July 29, 2019

3186 words 15 mins read

Paper Group ANR 12

Training Neural Networks Based on Imperialist Competitive Algorithm for Predicting Earthquake Intensity. Surface Normals in the Wild. Learning Audio Sequence Representations for Acoustic Event Classification. Embedded Real-Time Fall Detection Using Deep Learning For Elderly Care. I Probe, Therefore I Am: Designing a Virtual Journalist with Human Em …

Training Neural Networks Based on Imperialist Competitive Algorithm for Predicting Earthquake Intensity


Title	Training Neural Networks Based on Imperialist Competitive Algorithm for Predicting Earthquake Intensity
Authors	Mohsen Moradi
Abstract	In this study we determined neural network weights and biases by Imperialist Competitive Algorithm (ICA) in order to train network for predicting earthquake intensity in Richter. For this reason, we used dependent parameters like earthquake occurrence time, epicenter’s latitude and longitude in degree, focal depth in kilometer, and the seismological center distance from epicenter and earthquake focal center in kilometer which has been provided by Berkeley data base. The studied neural network has two hidden layer: its first layer has 16 neurons and the second layer has 24 neurons. By using ICA algorithm, average error for testing data is 0.0007 with a variance equal to 0.318. The earthquake prediction error in Richter by MSE criteria for ICA algorithm is 0.101, but by using GA, the MSE value is 0.115.
Tasks
Published	2017-02-13
URL	http://arxiv.org/abs/1704.04095v1
PDF	http://arxiv.org/pdf/1704.04095v1.pdf
PWC	https://paperswithcode.com/paper/training-neural-networks-based-on-imperialist
Repo
Framework

Surface Normals in the Wild


Title	Surface Normals in the Wild
Authors	Weifeng Chen, Donglai Xiang, Jia Deng
Abstract	We study the problem of single-image depth estimation for images in the wild. We collect human annotated surface normals and use them to train a neural network that directly predicts pixel-wise depth. We propose two novel loss functions for training with surface normal annotations. Experiments on NYU Depth and our own dataset demonstrate that our approach can significantly improve the quality of depth estimation in the wild.
Tasks	Depth Estimation
Published	2017-04-10
URL	http://arxiv.org/abs/1704.02956v1
PDF	http://arxiv.org/pdf/1704.02956v1.pdf
PWC	https://paperswithcode.com/paper/surface-normals-in-the-wild
Repo
Framework

Learning Audio Sequence Representations for Acoustic Event Classification


Title	Learning Audio Sequence Representations for Acoustic Event Classification
Authors	Zixing Zhang, Ding Liu, Jing Han, Björn Schuller
Abstract	Acoustic Event Classification (AEC) has become a significant task for machines to perceive the surrounding auditory scene. However, extracting effective representations that capture the underlying characteristics of the acoustic events is still challenging. Previous methods mainly focused on designing the audio features in a ‘hand-crafted’ manner. Interestingly, data-learnt features have been recently reported to show better performance. Up to now, these were only considered on the frame-level. In this paper, we propose an unsupervised learning framework to learn a vector representation of an audio sequence for AEC. This framework consists of a Recurrent Neural Network (RNN) encoder and a RNN decoder, which respectively transforms the variable-length audio sequence into a fixed-length vector and reconstructs the input sequence on the generated vector. After training the encoder-decoder, we feed the audio sequences to the encoder and then take the learnt vectors as the audio sequence representations. Compared with previous methods, the proposed method can not only deal with the problem of arbitrary-lengths of audio streams, but also learn the salient information of the sequence. Extensive evaluation on a large-size acoustic event database is performed, and the empirical results demonstrate that the learnt audio sequence representation yields a significant performance improvement by a large margin compared with other state-of-the-art hand-crafted sequence features for AEC.
Tasks
Published	2017-07-27
URL	http://arxiv.org/abs/1707.08729v1
PDF	http://arxiv.org/pdf/1707.08729v1.pdf
PWC	https://paperswithcode.com/paper/learning-audio-sequence-representations-for
Repo
Framework

