January 26, 2020

3304 words 16 mins read

Paper Group ANR 1570

Solving Partial Assignment Problems using Random Clique Complexes. SOM-Guided Evolutionary Search for Solving MinMax Multiple-TSP. A Predictive On-Demand Placement of UAV Base Stations Using Echo State Network. Hahahahaha, Duuuuude, Yeeessss!: A two-parameter characterization of stretchable words and the dynamics of mistypings and misspellings. Con …

Solving Partial Assignment Problems using Random Clique Complexes


Title	Solving Partial Assignment Problems using Random Clique Complexes
Authors	Charu Sharma, Deepak Nathani, Manohar Kaul
Abstract	We present an alternate formulation of the partial assignment problem as matching random clique complexes, that are higher-order analogues of random graphs, designed to provide a set of invariants that better detect higher-order structure. The proposed method creates random clique adjacency matrices for each k-skeleton of the random clique complexes and matches them, taking into account each point as the affine combination of its geometric neighbourhood. We justify our solution theoretically, by analyzing the runtime and storage complexity of our algorithm along with the asymptotic behaviour of the quadratic assignment problem (QAP) that is associated with the underlying random clique adjacency matrices. Experiments on both synthetic and real-world datasets, containing severe occlusions and distortions, provide insight into the accuracy, efficiency, and robustness of our approach. We outperform diverse matching algorithms by a significant margin.
Tasks
Published	2019-07-03
URL	https://arxiv.org/abs/1907.01739v1
PDF	https://arxiv.org/pdf/1907.01739v1.pdf
PWC	https://paperswithcode.com/paper/solving-partial-assignment-problems-using-1
Repo
Framework

SOM-Guided Evolutionary Search for Solving MinMax Multiple-TSP


Title	SOM-Guided Evolutionary Search for Solving MinMax Multiple-TSP
Authors	Vlad-Ioan Lupoaie, Ivona-Alexandra Chili, Mihaela Elena Breaban, Madalina Raschip
Abstract	Multiple-TSP, also abbreviated in the literature as mTSP, is an extension of the Traveling Salesman Problem that lies at the core of many variants of the Vehicle Routing problem of great practical importance. The current paper develops and experiments with Self Organizing Maps, Evolutionary Algorithms and Ant Colony Systems to tackle the MinMax formulation of the Single-Depot Multiple-TSP. Hybridization between the neural network approach and the two meta-heuristics shows to bring significant improvements, outperforming results reported in the literature on a set of problem instances taken from TSPLIB.
Tasks
Published	2019-07-27
URL	https://arxiv.org/abs/1907.11910v1
PDF	https://arxiv.org/pdf/1907.11910v1.pdf
PWC	https://paperswithcode.com/paper/som-guided-evolutionary-search-for-solving
Repo
Framework

A Predictive On-Demand Placement of UAV Base Stations Using Echo State Network


Title	A Predictive On-Demand Placement of UAV Base Stations Using Echo State Network
Authors	Haoran Peng, Chao Chen, Chuan-Chi Lai, Li-Chun Wang, Zhu Han
Abstract	The unmanned aerial vehicles base stations (UAV-BSs) have great potential in being widely used in many dynamic application scenarios. In those scenarios, the movements of served user equipments (UEs) are inevitable, so the UAV-BSs needs to be re-positioned dynamically for providing seamless services. In this paper, we propose a system framework consisting of UEs clustering, UAV-BS placement, UEs trajectories prediction, and UAV-BS reposition matching scheme, to serve the UEs seamlessly as well as minimize the energy cost of UAV-BSs’ reposition trajectories. An Echo State Network (ESN) based algorithm for predicting the future trajectories of UEs and a Kuhn-Munkres-based algorithm for finding the energy-efficient reposition trajectories of UAV-BSs is designed, respectively. We conduct a simulation using a real open dataset for performance validation. The simulation results indicate that the proposed framework achieves high prediction accuracy and provides the energy-efficient matching scheme.
Tasks
Published	2019-09-25
URL	https://arxiv.org/abs/1909.11598v2
PDF	https://arxiv.org/pdf/1909.11598v2.pdf
PWC	https://paperswithcode.com/paper/a-predictive-on-demand-placement-of-uav-base
Repo
Framework

Hahahahaha, Duuuuude, Yeeessss!: A two-parameter characterization of stretchable words and the dynamics of mistypings and misspellings


