January 30, 2020

3174 words 15 mins read

Paper Group ANR 306

FastEstimator: A Deep Learning Library for Fast Prototyping and Productization. Generic Primitive Detection in Point Clouds Using Novel Minimal Quadric Fits. Brain correlates of task-load and dementia elucidation with tensor machine learning using oddball BCI paradigm. Dynamic Multi-path Neural Network. Promotion of Answer Value Measurement with Do …

FastEstimator: A Deep Learning Library for Fast Prototyping and Productization


Title	FastEstimator: A Deep Learning Library for Fast Prototyping and Productization
Authors	Xiaomeng Dong, Junpyo Hong, Hsi-Ming Chang, Michael Potter, Aritra Chowdhury, Purujit Bahl, Vivek Soni, Yun-Chan Tsai, Rajesh Tamada, Gaurav Kumar, Caroline Favart, V. Ratna Saripalli, Gopal Avinash
Abstract	As the complexity of state-of-the-art deep learning models increases by the month, implementation, interpretation, and traceability become ever-more-burdensome challenges for AI practitioners around the world. Several AI frameworks have risen in an effort to stem this tide, but the steady advance of the field has begun to test the bounds of their flexibility, expressiveness, and ease of use. To address these concerns, we introduce a radically flexible high-level open source deep learning framework for both research and industry. We introduce FastEstimator.
Tasks
Published	2019-10-07
URL	https://arxiv.org/abs/1910.04875v2
PDF	https://arxiv.org/pdf/1910.04875v2.pdf
PWC	https://paperswithcode.com/paper/fastestimator-a-deep-learning-library-for
Repo
Framework

Generic Primitive Detection in Point Clouds Using Novel Minimal Quadric Fits


Title	Generic Primitive Detection in Point Clouds Using Novel Minimal Quadric Fits
Authors	Tolga Birdal, Benjamin Busam, Nassir Navab, Slobodan Ilic, Peter Sturm
Abstract	We present a novel and effective method for detecting 3D primitives in cluttered, unorganized point clouds, without axillary segmentation or type specification. We consider the quadric surfaces for encapsulating the basic building blocks of our environments - planes, spheres, ellipsoids, cones or cylinders, in a unified fashion. Moreover, quadrics allow us to model higher degree of freedom shapes, such as hyperboloids or paraboloids that could be used in non-rigid settings. We begin by contributing two novel quadric fits targeting 3D point sets that are endowed with tangent space information. Based upon the idea of aligning the quadric gradients with the surface normals, our first formulation is exact and requires as low as four oriented points. The second fit approximates the first, and reduces the computational effort. We theoretically analyze these fits with rigor, and give algebraic and geometric arguments. Next, by re-parameterizing the solution, we devise a new local Hough voting scheme on the null-space coefficients that is combined with RANSAC, reducing the complexity from $O(N^4)$ to $O(N^3)$ (three points). To the best of our knowledge, this is the first method capable of performing a generic cross-type multi-object primitive detection in difficult scenes without segmentation. Our extensive qualitative and quantitative results show that our method is efficient and flexible, as well as being accurate.
Tasks
Published	2019-01-04
URL	http://arxiv.org/abs/1901.01255v1
PDF	http://arxiv.org/pdf/1901.01255v1.pdf
PWC	https://paperswithcode.com/paper/generic-primitive-detection-in-point-clouds
Repo
Framework

Brain correlates of task-load and dementia elucidation with tensor machine learning using oddball BCI paradigm


Title	Brain correlates of task-load and dementia elucidation with tensor machine learning using oddball BCI paradigm
Authors	Tomasz M. Rutkowski, Marcin Koculak, Masato S. Abe, Mihoko Otake-Matsuura
Abstract	Dementia in the elderly has recently become the most usual cause of cognitive decline. The proliferation of dementia cases in aging societies creates a remarkable economic as well as medical problems in many communities worldwide. A recently published report by The World Health Organization (WHO) estimates that about 47 million people are suffering from dementia-related neurocognitive declines worldwide. The number of dementia cases is predicted by 2050 to triple, which requires the creation of an AI-based technology application to support interventions with early screening for subsequent mental wellbeing checking as well as preservation with digital-pharma (the so-called beyond a pill) therapeutical approaches. We present an attempt and exploratory results of brain signal (EEG) classification to establish digital biomarkers for dementia stage elucidation. We discuss a comparison of various machine learning approaches for automatic event-related potentials (ERPs) classification of a high and low task-load sound stimulus recognition. These ERPs are similar to those in dementia. The proposed winning method using tensor-based machine learning in a deep fully connected neural network setting is a step forward to develop AI-based approaches for a subsequent application for subjective- and mild-cognitive impairment (SCI and MCI) diagnostics.
Tasks	EEG
Published	2019-06-19
URL	https://arxiv.org/abs/1906.07899v1
PDF	https://arxiv.org/pdf/1906.07899v1.pdf
PWC	https://paperswithcode.com/paper/brain-correlates-of-task-load-and-dementia
Repo
Framework