Embedded Real-Time Fall Detection Using Deep Learning For Elderly Care


Title	Embedded Real-Time Fall Detection Using Deep Learning For Elderly Care
Authors	Hyunwoo Lee, Jooyoung Kim, Dojun Yang, Joon-Ho Kim
Abstract	This paper proposes a real-time embedded fall detection system using a DVS(Dynamic Vision Sensor) that has never been used for traditional fall detection, a dataset for fall detection using that, and a DVS-TN(DVS-Temporal Network). The first contribution is building a DVS Falls Dataset, which made our network to recognize a much greater variety of falls than the existing datasets that existed before and solved privacy issues using the DVS. Secondly, we introduce the DVS-TN : optimized deep learning network to detect falls using DVS. Finally, we implemented a fall detection system which can run on low-computing H/W with real-time, and tested on DVS Falls Dataset that takes into account various falls situations. Our approach achieved 95.5% on the F1-score and operates at 31.25 FPS on NVIDIA Jetson TX1 board.
Tasks
Published	2017-11-30
URL	http://arxiv.org/abs/1711.11200v1
PDF	http://arxiv.org/pdf/1711.11200v1.pdf
PWC	https://paperswithcode.com/paper/embedded-real-time-fall-detection-using-deep
Repo
Framework

I Probe, Therefore I Am: Designing a Virtual Journalist with Human Emotions


Title	I Probe, Therefore I Am: Designing a Virtual Journalist with Human Emotions
Authors	Kevin K. Bowden, Tommy Nilsson, Christine P. Spencer, Kubra Cengiz, Alexandru Ghitulescu, Jelte B. van Waterschoot
Abstract	By utilizing different communication channels, such as verbal language, gestures or facial expressions, virtually embodied interactive humans hold a unique potential to bridge the gap between human-computer interaction and actual interhuman communication. The use of virtual humans is consequently becoming increasingly popular in a wide range of areas where such a natural communication might be beneficial, including entertainment, education, mental health research and beyond. Behind this development lies a series of technological advances in a multitude of disciplines, most notably natural language processing, computer vision, and speech synthesis. In this paper we discuss a Virtual Human Journalist, a project employing a number of novel solutions from these disciplines with the goal to demonstrate their viability by producing a humanoid conversational agent capable of naturally eliciting and reacting to information from a human user. A set of qualitative and quantitative evaluation sessions demonstrated the technical feasibility of the system whilst uncovering a number of deficits in its capacity to engage users in a way that would be perceived as natural and emotionally engaging. We argue that naturalness should not always be seen as a desirable goal and suggest that deliberately suppressing the naturalness of virtual human interactions, such as by altering its personality cues, might in some cases yield more desirable results.
Tasks	Speech Synthesis
Published	2017-05-18
URL	http://arxiv.org/abs/1705.06694v1
PDF	http://arxiv.org/pdf/1705.06694v1.pdf
PWC	https://paperswithcode.com/paper/i-probe-therefore-i-am-designing-a-virtual
Repo
Framework

HTM-MAT: An online prediction software toolbox based on cortical machine learning algorithm


Title	HTM-MAT: An online prediction software toolbox based on cortical machine learning algorithm
Authors	V. I. Anireh, EN Osegi
Abstract	HTM-MAT is a MATLAB based toolbox for implementing cortical learning algorithms (CLA) including related cortical-like algorithms that possesses spatiotemporal properties. CLA is a suite of predictive machine learning algorithms developed by Numenta Inc. and is based on the hierarchical temporal memory (HTM). This paper presents an implementation of HTM-MAT with several illustrative examples including several toy datasets and compared with two sequence learning applications employing state-of-the-art algorithms - the recurrentjs based on the Long Short-Term Memory (LSTM) algorithm and OS-ELM which is based on an online sequential version of the Extreme Learning Machine. The performance of HTM-MAT using two historical benchmark datasets and one real world dataset is also compared with one of the existing sequence learning applications, the OS-ELM. The results indicate that HTM-MAT predictions are indeed competitive and can outperform OS-ELM in sequential prediction tasks.
Tasks
Published	2017-06-28
URL	http://arxiv.org/abs/1708.01659v1
PDF	http://arxiv.org/pdf/1708.01659v1.pdf
PWC	https://paperswithcode.com/paper/htm-mat-an-online-prediction-software-toolbox
Repo
Framework

