October 17, 2019

2892 words 14 mins read

Paper Group ANR 856

Detecting Compressed Cleartext Traffic from Consumer Internet of Things Devices. Autonomous Wireless Systems with Artificial Intelligence. Estimating the intrinsic dimension of datasets by a minimal neighborhood information. A comparison of recent waveform generation and acoustic modeling methods for neural-network-based speech synthesis. Learning …

Detecting Compressed Cleartext Traffic from Consumer Internet of Things Devices


Title	Detecting Compressed Cleartext Traffic from Consumer Internet of Things Devices
Authors	Daniel Hahn, Noah Apthorpe, Nick Feamster
Abstract	Data encryption is the primary method of protecting the privacy of consumer device Internet communications from network observers. The ability to automatically detect unencrypted data in network traffic is therefore an essential tool for auditing Internet-connected devices. Existing methods identify network packets containing cleartext but cannot differentiate packets containing encrypted data from packets containing compressed unencrypted data, which can be easily recovered by reversing the compression algorithm. This makes it difficult for consumer protection advocates to identify devices that risk user privacy by sending sensitive data in a compressed unencrypted format. Here, we present the first technique to automatically distinguish encrypted from compressed unencrypted network transmissions on a per-packet basis. We apply three machine learning models and achieve a maximum 66.9% accuracy with a convolutional neural network trained on raw packet data. This result is a baseline for this previously unstudied machine learning problem, which we hope will motivate further attention and accuracy improvements. To facilitate continuing research on this topic, we have made our training and test datasets available to the public.
Tasks
Published	2018-05-07
URL	http://arxiv.org/abs/1805.02722v1
PDF	http://arxiv.org/pdf/1805.02722v1.pdf
PWC	https://paperswithcode.com/paper/detecting-compressed-cleartext-traffic-from
Repo
Framework

Autonomous Wireless Systems with Artificial Intelligence


Title	Autonomous Wireless Systems with Artificial Intelligence
Authors	Haris Gacanin
Abstract	This paper discusses technology and opportunities to embrace artificial intelligence (AI) in the design of autonomous wireless systems. We aim to provide readers with motivation and general AI methodology of autonomous agents in the context of self-organization in real time by unifying knowledge management with sensing, reasoning and active learning. We highlight differences between training-based methods for matching problems and training-free methods for environment-specific problems. Finally, we conceptually introduce the functions of an autonomous agent with knowledge management.
Tasks	Active Learning
Published	2018-06-27
URL	https://arxiv.org/abs/1806.10518v2
PDF	https://arxiv.org/pdf/1806.10518v2.pdf
PWC	https://paperswithcode.com/paper/knowledge-driven-wireless-networks-with
Repo
Framework

Estimating the intrinsic dimension of datasets by a minimal neighborhood information


Title	Estimating the intrinsic dimension of datasets by a minimal neighborhood information
Authors	Elena Facco, Maria d’Errico, Alex Rodriguez, Alessandro Laio
Abstract	Analyzing large volumes of high-dimensional data is an issue of fundamental importance in data science, molecular simulations and beyond. Several approaches work on the assumption that the important content of a dataset belongs to a manifold whose Intrinsic Dimension (ID) is much lower than the crude large number of coordinates. Such manifold is generally twisted and curved, in addition points on it will be non-uniformly distributed: two factors that make the identification of the ID and its exploitation really hard. Here we propose a new ID estimator using only the distance of the first and the second nearest neighbor of each point in the sample. This extreme minimality enables us to reduce the effects of curvature, of density variation, and the resulting computational cost. The ID estimator is theoretically exact in uniformly distributed datasets, and provides consistent measures in general. When used in combination with block analysis, it allows discriminating the relevant dimensions as a function of the block size. This allows estimating the ID even when the data lie on a manifold perturbed by a high-dimensional noise, a situation often encountered in real world data sets. We demonstrate the usefulness of the approach on molecular simulations and image analysis.
Tasks
Published	2018-03-19
URL	http://arxiv.org/abs/1803.06992v1
PDF	http://arxiv.org/pdf/1803.06992v1.pdf
PWC	https://paperswithcode.com/paper/estimating-the-intrinsic-dimension-of
Repo
Framework

