January 30, 2020

3151 words 15 mins read

Paper Group ANR 335

A Novel Deep Neural Network Based Approach for Sparse Code Multiple Access. Distributed Learning of Deep Neural Networks using Independent Subnet Training. Dynamic Learning with Frequent New Product Launches: A Sequential Multinomial Logit Bandit Problem. Angle-Closure Detection in Anterior Segment OCT based on Multi-Level Deep Network. A Variation …

A Novel Deep Neural Network Based Approach for Sparse Code Multiple Access


Title	A Novel Deep Neural Network Based Approach for Sparse Code Multiple Access
Authors	Jinzhi Lin, Shengzhong Feng, Zhile Yang, Yun Zhang, Yong Zhang
Abstract	Sparse code multiple access (SCMA) has been one of non-orthogonal multiple access (NOMA) schemes aiming to support high spectral efficiency and ubiquitous access requirements for 5G wireless communication networks. Conventional SCMA approaches are confronting remarkable challenges in designing low complexity high accuracy decoding algorithm and constructing optimum codebooks. Fortunately, the recent spotlighted deep learning technologies are of significant potentials in solving many communication engineering problems. Inspired by this, we explore approaches to improve SCMA performances with the help of deep learning methods. We propose and train a deep neural network (DNN) called DL-SCMA to learn to decode SCMA modulated signals corrupted by additive white Gaussian noise (AWGN). Putting encoding and decoding together, an autoencoder called AE-SCMA is established and trained to generate optimal SCMA codewords and reconstruct original bits. Furthermore, by manipulating the mapping vectors, an autoencoder is able to generalize SCMA, thus a dense code multiple access (DCMA) scheme is proposed. Simulations show that the DNN SCMA decoder significantly outperforms the conventional message passing algorithm (MPA) in terms of bit error rate (BER), symbol error rate (SER) and computational complexity, and AE-SCMA also demonstrates better performances via constructing better SCMA codebooks. The performance of deep learning aided DCMA is superior to the SCMA.
Tasks
Published	2019-06-04
URL	https://arxiv.org/abs/1906.03169v2
PDF	https://arxiv.org/pdf/1906.03169v2.pdf
PWC	https://paperswithcode.com/paper/a-novel-deep-neural-network-based-approach
Repo
Framework

Distributed Learning of Deep Neural Networks using Independent Subnet Training


Title	Distributed Learning of Deep Neural Networks using Independent Subnet Training
Authors	Binhang Yuan, Anastasios Kyrillidis, Christopher M. Jermaine
Abstract	We alleviate costly communication/computation overhead in classical distributed learning by introducing independent subnet training: a novel, simple, jointly model-parallel and data-parallel approach to distributed neural network training.Our main idea is that, per iteration, the model’s neurons can be randomly divided into smaller surrogate models without replacement—dubbed as subnetworks or subnets—and each subwork is sent for training only to a single worker. This way, our algorithm broadcasts the whole model parameters only once into the distributed network per synchronization cycle. This not only reduces the overall communication overhead, but also the computation workload: each worker only receives the weights associated with the subwork it has been assigned to. Further, subwork generation and training reduces synchronization frequency: since workers train disjoint portions of the network as if they were independent models, training continues for longer periods of time before synchronization, similar to local SGD approaches. We test our approach on speech recognition and product recommendation applications, as well as image classification tasks. Subnet training: i) leads to accelerated training, as compared to state of the art distributed models, and ii) often results into boosting the testing accuracy, as it implicitly leverages dropout regularization during training.
Tasks	Image Classification, Product Recommendation, Speech Recognition
Published	2019-10-04
URL	https://arxiv.org/abs/1910.02120v3
PDF	https://arxiv.org/pdf/1910.02120v3.pdf
PWC	https://paperswithcode.com/paper/distributed-learning-of-deep-neural-networks
Repo
Framework

Dynamic Learning with Frequent New Product Launches: A Sequential Multinomial Logit Bandit Problem