Title	Hahahahaha, Duuuuude, Yeeessss!: A two-parameter characterization of stretchable words and the dynamics of mistypings and misspellings
Authors	Tyler J. Gray, Christopher M. Danforth, Peter Sheridan Dodds
Abstract	Stretched words like `heellllp' or` heyyyyy’ are a regular feature of spoken language, often used to emphasize or exaggerate the underlying meaning of the root word. While stretched words are rarely found in formal written language and dictionaries, they are prevalent within social media. In this paper, we examine the frequency distributions of `stretchable words' found in roughly 100 billion tweets authored over an 8 year period. We introduce two central parameters,` balance’ and `stretch', that capture their main characteristics, and explore their dynamics by creating visual tools we call` balance plots’ and `spelling trees’. We discuss how the tools and methods we develop here could be used to study the statistical patterns of mistypings and misspellings, along with the potential applications in augmenting dictionaries, improving language processing, and in any area where sequence construction matters, such as genetics. \|
Tasks
Published	2019-07-09
URL	https://arxiv.org/abs/1907.03920v1
PDF	https://arxiv.org/pdf/1907.03920v1.pdf
PWC	https://paperswithcode.com/paper/hahahahaha-duuuuude-yeeessss-a-two-parameter
Repo
Framework

Continual Learning with Adaptive Weights (CLAW)


Title	Continual Learning with Adaptive Weights (CLAW)
Authors	Tameem Adel, Han Zhao, Richard E. Turner
Abstract	Approaches to continual learning aim to successfully learn a set of related tasks that arrive in an online manner. Recently, several frameworks have been developed which enable deep learning to be deployed in this learning scenario. A key modelling decision is to what extent the architecture should be shared across tasks. On the one hand, separately modelling each task avoids catastrophic forgetting but it does not support transfer learning and leads to large models. On the other hand, rigidly specifying a shared component and a task-specific part enables task transfer and limits the model size, but it is vulnerable to catastrophic forgetting and restricts the form of task-transfer that can occur. Ideally, the network should adaptively identify which parts of the network to share in a data driven way. Here we introduce such an approach called Continual Learning with Adaptive Weights (CLAW), which is based on probabilistic modelling and variational inference. Experiments show that CLAW achieves state-of-the-art performance on six benchmarks in terms of overall continual learning performance, as measured by classification accuracy, and in terms of addressing catastrophic forgetting.
Tasks	Continual Learning, Transfer Learning
Published	2019-11-21
URL	https://arxiv.org/abs/1911.09514v1
PDF	https://arxiv.org/pdf/1911.09514v1.pdf
PWC	https://paperswithcode.com/paper/continual-learning-with-adaptive-weights-claw-1
Repo
Framework

Encrypted Speech Recognition using Deep Polynomial Networks


Title	Encrypted Speech Recognition using Deep Polynomial Networks
Authors	Shi-Xiong Zhang, Yifan Gong, Dong Yu
Abstract	The cloud-based speech recognition/API provides developers or enterprises an easy way to create speech-enabled features in their applications. However, sending audios about personal or company internal information to the cloud, raises concerns about the privacy and security issues. The recognition results generated in cloud may also reveal some sensitive information. This paper proposes a deep polynomial network (DPN) that can be applied to the encrypted speech as an acoustic model. It allows clients to send their data in an encrypted form to the cloud to ensure that their data remains confidential, at mean while the DPN can still make frame-level predictions over the encrypted speech and return them in encrypted form. One good property of the DPN is that it can be trained on unencrypted speech features in the traditional way. To keep the cloud away from the raw audio and recognition results, a cloud-local joint decoding framework is also proposed. We demonstrate the effectiveness of model and framework on the Switchboard and Cortana voice assistant tasks with small performance degradation and latency increased comparing with the traditional cloud-based DNNs.
Tasks	Speech Recognition
Published	2019-05-11
URL	https://arxiv.org/abs/1905.05605v1
PDF	https://arxiv.org/pdf/1905.05605v1.pdf
PWC	https://paperswithcode.com/paper/encrypted-speech-recognition-using-deep
Repo
Framework

