October 16, 2019

2811 words 14 mins read

Paper Group ANR 1077

Algoritmos Genéticos Aplicado ao Problema de Roteamento de Veículos. Crossbar-aware neural network pruning. Subspace Clustering through Sub-Clusters. Maize Haploid Identification via LSTM-CNN and Hyperspectral Imaging Technology. Building Function Approximators on top of Haar Scattering Networks. Reasons and Means to Model Preferences as Incomplete …

Algoritmos Genéticos Aplicado ao Problema de Roteamento de Veículos


Title	Algoritmos Genéticos Aplicado ao Problema de Roteamento de Veículos
Authors	Felipe F. Müller, Luis A. A. Meira
Abstract	Routing problems are often faced by companies who serve costumers through vehicles. Such problems have a challenging structure to optimize, despite the recent advances in combinatorial optimization. The goal of this project is to study and propose optimization algorithms to the vehicle routing problems (VRP). Focus will be on the problem variant in which the length of the route is restricted by a constant. A real problem will be tackled: optimization of postmen routes. Such problem was modeled as {multi-objective} in a roadmap with 25 vehicles and {30,000 deliveries} per day.
Tasks	Combinatorial Optimization
Published	2018-08-31
URL	http://arxiv.org/abs/1808.10866v1
PDF	http://arxiv.org/pdf/1808.10866v1.pdf
PWC	https://paperswithcode.com/paper/algoritmos-geneticos-aplicado-ao-problema-de
Repo
Framework

Crossbar-aware neural network pruning


Title	Crossbar-aware neural network pruning
Authors	Ling Liang, Lei Deng, Yueling Zeng, Xing Hu, Yu Ji, Xin Ma, Guoqi Li, Yuan Xie
Abstract	Crossbar architecture based devices have been widely adopted in neural network accelerators by taking advantage of the high efficiency on vector-matrix multiplication (VMM) operations. However, in the case of convolutional neural networks (CNNs), the efficiency is compromised dramatically due to the large amounts of data reuse. Although some mapping methods have been designed to achieve a balance between the execution throughput and resource overhead, the resource consumption cost is still huge while maintaining the throughput. Network pruning is a promising and widely studied leverage to shrink the model size. Whereas, previous work didn`t consider the crossbar architecture and the corresponding mapping method, which cannot be directly utilized by crossbar-based neural network accelerators. Tightly combining the crossbar structure and its mapping, this paper proposes a crossbar-aware pruning framework based on a formulated L0-norm constrained optimization problem. Specifically, we design an L0-norm constrained gradient descent (LGD) with relaxant probabilistic projection (RPP) to solve this problem. Two grains of sparsity are successfully achieved: i) intuitive crossbar-grain sparsity and ii) column-grain sparsity with output recombination, based on which we further propose an input feature maps (FMs) reorder method to improve the model accuracy. We evaluate our crossbar-aware pruning framework on median-scale CIFAR10 dataset and large-scale ImageNet dataset with VGG and ResNet models. Our method is able to reduce the crossbar overhead by 44%-72% with little accuracy degradation. This work greatly saves the resource and the related energy cost, which provides a new co-design solution for mapping CNNs onto various crossbar devices with significantly higher efficiency. \|
Tasks	Network Pruning
Published	2018-07-25
URL	http://arxiv.org/abs/1807.10816v3
PDF	http://arxiv.org/pdf/1807.10816v3.pdf
PWC	https://paperswithcode.com/paper/crossbar-aware-neural-network-pruning
Repo
Framework