Title	Dynamic Learning with Frequent New Product Launches: A Sequential Multinomial Logit Bandit Problem
Authors	Junyu Cao, Wei Sun
Abstract	Motivated by the phenomenon that companies introduce new products to keep abreast with customers’ rapidly changing tastes, we consider a novel online learning setting where a profit-maximizing seller needs to learn customers’ preferences through offering recommendations, which may contain existing products and new products that are launched in the middle of a selling period. We propose a sequential multinomial logit (SMNL) model to characterize customers’ behavior when product recommendations are presented in tiers. For the offline version with known customers’ preferences, we propose a polynomial-time algorithm and characterize the properties of the optimal tiered product recommendation. For the online problem, we propose a learning algorithm and quantify its regret bound. Moreover, we extend the setting to incorporate a constraint which ensures every new product is learned to a given accuracy. Our results demonstrate the tier structure can be used to mitigate the risks associated with learning new products.
Tasks	Product Recommendation
Published	2019-04-29
URL	http://arxiv.org/abs/1904.12445v1
PDF	http://arxiv.org/pdf/1904.12445v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-learning-with-frequent-new-product
Repo
Framework

Angle-Closure Detection in Anterior Segment OCT based on Multi-Level Deep Network


Title	Angle-Closure Detection in Anterior Segment OCT based on Multi-Level Deep Network
Authors	Huazhu Fu, Yanwu Xu, Stephen Lin, Damon Wing Kee Wong, Mani Baskaran, Meenakshi Mahesh, Tin Aung, Jiang Liu
Abstract	Irreversible visual impairment is often caused by primary angle-closure glaucoma, which could be detected via Anterior Segment Optical Coherence Tomography (AS-OCT). In this paper, an automated system based on deep learning is presented for angle-closure detection in AS-OCT images. Our system learns a discriminative representation from training data that captures subtle visual cues not modeled by handcrafted features. A Multi-Level Deep Network (MLDN) is proposed to formulate this learning, which utilizes three particular AS-OCT regions based on clinical priors: the global anterior segment structure, local iris region, and anterior chamber angle (ACA) patch. In our method, a sliding window based detector is designed to localize the ACA region, which addresses ACA detection as a regression task. Then, three parallel sub-networks are applied to extract AS-OCT representations for the global image and at clinically-relevant local regions. Finally, the extracted deep features of these sub-networks are concatenated into one fully connected layer to predict the angle-closure detection result. In the experiments, our system is shown to surpass previous detection methods and other deep learning systems on two clinical AS-OCT datasets.
Tasks
Published	2019-02-10
URL	http://arxiv.org/abs/1902.03585v1
PDF	http://arxiv.org/pdf/1902.03585v1.pdf
PWC	https://paperswithcode.com/paper/angle-closure-detection-in-anterior-segment
Repo
Framework

A Variational Auto-Encoder Model for Stochastic Point Processes


Title	A Variational Auto-Encoder Model for Stochastic Point Processes
Authors	Nazanin Mehrasa, Akash Abdu Jyothi, Thibaut Durand, Jiawei He, Leonid Sigal, Greg Mori
Abstract	We propose a novel probabilistic generative model for action sequences. The model is termed the Action Point Process VAE (APP-VAE), a variational auto-encoder that can capture the distribution over the times and categories of action sequences. Modeling the variety of possible action sequences is a challenge, which we show can be addressed via the APP-VAE’s use of latent representations and non-linear functions to parameterize distributions over which event is likely to occur next in a sequence and at what time. We empirically validate the efficacy of APP-VAE for modeling action sequences on the MultiTHUMOS and Breakfast datasets.
Tasks	Point Processes
Published	2019-04-05
URL	http://arxiv.org/abs/1904.03273v1
PDF	http://arxiv.org/pdf/1904.03273v1.pdf
PWC	https://paperswithcode.com/paper/a-variational-auto-encoder-model-for
Repo
Framework

Excess risk bounds in robust empirical risk minimization


Title	Excess risk bounds in robust empirical risk minimization
Authors	Stanislav Minsker, Timothée Mathieu
Abstract	This paper investigates robust versions of the general empirical risk minimization algorithm, one of the core techniques underlying modern statistical methods. Success of the empirical risk minimization is based on the fact that for a “well-behaved” stochastic process $\left{ f(X), \ f\in \mathcal F\right}$ indexed by a class of functions $f\in \mathcal F$, averages $\frac{1}{N}\sum_{j=1}^N f(X_j)$ evaluated over a sample $X_1,\ldots,X_N$ of i.i.d. copies of $X$ provide good approximation to the expectations $\mathbb E f(X)$ uniformly over large classes $f\in \mathcal F$. However, this might no longer be true if the marginal distributions of the process are heavy-tailed or if the sample contains outliers. We propose a version of empirical risk minimization based on the idea of replacing sample averages by robust proxies of the expectation, and obtain high-confidence bounds for the excess risk of resulting estimators. In particular, we show that the excess risk of robust estimators can converge to $0$ at fast rates with respect to the sample size. We discuss implications of the main results to the linear and logistic regression problems, and evaluate the numerical performance of proposed methods on simulated and real data.
Tasks
Published	2019-10-16
URL	https://arxiv.org/abs/1910.07485v1
PDF	https://arxiv.org/pdf/1910.07485v1.pdf
PWC	https://paperswithcode.com/paper/excess-risk-bounds-in-robust-empirical-risk
Repo
Framework