Group Sparse CNNs for Question Classification with Answer Sets


Title	Group Sparse CNNs for Question Classification with Answer Sets
Authors	Mingbo Ma, Liang Huang, Bing Xiang, Bowen Zhou
Abstract	Question classification is an important task with wide applications. However, traditional techniques treat questions as general sentences, ignoring the corresponding answer data. In order to consider answer information into question modeling, we first introduce novel group sparse autoencoders which refine question representation by utilizing group information in the answer set. We then propose novel group sparse CNNs which naturally learn question representation with respect to their answers by implanting group sparse autoencoders into traditional CNNs. The proposed model significantly outperform strong baselines on four datasets.
Tasks
Published	2017-10-07
URL	http://arxiv.org/abs/1710.02717v1
PDF	http://arxiv.org/pdf/1710.02717v1.pdf
PWC	https://paperswithcode.com/paper/group-sparse-cnns-for-question-classification
Repo
Framework

Recognizing Dynamic Scenes with Deep Dual Descriptor based on Key Frames and Key Segments


Title	Recognizing Dynamic Scenes with Deep Dual Descriptor based on Key Frames and Key Segments
Authors	Sungeun Hong, Jongbin Ryu, Woobin Im, Hyun S. Yang
Abstract	Recognizing dynamic scenes is one of the fundamental problems in scene understanding, which categorizes moving scenes such as a forest fire, landslide, or avalanche. While existing methods focus on reliable capturing of static and dynamic information, few works have explored frame selection from a dynamic scene sequence. In this paper, we propose dynamic scene recognition using a deep dual descriptor based on `key frames' and` key segments.’ Key frames that reflect the feature distribution of the sequence with a small number are used for capturing salient static appearances. Key segments, which are captured from the area around each key frame, provide an additional discriminative power by dynamic patterns within short time intervals. To this end, two types of transferred convolutional neural network features are used in our approach. A fully connected layer is used to select the key frames and key segments, while the convolutional layer is used to describe them. We conducted experiments using public datasets as well as a new dataset comprised of 23 dynamic scene classes with 10 videos per class. The evaluation results demonstrated the state-of-the-art performance of the proposed method.
Tasks	Scene Recognition, Scene Understanding
Published	2017-02-15
URL	http://arxiv.org/abs/1702.04479v2
PDF	http://arxiv.org/pdf/1702.04479v2.pdf
PWC	https://paperswithcode.com/paper/recognizing-dynamic-scenes-with-deep-dual
Repo
Framework

Efficient Data-Driven Geologic Feature Detection from Pre-stack Seismic Measurements using Randomized Machine-Learning Algorithm


Title	Efficient Data-Driven Geologic Feature Detection from Pre-stack Seismic Measurements using Randomized Machine-Learning Algorithm
Authors	Youzuo Lin, Shusen Wang, Jayaraman Thiagarajan, George Guthrie, David Coblentz
Abstract	Conventional seismic techniques for detecting the subsurface geologic features are challenged by limited data coverage, computational inefficiency, and subjective human factors. We developed a novel data-driven geological feature detection approach based on pre-stack seismic measurements. Our detection method employs an efficient and accurate machine-learning detection approach to extract useful subsurface geologic features automatically. Specifically, our method is based on kernel ridge regression model. The conventional kernel ridge regression can be computationally prohibited because of the large volume of seismic measurements. We employ a data reduction technique in combination with the conventional kernel ridge regression method to improve the computational efficiency and reduce memory usage. In particular, we utilize a randomized numerical linear algebra technique, named Nystr"om method, to effectively reduce the dimensionality of the feature space without compromising the information content required for accurate detection. We provide thorough computational cost analysis to show efficiency of our new geological feature detection methods. We further validate the performance of our new subsurface geologic feature detection method using synthetic surface seismic data for 2D acoustic and elastic velocity models. Our numerical examples demonstrate that our new detection method significantly improves the computational efficiency while maintaining comparable accuracy. Interestingly, we show that our method yields a speed-up ratio on the order of $\sim10^2$ to $\sim 10^3$ in a multi-core computational environment.
Tasks
Published	2017-10-11
URL	http://arxiv.org/abs/1710.04329v1
PDF	http://arxiv.org/pdf/1710.04329v1.pdf
PWC	https://paperswithcode.com/paper/efficient-data-driven-geologic-feature
Repo
Framework