Subspace Clustering through Sub-Clusters


Title	Subspace Clustering through Sub-Clusters
Authors	Weiwei Li, Jan Hannig, Sayan Mukherjee
Abstract	The problem of dimension reduction is of increasing importance in modern data analysis. In this paper, we consider modeling the collection of points in a high dimensional space as a union of low dimensional subspaces. In particular we propose a highly scalable sampling based algorithm that clusters the entire data via first spectral clustering of a small random sample followed by classifying or labeling the remaining out of sample points. The key idea is that this random subset borrows information across the entire data set and that the problem of clustering points can be replaced with the more efficient and robust problem of “clustering sub-clusters”. We provide theoretical guarantees for our procedure. The numerical results indicate we outperform other state-of-the-art subspace clustering algorithms with respect to accuracy and speed.
Tasks	Dimensionality Reduction
Published	2018-11-15
URL	http://arxiv.org/abs/1811.06580v1
PDF	http://arxiv.org/pdf/1811.06580v1.pdf
PWC	https://paperswithcode.com/paper/subspace-clustering-through-sub-clusters
Repo
Framework

Maize Haploid Identification via LSTM-CNN and Hyperspectral Imaging Technology


Title	Maize Haploid Identification via LSTM-CNN and Hyperspectral Imaging Technology
Authors	Xuan-Yu Wang, Wen-Xuan Liao, Dong An, Yao-Guang Wei
Abstract	Accurate and fast identification of seed cultivars is crucial to plant breeding, with accelerating breeding of new products and increasing its quality. In our study, the first attempt to design a high-accurate identification model of maize haploid seeds from diploid ones based on optimum waveband selection of the LSTM-CNN algorithm is realized via deep learning and hyperspectral imaging technology, with accuracy reaching 97% in the determining optimum waveband of 1367.6-1526.4nm. The verification of testing another cultivar achieved an accuracy of 93% in the same waveband. The model collected images of 256 wavebands of seeds in the spectral region of 862.9-1704.2nm. The high-noise waveband intervals were found and deleted by the LSTM. The optimum-data waveband intervals were determined by CNN’s waveband-based detection. The optimum sample set for network training only accounted for 1/5 of total sample data. The accuracy was significantly higher than the full-waveband modeling or modeling of any other wavebands. Our study demonstrates that the proposed model has outstanding effect on maize haploid identification and it could be generalized to some extent.
Tasks
Published	2018-05-23
URL	http://arxiv.org/abs/1805.09105v2
PDF	http://arxiv.org/pdf/1805.09105v2.pdf
PWC	https://paperswithcode.com/paper/maize-haploid-identification-via-lstm-cnn-and
Repo
Framework

Building Function Approximators on top of Haar Scattering Networks


Title	Building Function Approximators on top of Haar Scattering Networks
Authors	Fernando Fernandes Neto
Abstract	In this article we propose building general-purpose function approximators on top of Haar Scattering Networks. We advocate that this architecture enables a better comprehension of feature extraction, in addition to its implementation simplicity and low computational costs. We show its approximation and feature extraction capabilities in a wide range of different problems, which can be applied on several phenomena in signal processing, system identification, econometrics and other potential fields.
Tasks
Published	2018-04-09
URL	http://arxiv.org/abs/1804.03236v1
PDF	http://arxiv.org/pdf/1804.03236v1.pdf
PWC	https://paperswithcode.com/paper/building-function-approximators-on-top-of
Repo
Framework

Reasons and Means to Model Preferences as Incomplete


Title	Reasons and Means to Model Preferences as Incomplete
Authors	Olivier Cailloux, Sébastien Destercke
Abstract	Literature involving preferences of artificial agents or human beings often assume their preferences can be represented using a complete transitive binary relation. Much has been written however on different models of preferences. We review some of the reasons that have been put forward to justify more complex modeling, and review some of the techniques that have been proposed to obtain models of such preferences.
Tasks
Published	2018-01-05
URL	http://arxiv.org/abs/1801.01657v1
PDF	http://arxiv.org/pdf/1801.01657v1.pdf
PWC	https://paperswithcode.com/paper/reasons-and-means-to-model-preferences-as
Repo
Framework

Disease Detection in Weakly Annotated Volumetric Medical Images using a Convolutional LSTM Network