A comparison of recent waveform generation and acoustic modeling methods for neural-network-based speech synthesis


Title	A comparison of recent waveform generation and acoustic modeling methods for neural-network-based speech synthesis
Authors	Xin Wang, Jaime Lorenzo-Trueba, Shinji Takaki, Lauri Juvela, Junichi Yamagishi
Abstract	Recent advances in speech synthesis suggest that limitations such as the lossy nature of the amplitude spectrum with minimum phase approximation and the over-smoothing effect in acoustic modeling can be overcome by using advanced machine learning approaches. In this paper, we build a framework in which we can fairly compare new vocoding and acoustic modeling techniques with conventional approaches by means of a large scale crowdsourced evaluation. Results on acoustic models showed that generative adversarial networks and an autoregressive (AR) model performed better than a normal recurrent network and the AR model performed best. Evaluation on vocoders by using the same AR acoustic model demonstrated that a Wavenet vocoder outperformed classical source-filter-based vocoders. Particularly, generated speech waveforms from the combination of AR acoustic model and Wavenet vocoder achieved a similar score of speech quality to vocoded speech.
Tasks	Speech Synthesis
Published	2018-04-07
URL	http://arxiv.org/abs/1804.02549v1
PDF	http://arxiv.org/pdf/1804.02549v1.pdf
PWC	https://paperswithcode.com/paper/a-comparison-of-recent-waveform-generation
Repo
Framework

Learning Discriminators as Energy Networks in Adversarial Learning


Title	Learning Discriminators as Energy Networks in Adversarial Learning
Authors	Pingbo Pan, Yan Yan, Tianbao Yang, Yi Yang
Abstract	We propose a novel framework for structured prediction via adversarial learning. Existing adversarial learning methods involve two separate networks, i.e., the structured prediction models and the discriminative models, in the training. The information captured by discriminative models complements that in the structured prediction models, but few existing researches have studied on utilizing such information to improve structured prediction models at the inference stage. In this work, we propose to refine the predictions of structured prediction models by effectively integrating discriminative models into the prediction. Discriminative models are treated as energy-based models. Similar to the adversarial learning, discriminative models are trained to estimate scores which measure the quality of predicted outputs, while structured prediction models are trained to predict contrastive outputs with maximal energy scores. In this way, the gradient vanishing problem is ameliorated, and thus we are able to perform inference by following the ascent gradient directions of discriminative models to refine structured prediction models. The proposed method is able to handle a range of tasks, e.g., multi-label classification and image segmentation. Empirical results on these two tasks validate the effectiveness of our learning method.
Tasks	Multi-Label Classification, Semantic Segmentation, Structured Prediction
Published	2018-10-02
URL	http://arxiv.org/abs/1810.01152v1
PDF	http://arxiv.org/pdf/1810.01152v1.pdf
PWC	https://paperswithcode.com/paper/learning-discriminators-as-energy-networks-in
Repo
Framework

A Concept Learning Tool Based On Calculating Version Space Cardinality


Title	A Concept Learning Tool Based On Calculating Version Space Cardinality
Authors	Kuo-Kai Hsieh, Li-C. Wang
Abstract	In this paper, we proposed VeSC-CoL (Version Space Cardinality based Concept Learning) to deal with concept learning on extremely imbalanced datasets, especially when cross-validation is not a viable option. VeSC-CoL uses version space cardinality as a measure for model quality to replace cross-validation. Instead of naive enumeration of the version space, Ordered Binary Decision Diagram and Boolean Satisfiability are used to compute the version space. Experiments show that VeSC-CoL can accurately learn the target concept when computational resource is allowed.
Tasks
Published	2018-03-23
URL	http://arxiv.org/abs/1803.08625v1
PDF	http://arxiv.org/pdf/1803.08625v1.pdf
PWC	https://paperswithcode.com/paper/a-concept-learning-tool-based-on-calculating
Repo
Framework