Deep Sparse Coding for Invariant Multimodal Halle Berry Neurons


Title	Deep Sparse Coding for Invariant Multimodal Halle Berry Neurons
Authors	Edward Kim, Darryl Hannan, Garrett Kenyon
Abstract	Deep feed-forward convolutional neural networks (CNNs) have become ubiquitous in virtually all machine learning and computer vision challenges; however, advancements in CNNs have arguably reached an engineering saturation point where incremental novelty results in minor performance gains. Although there is evidence that object classification has reached human levels on narrowly defined tasks, for general applications, the biological visual system is far superior to that of any computer. Research reveals there are numerous missing components in feed-forward deep neural networks that are critical in mammalian vision. The brain does not work solely in a feed-forward fashion, but rather all of the neurons are in competition with each other; neurons are integrating information in a bottom up and top down fashion and incorporating expectation and feedback in the modeling process. Furthermore, our visual cortex is working in tandem with our parietal lobe, integrating sensory information from various modalities. In our work, we sought to improve upon the standard feed-forward deep learning model by augmenting them with biologically inspired concepts of sparsity, top-down feedback, and lateral inhibition. We define our model as a sparse coding problem using hierarchical layers. We solve the sparse coding problem with an additional top-down feedback error driving the dynamics of the neural network. While building and observing the behavior of our model, we were fascinated that multimodal, invariant neurons naturally emerged that mimicked, “Halle Berry neurons” found in the human brain. Furthermore, our sparse representation of multimodal signals demonstrates qualitative and quantitative superiority to the standard feed-forward joint embedding in common vision and machine learning tasks.
Tasks	Object Classification
Published	2017-11-21
URL	http://arxiv.org/abs/1711.07998v2
PDF	http://arxiv.org/pdf/1711.07998v2.pdf
PWC	https://paperswithcode.com/paper/deep-sparse-coding-for-invariant-multimodal
Repo
Framework

Relating Complexity-theoretic Parameters with SAT Solver Performance


Title	Relating Complexity-theoretic Parameters with SAT Solver Performance
Authors	Edward Zulkoski, Ruben Martins, Christoph Wintersteiger, Robert Robere, Jia Liang, Krzysztof Czarnecki, Vijay Ganesh
Abstract	Over the years complexity theorists have proposed many structural parameters to explain the surprising efficiency of conflict-driven clause-learning (CDCL) SAT solvers on a wide variety of large industrial Boolean instances. While some of these parameters have been studied empirically, until now there has not been a unified comparative study of their explanatory power on a comprehensive benchmark. We correct this state of affairs by conducting a large-scale empirical evaluation of CDCL SAT solver performance on nearly 7000 industrial and crafted formulas against several structural parameters such as backdoors, treewidth, backbones, and community structure. Our study led us to several results. First, we show that while such parameters only weakly correlate with CDCL solving time, certain combinations of them yield much better regression models. Second, we show how some parameters can be used as a “lens” to better understand the efficiency of different solving heuristics. Finally, we propose a new complexity-theoretic parameter, which we call learning-sensitive with restarts (LSR) backdoors, that extends the notion of learning-sensitive (LS) backdoors to incorporate restarts and discuss algorithms to compute them. We mathematically prove that for certain class of instances minimal LSR-backdoors are exponentially smaller than minimal-LS backdoors.
Tasks
Published	2017-06-26
URL	http://arxiv.org/abs/1706.08611v1
PDF	http://arxiv.org/pdf/1706.08611v1.pdf
PWC	https://paperswithcode.com/paper/relating-complexity-theoretic-parameters-with
Repo
Framework

Predicting Discharge Medications at Admission Time Based on Deep Learning


Title	Predicting Discharge Medications at Admission Time Based on Deep Learning
Authors	Yuan Yang, Pengtao Xie, Xin Gao, Carol Cheng, Christy Li, Hongbao Zhang, Eric Xing
Abstract	Predicting discharge medications right after a patient being admitted is an important clinical decision, which provides physicians with guidance on what type of medication regimen to plan for and what possible changes on initial medication may occur during an inpatient stay. It also facilitates medication reconciliation process with easy detection of medication discrepancy at discharge time to improve patient safety. However, since the information available upon admission is limited and patients’ condition may evolve during an inpatient stay, these predictions could be a difficult decision for physicians to make. In this work, we investigate how to leverage deep learning technologies to assist physicians in predicting discharge medications based on information documented in the admission note. We build a convolutional neural network which takes an admission note as input and predicts the medications placed on the patient at discharge time. Our method is able to distill semantic patterns from unstructured and noisy texts, and is capable of capturing the pharmacological correlations among medications. We evaluate our method on 25K patient visits and compare with 4 strong baselines. Our methods demonstrate a 20% increase in macro-averaged F1 score than the best baseline.
Tasks
Published	2017-11-04
URL	http://arxiv.org/abs/1711.01386v3
PDF	http://arxiv.org/pdf/1711.01386v3.pdf
PWC	https://paperswithcode.com/paper/predicting-discharge-medications-at-admission
Repo
Framework

