst
Abstract We created a corpus of utterances that attempt to save face from parliamentary debates and use it to automatically analyze the language of reputation defence. Our proposed model that incorporates information regarding threats to reputation can predict reputation defence language with high confidence. Further experiments and evaluations on different datasets show that the model is able to generalize to new utterances and can predict the language of reputation defence in a new dataset.
Tasks Argument Mining
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-5214/
PDF https://www.aclweb.org/anthology/W18-5214
PWC https://paperswithcode.com/paper/using-context-to-identify-the-language-of
Repo
Framework

Spontaneous Symmetry Breaking in Deep Neural Networks

Title Spontaneous Symmetry Breaking in Deep Neural Networks
Authors Ricky Fok, Aijun An, Xiaogang Wang
Abstract We propose a framework to understand the unprecedented performance and robustness of deep neural networks using field theory. Correlations between the weights within the same layer can be described by symmetries in that layer, and networks generalize better if such symmetries are broken to reduce the redundancies of the weights. Using a two parameter field theory, we find that the network can break such symmetries itself towards the end of training in a process commonly known in physics as spontaneous symmetry breaking. This corresponds to a network generalizing itself without any user input layers to break the symmetry, but by communication with adjacent layers. In the layer decoupling limit applicable to residual networks (He et al., 2015), we show that the remnant symmetries that survive the non-linear layers are spontaneously broken based on empirical results. The Lagrangian for the non-linear and weight layers together has striking similarities with the one in quantum field theory of a scalar. Using results from quantum field theory we show that our framework is able to explain many experimentally observed phenomena, such as training on random labels with zero error (Zhang et al., 2017), the information bottleneck and the phase transition out of it (Shwartz-Ziv & Tishby, 2017), shattered gradients (Balduzzi et al., 2017), and many more.
Tasks
Published 2018-01-01
URL https://openreview.net/forum?id=SkiCjzNTZ
PDF https://openreview.net/pdf?id=SkiCjzNTZ
PWC https://paperswithcode.com/paper/spontaneous-symmetry-breaking-in-deep-neural
Repo
Framework
comments powered by Disqus