Chat More If You Like: Dynamic Cue Words Planning to Flow Longer Conversations


Title	Chat More If You Like: Dynamic Cue Words Planning to Flow Longer Conversations
Authors	Lili Yao, Ruijian Xu, Chao Li, Dongyan Zhao, Rui Yan
Abstract	To build an open-domain multi-turn conversation system is one of the most interesting and challenging tasks in Artificial Intelligence. Many research efforts have been dedicated to building such dialogue systems, yet few shed light on modeling the conversation flow in an ongoing dialogue. Besides, it is common for people to talk about highly relevant aspects during a conversation. And the topics are coherent and drift naturally, which demonstrates the necessity of dialogue flow modeling. To this end, we present the multi-turn cue-words driven conversation system with reinforcement learning method (RLCw), which strives to select an adaptive cue word with the greatest future credit, and therefore improve the quality of generated responses. We introduce a new reward to measure the quality of cue words in terms of effectiveness and relevance. To further optimize the model for long-term conversations, a reinforcement approach is adopted in this paper. Experiments on real-life dataset demonstrate that our model consistently outperforms a set of competitive baselines in terms of simulated turns, diversity and human evaluation.
Tasks
Published	2018-11-19
URL	http://arxiv.org/abs/1811.07631v1
PDF	http://arxiv.org/pdf/1811.07631v1.pdf
PWC	https://paperswithcode.com/paper/chat-more-if-you-like-dynamic-cue-words
Repo
Framework

CAPTAIN: Comprehensive Composition Assistance for Photo Taking


Title	CAPTAIN: Comprehensive Composition Assistance for Photo Taking
Authors	Farshid Farhat, Mohammad Mahdi Kamani, James Z. Wang
Abstract	Many people are interested in taking astonishing photos and sharing with others. Emerging hightech hardware and software facilitate ubiquitousness and functionality of digital photography. Because composition matters in photography, researchers have leveraged some common composition techniques to assess the aesthetic quality of photos computationally. However, composition techniques developed by professionals are far more diverse than well-documented techniques can cover. We leverage the vast underexplored innovations in photography for computational composition assistance. We propose a comprehensive framework, named CAPTAIN (Composition Assistance for Photo Taking), containing integrated deep-learned semantic detectors, sub-genre categorization, artistic pose clustering, personalized aesthetics-based image retrieval, and style set matching. The framework is backed by a large dataset crawled from a photo-sharing Website with mostly photography enthusiasts and professionals. The work proposes a sequence of steps that have not been explored in the past by researchers. The work addresses personal preferences for composition through presenting a ranked-list of photographs to the user based on user-specified weights in the similarity measure. The matching algorithm recognizes the best shot among a sequence of shots with respect to the user’s preferred style set. We have conducted a number of experiments on the newly proposed components and reported findings. A user study demonstrates that the work is useful to those taking photos.
Tasks	Image Retrieval
Published	2018-11-10
URL	http://arxiv.org/abs/1811.04184v1
PDF	http://arxiv.org/pdf/1811.04184v1.pdf
PWC	https://paperswithcode.com/paper/captain-comprehensive-composition-assistance
Repo
Framework

Learning Answer Embeddings for Visual Question Answering


Title	Learning Answer Embeddings for Visual Question Answering
Authors	Hexiang Hu, Wei-Lun Chao, Fei Sha
Abstract	We propose a novel probabilistic model for visual question answering (Visual QA). The key idea is to infer two sets of embeddings: one for the image and the question jointly and the other for the answers. The learning objective is to learn the best parameterization of those embeddings such that the correct answer has higher likelihood among all possible answers. In contrast to several existing approaches of treating Visual QA as multi-way classification, the proposed approach takes the semantic relationships (as characterized by the embeddings) among answers into consideration, instead of viewing them as independent ordinal numbers. Thus, the learned embedded function can be used to embed unseen answers (in the training dataset). These properties make the approach particularly appealing for transfer learning for open-ended Visual QA, where the source dataset on which the model is learned has limited overlapping with the target dataset in the space of answers. We have also developed large-scale optimization techniques for applying the model to datasets with a large number of answers, where the challenge is to properly normalize the proposed probabilistic models. We validate our approach on several Visual QA datasets and investigate its utility for transferring models across datasets. The empirical results have shown that the approach performs well not only on in-domain learning but also on transfer learning.
Tasks	Question Answering, Transfer Learning, Visual Question Answering
Published	2018-06-10
URL	http://arxiv.org/abs/1806.03724v1
PDF	http://arxiv.org/pdf/1806.03724v1.pdf
PWC	https://paperswithcode.com/paper/learning-answer-embeddings-for-visual
Repo
Framework