Dynamic Multi-path Neural Network


Title	Dynamic Multi-path Neural Network
Authors	Yingcheng Su, Shunfeng Zhou, Yichao Wu, Tian Su, Ding Liang, Jiaheng Liu, Dixin Zheng, Yingxu Wang, Junjie Yan, Xiaolin Hu
Abstract	Although deeper and larger neural networks have achieved better performance, the complex network structure and increasing computational cost cannot meet the demands of many resource-constrained applications. Existing methods usually choose to execute or skip an entire specific layer, which can only alter the depth of the network. In this paper, we propose a novel method called Dynamic Multi-path Neural Network (DMNN), which provides more path selection choices in terms of network width and depth during inference. The inference path of the network is determined by a controller, which takes into account both previous state and object category information. The proposed method can be easily incorporated into most modern network architectures. Experimental results on ImageNet and CIFAR-100 demonstrate the superiority of our method on both efficiency and overall classification accuracy. To be specific, DMNN-101 significantly outperforms ResNet-101 with an encouraging 45.1% FLOPs reduction, and DMNN-50 performs comparably to ResNet-101 while saving 42.1% parameters.
Tasks
Published	2019-02-28
URL	http://arxiv.org/abs/1902.10949v3
PDF	http://arxiv.org/pdf/1902.10949v3.pdf
PWC	https://paperswithcode.com/paper/context-aware-dynamic-block
Repo
Framework

Promotion of Answer Value Measurement with Domain Effects in Community Question Answering Systems


Title	Promotion of Answer Value Measurement with Domain Effects in Community Question Answering Systems
Authors	Binbin Jin, Enhong Chen, Hongke Zhao, Zhenya Huang, Qi Liu, Hengshu Zhu, Shui Yu
Abstract	In the area of community question answering (CQA), answer selection and answer ranking are two tasks which are applied to help users quickly access valuable answers. Existing solutions mainly exploit the syntactic or semantic correlation between a question and its related answers (Q&A), where the multi-facet domain effects in CQA are still underexplored. In this paper, we propose a unified model, Enhanced Attentive Recurrent Neural Network (EARNN), for both answer selection and answer ranking tasks by taking full advantages of both Q&A semantics and multi-facet domain effects (i.e., topic effects and timeliness). Specifically, we develop a serialized LSTM to learn the unified representations of Q&A, where two attention mechanisms at either sentence-level or word-level are designed for capturing the deep effects of topics. Meanwhile, the emphasis of Q&A can be automatically distinguished. Furthermore, we design a time-sensitive ranking function to model the timeliness in CQA. To effectively train EARNN, a question-dependent pairwise learning strategy is also developed. Finally, we conduct extensive experiments on a real-world dataset from Quora. Experimental results validate the effectiveness and interpretability of our proposed EARNN model.
Tasks	Answer Selection, Community Question Answering, Question Answering
Published	2019-06-01
URL	https://arxiv.org/abs/1906.00156v2
PDF	https://arxiv.org/pdf/1906.00156v2.pdf
PWC	https://paperswithcode.com/paper/190600156
Repo
Framework

PREMA: A Predictive Multi-task Scheduling Algorithm For Preemptible Neural Processing Units


Title	PREMA: A Predictive Multi-task Scheduling Algorithm For Preemptible Neural Processing Units
Authors	Yujeong Choi, Minsoo Rhu
Abstract	To amortize cost, cloud vendors providing DNN acceleration as a service to end-users employ consolidation and virtualization to share the underlying resources among multiple DNN service requests. This paper makes a case for a “preemptible” neural processing unit (NPU) and a “predictive” multi-task scheduler to meet the latency demands of high-priority inference while maintaining high throughput. We evaluate both the mechanisms that enable NPUs to be preemptible and the policies that utilize them to meet scheduling objectives. We show that preemptive NPU multi-tasking can achieve an average 7.8x, 1.4x, and 4.8x improvement in latency, throughput, and SLA satisfaction, respectively.
Tasks
Published	2019-09-06
URL	https://arxiv.org/abs/1909.04548v1
PDF	https://arxiv.org/pdf/1909.04548v1.pdf
PWC	https://paperswithcode.com/paper/prema-a-predictive-multi-task-scheduling
Repo
Framework