Deep Learning for Cognitive Neuroscience


Title	Deep Learning for Cognitive Neuroscience
Authors	Katherine R. Storrs, Nikolaus Kriegeskorte
Abstract	Neural network models can now recognise images, understand text, translate languages, and play many human games at human or superhuman levels. These systems are highly abstracted, but are inspired by biological brains and use only biologically plausible computations. In the coming years, neural networks are likely to become less reliant on learning from massive labelled datasets, and more robust and generalisable in their task performance. From their successes and failures, we can learn about the computational requirements of the different tasks at which brains excel. Deep learning also provides the tools for testing cognitive theories. In order to test a theory, we need to realise the proposed information-processing system at scale, so as to be able to assess its feasibility and emergent behaviours. Deep learning allows us to scale up from principles and circuit models to end-to-end trainable models capable of performing complex tasks. There are many levels at which cognitive neuroscientists can use deep learning in their work, from inspiring theories to serving as full computational models. Ongoing advances in deep learning bring us closer to understanding how cognition and perception may be implemented in the brain – the grand challenge at the core of cognitive neuroscience.
Tasks
Published	2019-03-04
URL	http://arxiv.org/abs/1903.01458v1
PDF	http://arxiv.org/pdf/1903.01458v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-cognitive-neuroscience
Repo
Framework

Opportunities and Challenges in Deep Learning Methods on Electrocardiogram Data: A Systematic Review


Title	Opportunities and Challenges in Deep Learning Methods on Electrocardiogram Data: A Systematic Review
Authors	Shenda Hong, Yuxi Zhou, Junyuan Shang, Cao Xiao, Jimeng Sun
Abstract	Objective: To conduct a systematic review of deep learning methods on Electrocardiogram (ECG) data from the perspective of model architecture and their application task. Methods: First, we extensively searched papers deploying deep learning (deep neural network networks) on ECG data that published between January 1st 2010 and September 30th 2019 from Google Scholar, PubMed and DBLP. Then we analyze them in three aspects including task, model and data. Finally, we conclude unresolved challenges and problems that existing models can not handle well. Results: The total number of papers is 124, among them 97 papers are published after in recent two years. Almost all kinds of common deep learning architectures have been used in ECG analytics tasks like disease detection/classification, annotation/localization, sleep staging, biometric human identification, denoising and so on. Conclusion: The number of works about deep learning on ECG data is growing explosively in recent years. Indeed, these works have achieve a far more better performance in terms of accuracy. However, there are some new challenges and problems like interpretability, scalability, efficiency, which need to be addressed and paid more attention. Moreover, it is also worth to investigate by discovering new interesting applications from both the dataset view and the method view. Significance: This paper summarizes existing deep learning methods on modeling ECG data from multiple views, while also point out existing challenges and problems, while can become potential research direction in the future.
Tasks	Denoising
Published	2019-12-28
URL	https://arxiv.org/abs/2001.01550v1
PDF	https://arxiv.org/pdf/2001.01550v1.pdf
PWC	https://paperswithcode.com/paper/opportunities-and-challenges-in-deep-learning
Repo
Framework

Learning to Transfer Learn


Title	Learning to Transfer Learn
Authors	Linchao Zhu, Sercan O. Arik, Yi Yang, Tomas Pfister
Abstract	We propose a novel framework, learning to transfer learn (L2TL), to improve transfer learning on a target dataset by judicious extraction of information from a source dataset. Our framework considers joint optimization of strongly-shared weights between models of source and target tasks, and employs adaptive weights for scaling of constituent loss terms. The adaptation of the weights is done using a reinforcement learning (RL)-based policy model, which is guided based on a performance metric on the target validation set. We demonstrate state-of-the-art performance of L2TL given fixed models, consistently outperforming fine-tuning baselines on various datasets. In addition, in the regimes of small-scale target datasets and significant label mismatch between source and target datasets, L2TL outperforms previous methods by a large margin.
Tasks	Transfer Learning
Published	2019-08-29
URL	https://arxiv.org/abs/1908.11406v1
PDF	https://arxiv.org/pdf/1908.11406v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-transfer-learn
Repo
Framework