Title	Disease Detection in Weakly Annotated Volumetric Medical Images using a Convolutional LSTM Network
Authors	Nathaniel Braman, David Beymer, Ehsan Dehghan
Abstract	We explore a solution for learning disease signatures from weakly, yet easily obtainable, annotated volumetric medical imaging data by analyzing 3D volumes as a sequence of 2D images. We demonstrate the performance of our solution in the detection of emphysema in lung cancer screening low-dose CT images. Our approach utilizes convolutional long short-term memory (LSTM) to “scan” sequentially through an imaging volume for the presence of disease in a portion of scanned region. This framework allowed effective learning given only volumetric images and binary disease labels, thus enabling training from a large dataset of 6,631 un-annotated image volumes from 4,486 patients. When evaluated in a testing set of 2,163 volumes from 2,163 patients, our model distinguished emphysema with area under the receiver operating characteristic curve (AUC) of .83. This approach was found to outperform 2D convolutional neural networks (CNN) implemented with various multiple-instance learning schemes (AUC=0.69-0.76) and a 3D CNN (AUC=.77).
Tasks	Multiple Instance Learning
Published	2018-12-03
URL	http://arxiv.org/abs/1812.01087v1
PDF	http://arxiv.org/pdf/1812.01087v1.pdf
PWC	https://paperswithcode.com/paper/disease-detection-in-weakly-annotated
Repo
Framework

Training on the test set? An analysis of Spampinato et al. [arXiv:1609.00344]


Title	Training on the test set? An analysis of Spampinato et al. [arXiv:1609.00344]
Authors	Ren Li, Jared S. Johansen, Hamad Ahmed, Thomas V. Ilyevsky, Ronnie B Wilbur, Hari M Bharadwaj, Jeffrey Mark Siskind
Abstract	A recent paper [arXiv:1609.00344] claims to classify brain processing evoked in subjects watching ImageNet stimuli as measured with EEG and to use a representation derived from this processing to create a novel object classifier. That paper, together with a series of subsequent papers [8, 15, 17, 20, 21, 30, 35], claims to revolutionize the field by achieving extremely successful results on several computer-vision tasks, including object classification, transfer learning, and generation of images depicting human perception and thought using brain-derived representations measured through EEG. Our novel experiments and analyses demonstrate that their results crucially depend on the block design that they use, where all stimuli of a given class are presented together, and fail with a rapid-event design, where stimuli of different classes are randomly intermixed. The block design leads to classification of arbitrary brain states based on block-level temporal correlations that tend to exist in all EEG data, rather than stimulus-related activity. Because every trial in their test sets comes from the same block as many trials in the corresponding training sets, their block design thus leads to surreptitiously training on the test set. This invalidates all subsequent analyses performed on this data in multiple published papers and calls into question all of the purported results. We further show that a novel object classifier constructed with a random codebook performs as well as or better than a novel object classifier constructed with the representation extracted from EEG data, suggesting that the performance of their classifier constructed with a representation extracted from EEG data does not benefit at all from the brain-derived representation. Our results calibrate the underlying difficulty of the tasks involved and caution against sensational and overly optimistic, but false, claims to the contrary.
Tasks	EEG, Object Classification, Transfer Learning
Published	2018-12-18
URL	http://arxiv.org/abs/1812.07697v1
PDF	http://arxiv.org/pdf/1812.07697v1.pdf
PWC	https://paperswithcode.com/paper/training-on-the-test-set-an-analysis-of
Repo
Framework

A Recursive PLS (Partial Least Squares) based Approach for Enterprise Threat Management


Title	A Recursive PLS (Partial Least Squares) based Approach for Enterprise Threat Management
Authors	Janardan Misra
Abstract	Most of the existing solutions to enterprise threat management are preventive approaches prescribing means to prevent policy violations with varying degrees of success. In this paper we consider the complementary scenario where a number of security violations have already occurred, or security threats, or vulnerabilities have been reported and a security administrator needs to generate optimal response to these security events. We present a principled approach to study and model the human expertise in responding to the emergent threats owing to these security events. A recursive Partial Least Squares based adaptive learning model is defined using a factorial analysis of the security events together with a method for estimating the effect of global context dependent semantic information used by the security administrators. Presented model is theoretically optimal and operationally recursive in nature to deal with the set of security events being generated continuously. We discuss the underlying challenges and ways in which the model could be operationalized in centralized versus decentralized, and real-time versus batch processing modes.
Tasks
Published	2018-06-23
URL	http://arxiv.org/abs/1806.08941v1
PDF	http://arxiv.org/pdf/1806.08941v1.pdf
PWC	https://paperswithcode.com/paper/a-recursive-pls-partial-least-squares-based
Repo
Framework