Neural Approximation of an Auto-Regressive Process through Confidence Guided Sampling


Title	Neural Approximation of an Auto-Regressive Process through Confidence Guided Sampling
Authors	YoungJoon Yoo, Sanghyuk Chun, Sangdoo Yun, Jung-Woo Ha, Jaejun Yoo
Abstract	We propose a generic confidence-based approximation that can be plugged in and simplify the auto-regressive generation process with a proved convergence. We first assume that the priors of future samples can be generated in an independently and identically distributed (i.i.d.) manner using an efficient predictor. Given the past samples and future priors, the mother AR model can post-process the priors while the accompanied confidence predictor decides whether the current sample needs a resampling or not. Thanks to the i.i.d. assumption, the post-processing can update each sample in a parallel way, which remarkably accelerates the mother model. Our experiments on different data domains including sequences and images show that the proposed method can successfully capture the complex structures of the data and generate the meaningful future samples with lower computational cost while preserving the sequential relationship of the data.
Tasks
Published	2019-10-15
URL	https://arxiv.org/abs/1910.06705v1
PDF	https://arxiv.org/pdf/1910.06705v1.pdf
PWC	https://paperswithcode.com/paper/neural-approximation-of-an-auto-regressive-1
Repo
Framework

On Learning Over-parameterized Neural Networks: A Functional Approximation Perspective


Title	On Learning Over-parameterized Neural Networks: A Functional Approximation Perspective
Authors	Lili Su, Pengkun Yang
Abstract	We consider training over-parameterized two-layer neural networks with Rectified Linear Unit (ReLU) using gradient descent (GD) method. Inspired by a recent line of work, we study the evolutions of network prediction errors across GD iterations, which can be neatly described in a matrix form. When the network is sufficiently over-parameterized, these matrices individually approximate {\em an} integral operator which is determined by the feature vector distribution $\rho$ only. Consequently, GD method can be viewed as {\em approximately} applying the powers of this integral operator on the underlying/target function $f^$ that generates the responses/labels. We show that if $f^$ admits a low-rank approximation with respect to the eigenspaces of this integral operator, then the empirical risk decreases to this low-rank approximation error at a linear rate which is determined by $f^$ and $\rho$ only, i.e., the rate is independent of the sample size $n$. Furthermore, if $f^$ has zero low-rank approximation error, then, as long as the width of the neural network is $\Omega(n\log n)$, the empirical risk decreases to $\Theta(1/\sqrt{n})$. To the best of our knowledge, this is the first result showing the sufficiency of nearly-linear network over-parameterization. We provide an application of our general results to the setting where $\rho$ is the uniform distribution on the spheres and $f^*$ is a polynomial. Throughout this paper, we consider the scenario where the input dimension $d$ is fixed.
Tasks
Published	2019-05-26
URL	https://arxiv.org/abs/1905.10826v2
PDF	https://arxiv.org/pdf/1905.10826v2.pdf
PWC	https://paperswithcode.com/paper/on-learning-over-parameterized-neural
Repo
Framework

TopoTag: A Robust and Scalable Topological Fiducial Marker System


Title	TopoTag: A Robust and Scalable Topological Fiducial Marker System
Authors	Guoxing Yu, Yongtao Hu, Jingwen Dai
Abstract	Fiducial markers have been playing an important role in augmented reality (AR), robot navigation, and general applications where the relative pose between a camera and an object is required. We introduce TopoTag, a robust and scalable topological fiducial marker system, which supports reliable and accurate pose estimation from a single image. TopoTag uses topological and geometrical information in marker detection to achieve higher robustness. Without sacrificing bits for higher recall and precision like previous systems, TopoTag can use full bits for ID encoding and supports tens of thousands unique IDs and easily extends to millions and more by adding more bits, thus achieves perfect scalability. We collect a large dataset including in total 169,713 images for evaluation, involving in-plane and out-of-plane rotation, image blur, different distances and various backgrounds, etc. Experiments show that TopoTag significantly outperforms previous fiducial marker systems in terms of various metrics, including detection accuracy, vertex jitter, pose jitter and accuracy, etc. In addition, TopoTag supports occlusion as long as main tag topological structure is maintained and flexible shape design where users can customize inter and outer marker shapes. Our dataset, marker design and detection algorithm are public to the community.
Tasks	Pose Estimation, Robot Navigation
Published	2019-08-05
URL	https://arxiv.org/abs/1908.01450v1
PDF	https://arxiv.org/pdf/1908.01450v1.pdf
PWC	https://paperswithcode.com/paper/topotag-a-robust-and-scalable-topological
Repo
Framework