Runtime Monitoring Neuron Activation Patterns


Title	Runtime Monitoring Neuron Activation Patterns
Authors	Chih-Hong Cheng, Georg Nührenberg, Hirotoshi Yasuoka
Abstract	For using neural networks in safety critical domains, it is important to know if a decision made by a neural network is supported by prior similarities in training. We propose runtime neuron activation pattern monitoring - after the standard training process, one creates a monitor by feeding the training data to the network again in order to store the neuron activation patterns in abstract form. In operation, a classification decision over an input is further supplemented by examining if a pattern similar (measured by Hamming distance) to the generated pattern is contained in the monitor. If the monitor does not contain any pattern similar to the generated pattern, it raises a warning that the decision is not based on the training data. Our experiments show that, by adjusting the similarity-threshold for activation patterns, the monitors can report a significant portion of misclassfications to be not supported by training with a small false-positive rate, when evaluated on a test set.
Tasks
Published	2018-09-18
URL	http://arxiv.org/abs/1809.06573v2
PDF	http://arxiv.org/pdf/1809.06573v2.pdf
PWC	https://paperswithcode.com/paper/runtime-monitoring-neuron-activation-patterns
Repo
Framework

Wasserstein variational gradient descent: From semi-discrete optimal transport to ensemble variational inference


Title	Wasserstein variational gradient descent: From semi-discrete optimal transport to ensemble variational inference
Authors	Luca Ambrogioni, Umut Guclu, Marcel van Gerven
Abstract	Particle-based variational inference offers a flexible way of approximating complex posterior distributions with a set of particles. In this paper we introduce a new particle-based variational inference method based on the theory of semi-discrete optimal transport. Instead of minimizing the KL divergence between the posterior and the variational approximation, we minimize a semi-discrete optimal transport divergence. The solution of the resulting optimal transport problem provides both a particle approximation and a set of optimal transportation densities that map each particle to a segment of the posterior distribution. We approximate these transportation densities by minimizing the KL divergence between a truncated distribution and the optimal transport solution. The resulting algorithm can be interpreted as a form of ensemble variational inference where each particle is associated with a local variational approximation.
Tasks
Published	2018-11-07
URL	https://arxiv.org/abs/1811.02827v2
PDF	https://arxiv.org/pdf/1811.02827v2.pdf
PWC	https://paperswithcode.com/paper/wasserstein-variational-gradient-descent-from
Repo
Framework

A VEST of the Pseudoinverse Learning Algorithm


Title	A VEST of the Pseudoinverse Learning Algorithm
Authors	Ping Guo
Abstract	In this paper, we briefly review the basic scheme of the pseudoinverse learning (PIL) algorithm and present some discussions on the PIL, as well as its variants. The PIL algorithm, first presented in 1995, is a non-gradient descent and non-iterative learning algorithm for multi-layer neural networks and has several advantages compared with gradient descent based algorithms. Some new viewpoints to PIL algorithm are presented, and several common pitfalls in practical implementation of the neural network learning task are also addressed. In addition, we show that so called extreme learning machine is a Variant crEated by Simple name alTernation (VEST) of the PIL algorithm for single hidden layer feedforward neural networks.
Tasks
Published	2018-05-20
URL	http://arxiv.org/abs/1805.07828v2
PDF	http://arxiv.org/pdf/1805.07828v2.pdf
PWC	https://paperswithcode.com/paper/a-vest-of-the-pseudoinverse-learning
Repo
Framework