Explanatory Graphs for CNNs


Title	Explanatory Graphs for CNNs
Authors	Quanshi Zhang, Xin Wang, Ruiming Cao, Ying Nian Wu, Feng Shi, Song-Chun Zhu
Abstract	This paper introduces a graphical model, namely an explanatory graph, which reveals the knowledge hierarchy hidden inside conv-layers of a pre-trained CNN. Each filter in a conv-layer of a CNN for object classification usually represents a mixture of object parts. We develop a simple yet effective method to disentangle object-part pattern components from each filter. We construct an explanatory graph to organize the mined part patterns, where a node represents a part pattern, and each edge encodes co-activation relationships and spatial relationships between patterns. More crucially, given a pre-trained CNN, the explanatory graph is learned without a need of annotating object parts. Experiments show that each graph node consistently represented the same object part through different images, which boosted the transferability of CNN features. We transferred part patterns in the explanatory graph to the task of part localization, and our method significantly outperformed other approaches.
Tasks	Object Classification
Published	2018-12-18
URL	http://arxiv.org/abs/1812.07997v1
PDF	http://arxiv.org/pdf/1812.07997v1.pdf
PWC	https://paperswithcode.com/paper/explanatory-graphs-for-cnns
Repo
Framework

Attack and defence in cellular decision-making: lessons from machine learning


Title	Attack and defence in cellular decision-making: lessons from machine learning
Authors	Thomas J. Rademaker, Emmanuel Bengio, Paul François
Abstract	Machine learning algorithms can be fooled by small well-designed adversarial perturbations. This is reminiscent of cellular decision-making where ligands (called antagonists) prevent correct signalling, like in early immune recognition. We draw a formal analogy between neural networks used in machine learning and models of cellular decision-making (adaptive proofreading). We apply attacks from machine learning to simple decision-making models, and show explicitly the correspondence to antagonism by weakly bound ligands. Such antagonism is absent in more nonlinear models, which inspired us to implement a biomimetic defence in neural networks filtering out adversarial perturbations. We then apply a gradient-descent approach from machine learning to different cellular decision-making models, and we reveal the existence of two regimes characterized by the presence or absence of a critical point for the gradient. This critical point causes the strongest antagonists to lie close to the decision boundary. This is validated in the loss landscapes of robust neural networks and cellular decision-making models, and observed experimentally for immune cells. For both regimes, we explain how associated defence mechanisms shape the geometry of the loss landscape, and why different adversarial attacks are effective in different regimes. Our work connects evolved cellular decision-making to machine learning, and motivates the design of a general theory of adversarial perturbations, both for in vivo and in silico systems.
Tasks	Decision Making
Published	2018-07-10
URL	https://arxiv.org/abs/1807.04270v3
PDF	https://arxiv.org/pdf/1807.04270v3.pdf
PWC	https://paperswithcode.com/paper/attack-and-defence-in-cellular-decision
Repo
Framework

Interactive Hand Pose Estimation: Boosting accuracy in localizing extended finger joints