Is Texture Predictive for Age and Sex in Brain MRI?


Title	Is Texture Predictive for Age and Sex in Brain MRI?
Authors	Nick Pawlowski, Ben Glocker
Abstract	Deep learning builds the foundation for many medical image analysis tasks where neuralnetworks are often designed to have a large receptive field to incorporate long spatialdependencies. Recent work has shown that large receptive fields are not always necessaryfor computer vision tasks on natural images. We explore whether this translates to certainmedical imaging tasks such as age and sex prediction from a T1-weighted brain MRI scans.
Tasks
Published	2019-07-25
URL	https://arxiv.org/abs/1907.10961v1
PDF	https://arxiv.org/pdf/1907.10961v1.pdf
PWC	https://paperswithcode.com/paper/is-texture-predictive-for-age-and-sex-in
Repo
Framework

Interpreting LSTM Prediction on Solar Flare Eruption with Time-series Clustering


Title	Interpreting LSTM Prediction on Solar Flare Eruption with Time-series Clustering
Authors	Hu Sun, Ward Manchester, Zhenbang Jiao, Xiantong Wang, Yang Chen
Abstract	We conduct a post hoc analysis of solar flare predictions made by a Long Short Term Memory (LSTM) model employing data in the form of Space-weather HMI Active Region Patches (SHARP) parameters calculated from data in proximity to the magnetic polarity inversion line where the flares originate. We train the the LSTM model for binary classification to provide a prediction score for the probability of M/X class flares to occur in next hour. We then develop a dimension-reduction technique to reduce the dimensions of SHARP parameter (LSTM inputs) and demonstrate the different patterns of SHARP parameters corresponding to the transition from low to high prediction score. Our work shows that a subset of SHARP parameters contain the key signals that strong solar flare eruptions are imminent. The dynamics of these parameters have a highly uniform trajectory for many events whose LSTM prediction scores for M/X class flares transition from very low to very high. The results demonstrate the existence of a few threshold values of SHARP parameters that when surpassed indicate a high probability of the eruption of a strong flare. Our method has distilled the knowledge of solar flare eruption learnt by deep learning model and provides a more interpretable approximation, which provides physical insight to processes driving solar flares.
Tasks	Dimensionality Reduction, Time Series, Time Series Clustering
Published	2019-12-27
URL	https://arxiv.org/abs/1912.12360v2
PDF	https://arxiv.org/pdf/1912.12360v2.pdf
PWC	https://paperswithcode.com/paper/interpreting-lstm-prediction-on-solar-flare
Repo
Framework

Micro- and Macro-Level Churn Analysis of Large-Scale Mobile Games


Title	Micro- and Macro-Level Churn Analysis of Large-Scale Mobile Games
Authors	Xi Liu, Muhe Xie, Xidao Wen, Rui Chen, Yong Ge, Nick Duffield, Na Wang
Abstract	As mobile devices become more and more popular, mobile gaming has emerged as a promising market with billion-dollar revenues. A variety of mobile game platforms and services have been developed around the world. A critical challenge for these platforms and services is to understand the churn behavior in mobile games, which usually involves churn at micro level (between an app and a specific user) and macro level (between an app and all its users). Accurate micro-level churn prediction and macro-level churn ranking will benefit many stakeholders such as game developers, advertisers, and platform operators. In this paper, we present the first large-scale churn analysis for mobile games that supports both micro-level churn prediction and macro-level churn ranking. For micro-level churn prediction, in view of the common limitations of the state-of-the-art methods built upon traditional machine learning models, we devise a novel semi-supervised and inductive embedding model that jointly learns the prediction function and the embedding function for user-app relationships. We model these two functions by deep neural networks with a unique edge embedding technique that is able to capture both contextual information and relationship dynamics. We also design a novel attributed random walk technique that takes into consideration both topological adjacency and attribute similarities. To address macro-level churn ranking, we propose to construct a relationship graph with estimated micro-level churn probabilities as edge weights and adapt link analysis algorithms on the graph. We devise a simple algorithm SimSum and adapt two more advanced algorithms PageRank and HITS. The performance of our solutions for the two-level churn analysis problems is evaluated on real-world data collected from the Samsung Game Launcher platform.
Tasks
Published	2019-01-14
URL	http://arxiv.org/abs/1901.06247v1
PDF	http://arxiv.org/pdf/1901.06247v1.pdf
PWC	https://paperswithcode.com/paper/micro-and-macro-level-churn-analysis-of-large
Repo
Framework