Predicting wind pressures around circular cylinders using machine learning techniques


Title	Predicting wind pressures around circular cylinders using machine learning techniques
Authors	Gang Hu, K. C. S. Kwok
Abstract	Numerous studies have been carried out to measure wind pressures around circular cylinders since the early 20th century due to its engineering significance. Consequently, a large amount of wind pressure data sets have accumulated, which presents an excellent opportunity for using machine learning (ML) techniques to train models to predict wind pressures around circular cylinders. Wind pressures around smooth circular cylinders are a function of mainly the Reynolds number (Re), turbulence intensity (Ti) of the incident wind, and circumferential angle of the cylinder. Considering these three parameters as the inputs, this study trained two ML models to predict mean and fluctuating pressures respectively. Three machine learning algorithms including decision tree regressor, random forest, and gradient boosting regression trees (GBRT) were tested. The GBRT models exhibited the best performance for predicting both mean and fluctuating pressures, and they are capable of making accurate predictions for Re ranging from 10^4 to 10^6 and Ti ranging from 0% to 15%. It is believed that the GBRT models provide very efficient and economical alternative to traditional wind tunnel tests and computational fluid dynamic simulations for determining wind pressures around smooth circular cylinders within the studied Re and Ti range.
Tasks
Published	2019-01-21
URL	http://arxiv.org/abs/1901.06752v1
PDF	http://arxiv.org/pdf/1901.06752v1.pdf
PWC	https://paperswithcode.com/paper/predicting-wind-pressures-around-circular
Repo
Framework

Selfie Drone Stick: A Natural Interface for Quadcopter Photography


Title	Selfie Drone Stick: A Natural Interface for Quadcopter Photography
Authors	Saif Alabachi, Gita Sukthankar, Rahul Sukthankar
Abstract	A physical selfie stick extends the user’s reach, enabling the creation of personal photos that include more of the background scene. Conversely a quadcopter can capture photos at distances unattainable for the human, but teloperating a quadcopter to a good viewpoint is a non-trivial task. This paper presents a natural interface for quadcopter photography, the Selfie Drone Stick that allows the user to guide the quadcopter to the optimal vantage point based on the phone’s sensors. The user points the phone once, and the quadcopter autonomously flies to the target viewpoint based on the phone camera and IMU sensor data. Visual servoing is achieved through the combination of a dense neural network object detector that matches the image captured from the phone camera to a bounding box in the scene and a Deep Q-Network controller that flies to the desired vantage point. Our deep learning architecture is trained with a combination of real-world images and simulated flight data. Integrating the deep RL controller with an intuitive interface provides a more positive user experience than a standard teleoperation paradigm.
Tasks
Published	2019-09-14
URL	https://arxiv.org/abs/1909.06491v1
PDF	https://arxiv.org/pdf/1909.06491v1.pdf
PWC	https://paperswithcode.com/paper/selfie-drone-stick-a-natural-interface-for
Repo
Framework

A Smartphone-Based Skin Disease Classification Using MobileNet CNN


Title	A Smartphone-Based Skin Disease Classification Using MobileNet CNN
Authors	Jessica Velasco, Cherry Pascion, Jean Wilmar Alberio, Jonathan Apuang, John Stephen Cruz, Mark Angelo Gomez, Benjamin Jr. Molina, Lyndon Tuala, August Thio-ac, Romeo Jr. Jorda
Abstract	The MobileNet model was used by applying transfer learning on the 7 skin diseases to create a skin disease classification system on Android application. The proponents gathered a total of 3,406 images and it is considered as imbalanced dataset because of the unequal number of images on its classes. Using different sampling method and preprocessing of input data was explored to further improved the accuracy of the MobileNet. Using under-sampling method and the default preprocessing of input data achieved an 84.28% accuracy. While, using imbalanced dataset and default preprocessing of input data achieved a 93.6% accuracy. Then, researchers explored oversampling the dataset and the model attained a 91.8% accuracy. Lastly, by using oversampling technique and data augmentation on preprocessing the input data provide a 94.4% accuracy and this model was deployed on the developed Android application.
Tasks	Data Augmentation, Transfer Learning
Published	2019-11-13
URL	https://arxiv.org/abs/1911.07929v1
PDF	https://arxiv.org/pdf/1911.07929v1.pdf
PWC	https://paperswithcode.com/paper/a-smartphone-based-skin-disease
Repo
Framework