Title	Interactive Hand Pose Estimation: Boosting accuracy in localizing extended finger joints
Authors	Cairong Zhang, Guijin Wang, Hengkai Guo, Xinghao Chen, Fei Qiao, Huazhong Yang
Abstract	Accurate 3D hand pose estimation plays an important role in Human Machine Interaction (HMI). In the reality of HMI, joints in fingers stretching out, especially corresponding fingertips, are much more important than other joints. We propose a novel method to refine stretching-out finger joint locations after obtaining rough hand pose estimation. It first detects which fingers are stretching out, then neighbor pixels of certain joint vote for its new location based on random forests. The algorithm is tested on two public datasets: MSRA15 and ICVL. After the refinement stage of stretching-out fingers, errors of predicted HMI finger joint locations are significantly reduced. Mean error of all fingertips reduces around 5mm (relatively more than 20%). Stretching-out fingertip locations are even more precise, which in MSRA15 reduces 10.51mm (relatively 41.4%).
Tasks	Hand Pose Estimation, Pose Estimation
Published	2018-04-02
URL	http://arxiv.org/abs/1804.00651v2
PDF	http://arxiv.org/pdf/1804.00651v2.pdf
PWC	https://paperswithcode.com/paper/interactive-hand-pose-estimation-boosting
Repo
Framework

Online Linear Quadratic Control


Title	Online Linear Quadratic Control
Authors	Alon Cohen, Avinatan Hassidim, Tomer Koren, Nevena Lazic, Yishay Mansour, Kunal Talwar
Abstract	We study the problem of controlling linear time-invariant systems with known noisy dynamics and adversarially chosen quadratic losses. We present the first efficient online learning algorithms in this setting that guarantee $O(\sqrt{T})$ regret under mild assumptions, where $T$ is the time horizon. Our algorithms rely on a novel SDP relaxation for the steady-state distribution of the system. Crucially, and in contrast to previously proposed relaxations, the feasible solutions of our SDP all correspond to “strongly stable” policies that mix exponentially fast to a steady state.
Tasks
Published	2018-06-19
URL	http://arxiv.org/abs/1806.07104v1
PDF	http://arxiv.org/pdf/1806.07104v1.pdf
PWC	https://paperswithcode.com/paper/online-linear-quadratic-control
Repo
Framework

RecipeQA: A Challenge Dataset for Multimodal Comprehension of Cooking Recipes


Title	RecipeQA: A Challenge Dataset for Multimodal Comprehension of Cooking Recipes
Authors	Semih Yagcioglu, Aykut Erdem, Erkut Erdem, Nazli Ikizler-Cinbis
Abstract	Understanding and reasoning about cooking recipes is a fruitful research direction towards enabling machines to interpret procedural text. In this work, we introduce RecipeQA, a dataset for multimodal comprehension of cooking recipes. It comprises of approximately 20K instructional recipes with multiple modalities such as titles, descriptions and aligned set of images. With over 36K automatically generated question-answer pairs, we design a set of comprehension and reasoning tasks that require joint understanding of images and text, capturing the temporal flow of events and making sense of procedural knowledge. Our preliminary results indicate that RecipeQA will serve as a challenging test bed and an ideal benchmark for evaluating machine comprehension systems. The data and leaderboard are available at http://hucvl.github.io/recipeqa.
Tasks	Reading Comprehension
Published	2018-09-04
URL	http://arxiv.org/abs/1809.00812v1
PDF	http://arxiv.org/pdf/1809.00812v1.pdf
PWC	https://paperswithcode.com/paper/recipeqa-a-challenge-dataset-for-multimodal
Repo
Framework

Rethinking Radiology: An Analysis of Different Approaches to BraTS


Title	Rethinking Radiology: An Analysis of Different Approaches to BraTS
Authors	William Bakst, Linus Meyer-Teruel, Jasdeep Singh
Abstract	This paper discusses the deep learning architectures currently used for pixel-wise segmentation of primary and secondary glioblastomas and low-grade gliomas. We implement various models such as the popular UNet architecture and compare the performance of these implementations on the BRATS dataset. This paper will explore the different approaches and combinations, offering an in depth discussion of how they perform and how we may improve upon them using more recent advancements in deep learning architectures.
Tasks
Published	2018-06-06
URL	http://arxiv.org/abs/1806.03981v1
PDF	http://arxiv.org/pdf/1806.03981v1.pdf
PWC	https://paperswithcode.com/paper/rethinking-radiology-an-analysis-of-different
Repo
Framework