October 19, 2019

2755 words 13 mins read

Paper Group ANR 220

CNN-Based Automatic Urinary Particles Recognition. Did you hear that? Adversarial Examples Against Automatic Speech Recognition. Learning to Prove with Tactics. Graph Signal Sampling via Reinforcement Learning. Heuristics for vehicle routing problems: Sequence or set optimization?. Planning with Arithmetic and Geometric Attributes. Variational Auto …

CNN-Based Automatic Urinary Particles Recognition


Title	CNN-Based Automatic Urinary Particles Recognition
Authors	Rui Kang, Yixiong Liang, Chunyan Lian, Yuan Mao
Abstract	The urine sediment analysis of particles in microscopic images can assist physicians in evaluating patients with renal and urinary tract diseases. Manual urine sediment examination is labor-intensive, subjective and time-consuming, and the traditional automatic algorithms often extract the hand-crafted features for recognition. Instead of using the hand-crafted features, in this paper, we exploit CNN to learn features in an end-to-end manner to recognize the urine particles. We treat the urine particles recognition as object detection and exploit two state-of-the-art CNN-based object detection methods, Faster R-CNN and SSD, as well as their variants for urine particles recognition. We further investigate different factors involving these CNN-based object detection methods for urine particles recognition. We comprehensively evaluate these methods on a dataset consisting of 5,376 annotated images corresponding to 7 categories of urine particles, i.e., erythrocyte, leukocyte, epithelial cell, crystal, cast, mycete, epithelial nuclei, and obtain a best mAP (mean average precision) of 84.1% while taking only 72 ms per image on a NVIDIA Titan X GPU.
Tasks	Object Detection
Published	2018-03-06
URL	http://arxiv.org/abs/1803.02699v1
PDF	http://arxiv.org/pdf/1803.02699v1.pdf
PWC	https://paperswithcode.com/paper/cnn-based-automatic-urinary-particles
Repo
Framework

Did you hear that? Adversarial Examples Against Automatic Speech Recognition


Title	Did you hear that? Adversarial Examples Against Automatic Speech Recognition
Authors	Moustafa Alzantot, Bharathan Balaji, Mani Srivastava
Abstract	Speech is a common and effective way of communication between humans, and modern consumer devices such as smartphones and home hubs are equipped with deep learning based accurate automatic speech recognition to enable natural interaction between humans and machines. Recently, researchers have demonstrated powerful attacks against machine learning models that can fool them to produceincorrect results. However, nearly all previous research in adversarial attacks has focused on image recognition and object detection models. In this short paper, we present a first of its kind demonstration of adversarial attacks against speech classification model. Our algorithm performs targeted attacks with 87% success by adding small background noise without having to know the underlying model parameter and architecture. Our attack only changes the least significant bits of a subset of audio clip samples, and the noise does not change 89% the human listener’s perception of the audio clip as evaluated in our human study.
Tasks	Object Detection, Speech Recognition
Published	2018-01-02
URL	http://arxiv.org/abs/1801.00554v1
PDF	http://arxiv.org/pdf/1801.00554v1.pdf
PWC	https://paperswithcode.com/paper/did-you-hear-that-adversarial-examples
Repo
Framework

Learning to Prove with Tactics


Title	Learning to Prove with Tactics
Authors	Thibault Gauthier, Cezary Kaliszyk, Josef Urban, Ramana Kumar, Michael Norrish
Abstract	We implement a automated tactical prover TacticToe on top of the HOL4 interactive theorem prover. TacticToe learns from human proofs which mathematical technique is suitable in each proof situation. This knowledge is then used in a Monte Carlo tree search algorithm to explore promising tactic-level proof paths. On a single CPU, with a time limit of 60 seconds, TacticToe proves 66.4 percent of the 7164 theorems in HOL4’s standard library, whereas E prover with auto-schedule solves 34.5 percent. The success rate rises to 69.0 percent by combining the results of TacticToe and E prover.
Tasks
Published	2018-04-02
URL	http://arxiv.org/abs/1804.00596v1
PDF	http://arxiv.org/pdf/1804.00596v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-prove-with-tactics
Repo
Framework