Exploring the Space of Black-box Attacks on Deep Neural Networks


Title	Exploring the Space of Black-box Attacks on Deep Neural Networks
Authors	Arjun Nitin Bhagoji, Warren He, Bo Li, Dawn Song
Abstract	Existing black-box attacks on deep neural networks (DNNs) so far have largely focused on transferability, where an adversarial instance generated for a locally trained model can “transfer” to attack other learning models. In this paper, we propose novel Gradient Estimation black-box attacks for adversaries with query access to the target model’s class probabilities, which do not rely on transferability. We also propose strategies to decouple the number of queries required to generate each adversarial sample from the dimensionality of the input. An iterative variant of our attack achieves close to 100% adversarial success rates for both targeted and untargeted attacks on DNNs. We carry out extensive experiments for a thorough comparative evaluation of black-box attacks and show that the proposed Gradient Estimation attacks outperform all transferability based black-box attacks we tested on both MNIST and CIFAR-10 datasets, achieving adversarial success rates similar to well known, state-of-the-art white-box attacks. We also apply the Gradient Estimation attacks successfully against a real-world Content Moderation classifier hosted by Clarifai. Furthermore, we evaluate black-box attacks against state-of-the-art defenses. We show that the Gradient Estimation attacks are very effective even against these defenses.
Tasks
Published	2017-12-27
URL	http://arxiv.org/abs/1712.09491v1
PDF	http://arxiv.org/pdf/1712.09491v1.pdf
PWC	https://paperswithcode.com/paper/exploring-the-space-of-black-box-attacks-on
Repo
Framework

MBMF: Model-Based Priors for Model-Free Reinforcement Learning


Title	MBMF: Model-Based Priors for Model-Free Reinforcement Learning
Authors	Somil Bansal, Roberto Calandra, Kurtland Chua, Sergey Levine, Claire Tomlin
Abstract	Reinforcement Learning is divided in two main paradigms: model-free and model-based. Each of these two paradigms has strengths and limitations, and has been successfully applied to real world domains that are appropriate to its corresponding strengths. In this paper, we present a new approach aimed at bridging the gap between these two paradigms. We aim to take the best of the two paradigms and combine them in an approach that is at the same time data-efficient and cost-savvy. We do so by learning a probabilistic dynamics model and leveraging it as a prior for the intertwined model-free optimization. As a result, our approach can exploit the generality and structure of the dynamics model, but is also capable of ignoring its inevitable inaccuracies, by directly incorporating the evidence provided by the direct observation of the cost. Preliminary results demonstrate that our approach outperforms purely model-based and model-free approaches, as well as the approach of simply switching from a model-based to a model-free setting.
Tasks
Published	2017-09-10
URL	http://arxiv.org/abs/1709.03153v2
PDF	http://arxiv.org/pdf/1709.03153v2.pdf
PWC	https://paperswithcode.com/paper/mbmf-model-based-priors-for-model-free
Repo
Framework

Analysing Temporal Evolution of Interlingual Wikipedia Article Pairs


Title	Analysing Temporal Evolution of Interlingual Wikipedia Article Pairs
Authors	Simon Gottschalk, Elena Demidova
Abstract	Wikipedia articles representing an entity or a topic in different language editions evolve independently within the scope of the language-specific user communities. This can lead to different points of views reflected in the articles, as well as complementary and inconsistent information. An analysis of how the information is propagated across the Wikipedia language editions can provide important insights in the article evolution along the temporal and cultural dimensions and support quality control. To facilitate such analysis, we present MultiWiki - a novel web-based user interface that provides an overview of the similarities and differences across the article pairs originating from different language editions on a timeline. MultiWiki enables users to observe the changes in the interlingual article similarity over time and to perform a detailed visual comparison of the article snapshots at a particular time point.
Tasks
Published	2017-02-02
URL	http://arxiv.org/abs/1702.00716v1
PDF	http://arxiv.org/pdf/1702.00716v1.pdf
PWC	https://paperswithcode.com/paper/analysing-temporal-evolution-of-interlingual
Repo
Framework