Learned SVD: solving inverse problems via hybrid autoencoding


Title	Learned SVD: solving inverse problems via hybrid autoencoding
Authors	Yoeri E. Boink, Christoph Brune
Abstract	Our world is full of physics-driven data where effective mappings between data manifolds are desired. There is an increasing demand for understanding combined model-driven and data-driven learning methods. We propose a nonlinear, learned singular value decomposition (L-SVD), which combines autoencoders that simultaneously learn and connect latent codes for desired signals and given measurements. Classical solution methods for inverse problems are based on regularisation techniques via SVD and variational methods. An open topic in deep learning for inverse problems is how to achieve model reduction via data dimensionality reduction to obtain a regularised inversion. We investigate this topic and provide a promising direction for solving inverse problems in cases where the underlying physics are not fully understood or have very complex behaviour. We show that the building blocks of learned inversion maps can be obtained automatically, with improved performance upon classical methods and better interpretability than black-box methods.
Tasks	Dimensionality Reduction
Published	2019-12-20
URL	https://arxiv.org/abs/1912.10840v2
PDF	https://arxiv.org/pdf/1912.10840v2.pdf
PWC	https://paperswithcode.com/paper/learned-svd-solving-inverse-problems-via
Repo
Framework

Deep learning to discover and predict dynamics on an inertial manifold


Title	Deep learning to discover and predict dynamics on an inertial manifold
Authors	Alec J. Linot, Michael D. Graham
Abstract	A data-driven framework is developed to represent chaotic dynamics on an inertial manifold (IM), and applied to solutions of the Kuramoto-Sivashinsky equation. A hybrid method combining linear and nonlinear (neural-network) dimension reduction transforms between coordinates in the full state space and on the IM. Additional neural networks predict time-evolution on the IM. The formalism accounts for translation invariance and energy conservation, and substantially outperforms linear dimension reduction, reproducing very well key dynamic and statistical features of the attractor.
Tasks	Dimensionality Reduction
Published	2019-12-20
URL	https://arxiv.org/abs/2001.04263v1
PDF	https://arxiv.org/pdf/2001.04263v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-to-discover-and-predict
Repo
Framework

Gaussian Process Latent Variable Model Factorization for Context-aware Recommender Systems


Title	Gaussian Process Latent Variable Model Factorization for Context-aware Recommender Systems
Authors	Wei Huang, Richard Yi Da Xu
Abstract	Context-aware recommender systems (CARS) have gained increasing attention due to their ability to utilize contextual information. Compared to traditional recommender systems, CARS are, in general, able to generate more accurate recommendations. Latent factors approach accounts for a large proportion of CARS. Recently, a non-linear Gaussian Process (GP) based factorization method was proven to outperform the state-of-the-art methods in CARS. Despite its effectiveness, GP model-based methods can suffer from over-fitting and may not be able to determine the impact of each context automatically. In order to address such shortcomings, we propose a Gaussian Process Latent Variable Model Factorization (GPLVMF) method, where we apply an appropriate prior to the original GP model. Our work is primarily inspired by the Gaussian Process Latent Variable Model (GPLVM), which was a non-linear dimensionality reduction method. As a result, we improve the performance on the real datasets significantly as well as capturing the importance of each context. In addition to the general advantages, our method provides two main contributions regarding recommender system settings: (1) addressing the influence of bias by setting a non-zero mean function, and (2) utilizing real-valued contexts by fixing the latent space with real values.
Tasks	Dimensionality Reduction, Recommendation Systems
Published	2019-12-19
URL	https://arxiv.org/abs/1912.09593v1
PDF	https://arxiv.org/pdf/1912.09593v1.pdf
PWC	https://paperswithcode.com/paper/gaussian-process-latent-variable-model
Repo
Framework