Neural sequence labeling for Vietnamese POS Tagging and NER


Title	Neural sequence labeling for Vietnamese POS Tagging and NER
Authors	Duong Nguyen Anh, Hieu Nguyen Kiem, Vi Ngo Van
Abstract	This paper presents a neural architecture for Vietnamese sequence labeling tasks including part-of-speech (POS) tagging and named entity recognition (NER). We applied the model described in \cite{lample-EtAl:2016:N16-1} that is a combination of bidirectional Long-Short Term Memory and Conditional Random Fields, which rely on two sources of information about words: character-based word representations learned from the supervised corpus and pre-trained word embeddings learned from other unannotated corpora. Experiments on benchmark datasets show that this work achieves state-of-the-art performances on both tasks - 93.52% accuracy for POS tagging and 94.88% F1 for NER. Our sourcecode is available at here.
Tasks	Named Entity Recognition, Part-Of-Speech Tagging, Word Embeddings
Published	2018-11-09
URL	http://arxiv.org/abs/1811.03754v2
PDF	http://arxiv.org/pdf/1811.03754v2.pdf
PWC	https://paperswithcode.com/paper/neural-sequence-labeling-for-vietnamese-pos
Repo
Framework

Object Detection based Deep Unsupervised Hashing


Title	Object Detection based Deep Unsupervised Hashing
Authors	Rong-Cheng Tu, Xian-Ling Mao, Bo-Si Feng, Bing-Bing Bian, Yu-shu Ying
Abstract	Recently, similarity-preserving hashing methods have been extensively studied for large-scale image retrieval. Compared with unsupervised hashing, supervised hashing methods for labeled data have usually better performance by utilizing semantic label information. Intuitively, for unlabeled data, it will improve the performance of unsupervised hashing methods if we can first mine some supervised semantic ‘label information’ from unlabeled data and then incorporate the ‘label information’ into the training process. Thus, in this paper, we propose a novel Object Detection based Deep Unsupervised Hashing method (ODDUH). Specifically, a pre-trained object detection model is utilized to mining supervised ‘label information’, which is used to guide the learning process to generate high-quality hash codes.Extensive experiments on two public datasets demonstrate that the proposed method outperforms the state-of-the-art unsupervised hashing methods in the image retrieval task.
Tasks	Image Retrieval, Object Detection
Published	2018-11-24
URL	http://arxiv.org/abs/1811.09822v1
PDF	http://arxiv.org/pdf/1811.09822v1.pdf
PWC	https://paperswithcode.com/paper/object-detection-based-deep-unsupervised
Repo
Framework

How Robust are Deep Neural Networks?


Title	How Robust are Deep Neural Networks?
Authors	Biswa Sengupta, Karl J. Friston
Abstract	Convolutional and Recurrent, deep neural networks have been successful in machine learning systems for computer vision, reinforcement learning, and other allied fields. However, the robustness of such neural networks is seldom apprised, especially after high classification accuracy has been attained. In this paper, we evaluate the robustness of three recurrent neural networks to tiny perturbations, on three widely used datasets, to argue that high accuracy does not always mean a stable and a robust (to bounded perturbations, adversarial attacks, etc.) system. Especially, normalizing the spectrum of the discrete recurrent network to bound the spectrum (using power method, Rayleigh quotient, etc.) on a unit disk produces stable, albeit highly non-robust neural networks. Furthermore, using the $\epsilon$-pseudo-spectrum, we show that training of recurrent networks, say using gradient-based methods, often result in non-normal matrices that may or may not be diagonalizable. Therefore, the open problem lies in constructing methods that optimize not only for accuracy but also for the stability and the robustness of the underlying neural network, a criterion that is distinct from the other.
Tasks
Published	2018-04-30
URL	http://arxiv.org/abs/1804.11313v1
PDF	http://arxiv.org/pdf/1804.11313v1.pdf
PWC	https://paperswithcode.com/paper/how-robust-are-deep-neural-networks
Repo
Framework