Interpretable Adversarial Training for Text


Title	Interpretable Adversarial Training for Text
Authors	Samuel Barham, Soheil Feizi
Abstract	Generating high-quality and interpretable adversarial examples in the text domain is a much more daunting task than it is in the image domain. This is due partly to the discrete nature of text, partly to the problem of ensuring that the adversarial examples are still probable and interpretable, and partly to the problem of maintaining label invariance under input perturbations. In order to address some of these challenges, we introduce sparse projected gradient descent (SPGD), a new approach to crafting interpretable adversarial examples for text. SPGD imposes a directional regularization constraint on input perturbations by projecting them onto the directions to nearby word embeddings with highest cosine similarities. This constraint ensures that perturbations move each word embedding in an interpretable direction (i.e., towards another nearby word embedding). Moreover, SPGD imposes a sparsity constraint on perturbations at the sentence level by ignoring word-embedding perturbations whose norms are below a certain threshold. This constraint ensures that our method changes only a few words per sequence, leading to higher quality adversarial examples. Our experiments with the IMDB movie review dataset show that the proposed SPGD method improves adversarial example interpretability and likelihood (evaluated by average per-word perplexity) compared to state-of-the-art methods, while suffering little to no loss in training performance.
Tasks	Word Embeddings
Published	2019-05-30
URL	https://arxiv.org/abs/1905.12864v1
PDF	https://arxiv.org/pdf/1905.12864v1.pdf
PWC	https://paperswithcode.com/paper/interpretable-adversarial-training-for-text
Repo
Framework

Deep Neural Networks for Marine Debris Detection in Sonar Images


Title	Deep Neural Networks for Marine Debris Detection in Sonar Images
Authors	Matias Valdenegro-Toro
Abstract	Garbage and waste disposal is one of the biggest challenges currently faced by mankind. Proper waste disposal and recycling is a must in any sustainable community, and in many coastal areas there is significant water pollution in the form of floating or submerged garbage. This is called marine debris. Submerged marine debris threatens marine life, and for shallow coastal areas, it can also threaten fishing vessels [I~niguez et al. 2016, Renewable and Sustainable Energy Reviews]. Submerged marine debris typically stays in the environment for a long time (20+ years), and consists of materials that can be recycled, such as metals, plastics, glass, etc. Many of these items should not be disposed in water bodies as this has a negative effect in the environment and human health. This thesis performs a comprehensive evaluation on the use of DNNs for the problem of marine debris detection in FLS images, as well as related problems such as image classification, matching, and detection proposals. We do this in a dataset of 2069 FLS images that we captured with an ARIS Explorer 3000 sensor on marine debris objects lying in the floor of a small water tank. The objects we used to produce this dataset contain typical household marine debris and distractor marine objects (tires, hooks, valves, etc), divided in 10 classes plus a background class. Our results show that for the evaluated tasks, DNNs are a superior technique than the corresponding state of the art. There are large gains particularly for the matching and detection proposal tasks. We also study the effect of sample complexity and object size in many tasks, which is valuable information for practitioners. We expect that our results will advance the objective of using Autonomous Underwater Vehicles to automatically survey, detect and collect marine debris from underwater environments.
Tasks	Image Classification
Published	2019-05-13
URL	https://arxiv.org/abs/1905.05241v1
PDF	https://arxiv.org/pdf/1905.05241v1.pdf
PWC	https://paperswithcode.com/paper/deep-neural-networks-for-marine-debris
Repo
Framework

Economy Statistical Recurrent Units For Inferring Nonlinear Granger Causality


Title	Economy Statistical Recurrent Units For Inferring Nonlinear Granger Causality
Authors	Saurabh Khanna, Vincent Y. F. Tan
Abstract	Granger causality is a widely-used criterion for analyzing interactions in large-scale networks. As most physical interactions are inherently nonlinear, we consider the problem of inferring the existence of pairwise Granger causality between nonlinearly interacting stochastic processes from their time series measurements. Our proposed approach relies on modeling the embedded nonlinearities in the measurements using a component-wise time series prediction model based on Statistical Recurrent Units (SRUs). We make a case that the network topology of Granger causal relations is directly inferrable from a structured sparse estimate of the internal parameters of the SRU networks trained to predict the processes$'$ time series measurements. We propose a variant of SRU, called economy-SRU, which, by design has considerably fewer trainable parameters, and therefore less prone to overfitting. The economy-SRU computes a low-dimensional sketch of its high-dimensional hidden state in the form of random projections to generate the feedback for its recurrent processing. Additionally, the internal weight parameters of the economy-SRU are strategically regularized in a group-wise manner to facilitate the proposed network in extracting meaningful predictive features that are highly time-localized to mimic real-world causal events. Extensive experiments are carried out to demonstrate that the proposed economy-SRU based time series prediction model outperforms the MLP, LSTM and attention-gated CNN-based time series models considered previously for inferring Granger causality.
Tasks	Time Series, Time Series Prediction
Published	2019-11-22
URL	https://arxiv.org/abs/1911.09879v2
PDF	https://arxiv.org/pdf/1911.09879v2.pdf
PWC	https://paperswithcode.com/paper/economy-statistical-recurrent-units-for-1
Repo
Framework