BiNet: Degraded-Manuscript Binarization in Diverse Document Textures and Layouts using Deep Encoder-Decoder Networks


Title	BiNet: Degraded-Manuscript Binarization in Diverse Document Textures and Layouts using Deep Encoder-Decoder Networks
Authors	Maruf A. Dhali, Jan Willem de Wit, Lambert Schomaker
Abstract	Handwritten document-image binarization is a semantic segmentation process to differentiate ink pixels from background pixels. It is one of the essential steps towards character recognition, writer identification, and script-style evolution analysis. The binarization task itself is challenging due to the vast diversity of writing styles, inks, and paper materials. It is even more difficult for historical manuscripts due to the aging and degradation of the documents over time. One of such manuscripts is the Dead Sea Scrolls (DSS) image collection, which poses extreme challenges for the existing binarization techniques. This article proposes a new binarization technique for the DSS images using the deep encoder-decoder networks. Although the artificial neural network proposed here is primarily designed to binarize the DSS images, it can be trained on different manuscript collections as well. Additionally, the use of transfer learning makes the network already utilizable for a wide range of handwritten documents, making it a unique multi-purpose tool for binarization. Qualitative results and several quantitative comparisons using both historical manuscripts and datasets from handwritten document image binarization competition (H-DIBCO and DIBCO) exhibit the robustness and the effectiveness of the system. The best performing network architecture proposed here is a variant of the U-Net encoder-decoders.
Tasks	Semantic Segmentation, Transfer Learning
Published	2019-11-13
URL	https://arxiv.org/abs/1911.07930v1
PDF	https://arxiv.org/pdf/1911.07930v1.pdf
PWC	https://paperswithcode.com/paper/binet-degraded-manuscript-binarization-in
Repo
Framework

End-To-End Prediction of Emotion From Heartbeat Data Collected by a Consumer Fitness Tracker


Title	End-To-End Prediction of Emotion From Heartbeat Data Collected by a Consumer Fitness Tracker
Authors	Ross Harper, Joshua Southern
Abstract	Automatic detection of emotion has the potential to revolutionize mental health and wellbeing. Recent work has been successful in predicting affect from unimodal electrocardiogram (ECG) data. However, to be immediately relevant for real-world applications, physiology-based emotion detection must make use of ubiquitous photoplethysmogram (PPG) data collected by affordable consumer fitness trackers. Additionally, applications of emotion detection in healthcare settings will require some measure of uncertainty over model predictions. We present here a Bayesian deep learning model for end-to-end classification of emotional valence, using only the unimodal heartbeat time series collected by a consumer fitness tracker (Garmin V'ivosmart 3). We collected a new dataset for this task, and report a peak F1 score of 0.7. This demonstrates a practical relevance of physiology-based emotion detection `in the wild’ today. \|
Tasks	Time Series
Published	2019-07-16
URL	https://arxiv.org/abs/1907.07327v1
PDF	https://arxiv.org/pdf/1907.07327v1.pdf
PWC	https://paperswithcode.com/paper/end-to-end-prediction-of-emotion-from
Repo
Framework

Lipschitz Learning for Signal Recovery


Title	Lipschitz Learning for Signal Recovery
Authors	Hong Jiang, Jong-Hoon Ahn, Xiaoyang Wang
Abstract	We consider the recovery of signals from their observations, which are samples of a transform of the signals rather than the signals themselves, by using machine learning (ML). We will develop a theoretical framework to characterize the signals that can be robustly recovered from their observations by an ML algorithm, and establish a Lipschitz condition on signals and observations that is both necessary and sufficient for the existence of a robust recovery. We will compare the Lipschitz condition with the well-known restricted isometry property of the sparse recovery of compressive sensing, and show the former is more general and less restrictive. For linear observations, our work also suggests an ML method in which the output space is reduced to the lowest possible dimension.
Tasks	Compressive Sensing
Published	2019-10-04
URL	https://arxiv.org/abs/1910.02142v1
PDF	https://arxiv.org/pdf/1910.02142v1.pdf
PWC	https://paperswithcode.com/paper/lipschitz-learning-for-signal-recovery
Repo
Framework