DC-AL GAN: Pseudoprogression and True Tumor Progression of Glioblastoma Multiform Image Classification Based on DCGAN and AlexNet


Title	DC-AL GAN: Pseudoprogression and True Tumor Progression of Glioblastoma Multiform Image Classification Based on DCGAN and AlexNet
Authors	Meiyu Li, Hailiang Tang, Michael D. Chan, Xiaobo Zhou, Xiaohua Qian
Abstract	Pseudoprogression (PsP) occurs in 20-30% of patients with glioblastoma multiforme (GBM) after receiving the standard treatment. In the course of post-treatment magnetic resonance imaging (MRI), PsP exhibits similarities in shape and intensity to the true tumor progression (TTP) of GBM. So, these similarities pose challenges on the differentiation of these types of progression and hence the selection of the appropriate clinical treatment strategy. In this paper, we introduce DC-AL GAN, a novel feature learning method based on deep convolutional generative adversarial network (DCGAN) and AlexNet, to discriminate between PsP and TTP in MRI images. Due to the adversarial relationship between the generator and the discriminator of DCGAN, high-level discriminative features of PsP and TTP can be derived for the discriminator with AlexNet. Also, a feature fusion scheme is used to combine higher-layer features with lower-layer information, leading to more powerful features that are used for effectively discriminating between PsP and TTP. The experimental results show that DC-AL GAN achieves desirable PsP and TTP classification performance that is superior to other state-of-the-art methods.
Tasks	Image Classification
Published	2019-02-16
URL	https://arxiv.org/abs/1902.06085v4
PDF	https://arxiv.org/pdf/1902.06085v4.pdf
PWC	https://paperswithcode.com/paper/dc-al-gan-pseudoprogression-and-true-tumor
Repo
Framework

Hierarchical Multi-Label Dialog Act Recognition on Spanish Data


Title	Hierarchical Multi-Label Dialog Act Recognition on Spanish Data
Authors	Eugénio Ribeiro, Ricardo Ribeiro, David Martins de Matos
Abstract	Dialog acts reveal the intention behind the uttered words. Thus, their automatic recognition is important for a dialog system trying to understand its conversational partner. The study presented in this article approaches that task on the DIHANA corpus, whose three-level dialog act annotation scheme poses problems which have not been explored in recent studies. In addition to the hierarchical problem, the two lower levels pose multi-label classification problems. Furthermore, each level in the hierarchy refers to a different aspect concerning the intention of the speaker both in terms of the structure of the dialog and the task. Also, since its dialogs are in Spanish, it allows us to assess whether the state-of-the-art approaches on English data generalize to a different language. More specifically, we compare the performance of different segment representation approaches focusing on both sequences and patterns of words and assess the importance of the dialog history and the relations between the multiple levels of the hierarchy. Concerning the single-label classification problem posed by the top level, we show that the conclusions drawn on English data also hold on Spanish data. Furthermore, we show that the approaches can be adapted to multi-label scenarios. Finally, by hierarchically combining the best classifiers for each level, we achieve the best results reported for this corpus.
Tasks	Multi-Label Classification
Published	2019-07-29
URL	https://arxiv.org/abs/1907.12316v1
PDF	https://arxiv.org/pdf/1907.12316v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-multi-label-dialog-act
Repo
Framework

Chester: A Web Delivered Locally Computed Chest X-Ray Disease Prediction System


Title	Chester: A Web Delivered Locally Computed Chest X-Ray Disease Prediction System
Authors	Joseph Paul Cohen, Paul Bertin, Vincent Frappier
Abstract	In order to bridge the gap between Deep Learning researchers and medical professionals we develop a very accessible free prototype system which can be used by medical professionals to understand the reality of Deep Learning tools for chest X-ray diagnostics. The system is designed to be a second opinion where a user can process an image to confirm or aid in their diagnosis. Code and network weights are delivered via a URL to a web browser (including cell phones) but the patient data remains on the users machine and all processing occurs locally. This paper discusses the three main components in detail: out-of-distribution detection, disease prediction, and prediction explanation. The system open source and freely available here: https://mlmed.org/tools/xray
Tasks	Disease Prediction, Out-of-Distribution Detection
Published	2019-01-31
URL	https://arxiv.org/abs/1901.11210v3
PDF	https://arxiv.org/pdf/1901.11210v3.pdf
PWC	https://paperswithcode.com/paper/chester-a-web-delivered-locally-computed
Repo
Framework