SysML’19 demo: customizable and reusable Collective Knowledge pipelines to automate and reproduce machine learning experiments


Title	SysML’19 demo: customizable and reusable Collective Knowledge pipelines to automate and reproduce machine learning experiments
Authors	Grigori Fursin
Abstract	Reproducing, comparing and reusing results from machine learning and systems papers is a very tedious, ad hoc and time-consuming process. I will demonstrate how to automate this process using open-source, portable, customizable and CLI-based Collective Knowledge workflows and pipelines developed by the community. I will help participants run several real-world non-virtualized CK workflows from the SysML’19 conference, companies (General Motors, Arm) and MLPerf benchmark to automate benchmarking and co-design of efficient software/hardware stacks for machine learning workloads. I hope that our approach will help authors reduce their effort when sharing reusable and extensible research artifacts while enabling artifact evaluators to automatically validate experimental results from published papers in a standard and portable way.
Tasks
Published	2019-03-31
URL	http://arxiv.org/abs/1904.00324v1
PDF	http://arxiv.org/pdf/1904.00324v1.pdf
PWC	https://paperswithcode.com/paper/sysml19-demo-customizable-and-reusable
Repo
Framework

Capturing Financial markets to apply Deep Reinforcement Learning


Title	Capturing Financial markets to apply Deep Reinforcement Learning
Authors	Souradeep Chakraborty
Abstract	In this paper we explore the usage of deep reinforcement learning algorithms to automatically generate consistently profitable, robust, uncorrelated trading signals in any general financial market. In order to do this, we present a novel Markov decision process (MDP) model to capture the financial trading markets. We review and propose various modifications to existing approaches and explore different techniques like the usage of technical indicators, to succinctly capture the market dynamics to model the markets. We then go on to use deep reinforcement learning to enable the agent (the algorithm) to learn how to take profitable trades in any market on its own, while suggesting various methodology changes and leveraging the unique representation of the FMDP (financial MDP) to tackle the primary challenges faced in similar works. Through our experimentation results, we go on to show that our model could be easily extended to two very different financial markets and generates a positively robust performance in all conducted experiments.
Tasks
Published	2019-07-09
URL	https://arxiv.org/abs/1907.04373v3
PDF	https://arxiv.org/pdf/1907.04373v3.pdf
PWC	https://paperswithcode.com/paper/deep-reinforcement-learning-in-financial
Repo
Framework

Unsupervised Image Super-Resolution with an Indirect Supervised Path


Title	Unsupervised Image Super-Resolution with an Indirect Supervised Path
Authors	Zhen Han, Enyan Dai, Xu Jia, Xiaoying Ren, Shuaijun Chen, Chunjing Xu, Jianzhuang Liu, Qi Tian
Abstract	The task of single image super-resolution (SISR) aims at reconstructing a high-resolution (HR) image from a low-resolution (LR) image. Although significant progress has been made by deep learning models, they are trained on synthetic paired data in a supervised way and do not perform well on real data. There are several attempts that directly apply unsupervised image translation models to address such a problem. However, unsupervised low-level vision problem poses more challenge on the accuracy of translation. In this work,we propose a novel framework which is composed of two stages: 1) unsupervised image translation between real LR images and synthetic LR images; 2) supervised super-resolution from approximated real LR images to HR images. It takes the synthetic LR images as a bridge and creates an indirect supervised path from real LR images to HR images. Any existed deep learning based image super-resolution model can be integrated into the second stage of the proposed framework for further improvement. In addition it shows great flexibility in balancing between distortion and perceptual quality under unsupervised setting. The proposed method is evaluated on both NTIRE 2017 and 2018 challenge datasets and achieves favorable performance against supervised methods.
Tasks	Image Super-Resolution, Super-Resolution
Published	2019-10-07
URL	https://arxiv.org/abs/1910.02593v2
PDF	https://arxiv.org/pdf/1910.02593v2.pdf
PWC	https://paperswithcode.com/paper/unsupervised-image-super-resolution-with-an
Repo
Framework