Graph Signal Sampling via Reinforcement Learning


Title	Graph Signal Sampling via Reinforcement Learning
Authors	Oleksii Abramenko, Alexander Jung
Abstract	We formulate the problem of sampling and recovering clustered graph signal as a multi-armed bandit (MAB) problem. This formulation lends naturally to learning sampling strategies using the well-known gradient MAB algorithm. In particular, the sampling strategy is represented as a probability distribution over the individual arms of the MAB and optimized using gradient ascent. Some illustrative numerical experiments indicate that the sampling strategies based on the gradient MAB algorithm outperform existing sampling methods.
Tasks
Published	2018-05-15
URL	http://arxiv.org/abs/1805.05827v1
PDF	http://arxiv.org/pdf/1805.05827v1.pdf
PWC	https://paperswithcode.com/paper/graph-signal-sampling-via-reinforcement
Repo
Framework

Heuristics for vehicle routing problems: Sequence or set optimization?


Title	Heuristics for vehicle routing problems: Sequence or set optimization?
Authors	Túlio A. M. Toffolo, Thibaut Vidal, Tony Wauters
Abstract	We investigate a structural decomposition for the capacitated vehicle routing problem (CVRP) based on vehicle-to-customer “assignment” and visits “sequencing” decision variables. We show that an heuristic search focused on assignment decisions with a systematic optimal choice of sequences (using Concorde TSP solver) during each move evaluation is promising but requires a prohibitive computational effort. We therefore introduce an intermediate search space, based on the dynamic programming procedure of Balas & Simonetti, which finds a good compromise between intensification and computational efficiency. A variety of speed-up techniques are proposed for a fast exploration: neighborhood reductions, dynamic move filters, memory structures, and concatenation techniques. Finally, a tunneling strategy is designed to reshape the search space as the algorithm progresses. The combination of these techniques within a classical local search, as well as in the unified hybrid genetic search (UHGS) leads to significant improvements of solution accuracy. New best solutions are found for surprisingly small instances with as few as 256 customers. These solutions had not been attained up to now with classic neighborhoods. Overall, this research permits to better evaluate the respective impact of sequence and assignment optimization, proposes new ways of combining the optimization of these two decision sets, and opens promising research perspectives for the CVRP and its variants.
Tasks
Published	2018-03-16
URL	http://arxiv.org/abs/1803.06062v1
PDF	http://arxiv.org/pdf/1803.06062v1.pdf
PWC	https://paperswithcode.com/paper/heuristics-for-vehicle-routing-problems
Repo
Framework

Planning with Arithmetic and Geometric Attributes


Title	Planning with Arithmetic and Geometric Attributes
Authors	David Folqué, Sainbayar Sukhbaatar, Arthur Szlam, Joan Bruna
Abstract	A desirable property of an intelligent agent is its ability to understand its environment to quickly generalize to novel tasks and compose simpler tasks into more complex ones. If the environment has geometric or arithmetic structure, the agent should exploit these for faster generalization. Building on recent work that augments the environment with user-specified attributes, we show that further equipping these attributes with the appropriate geometric and arithmetic structure brings substantial gains in sample complexity.
Tasks
Published	2018-09-06
URL	http://arxiv.org/abs/1809.02031v1
PDF	http://arxiv.org/pdf/1809.02031v1.pdf
PWC	https://paperswithcode.com/paper/planning-with-arithmetic-and-geometric
Repo
Framework

Variational Autoencoders for New Physics Mining at the Large Hadron Collider


Title	Variational Autoencoders for New Physics Mining at the Large Hadron Collider
Authors	Olmo Cerri, Thong Q. Nguyen, Maurizio Pierini, Maria Spiropulu, Jean-Roch Vlimant
Abstract	Using variational autoencoders trained on known physics processes, we develop a one-sided threshold test to isolate previously unseen processes as outlier events. Since the autoencoder training does not depend on any specific new physics signature, the proposed procedure doesn’t make specific assumptions on the nature of new physics. An event selection based on this algorithm would be complementary to classic LHC searches, typically based on model-dependent hypothesis testing. Such an algorithm would deliver a list of anomalous events, that the experimental collaborations could further scrutinize and even release as a catalog, similarly to what is typically done in other scientific domains. Event topologies repeating in this dataset could inspire new-physics model building and new experimental searches. Running in the trigger system of the LHC experiments, such an application could identify anomalous events that would be otherwise lost, extending the scientific reach of the LHC.
Tasks
Published	2018-11-26
URL	https://arxiv.org/abs/1811.10276v3
PDF	https://arxiv.org/pdf/1811.10276v3.pdf
PWC	https://paperswithcode.com/paper/variational-autoencoders-for-new-physics
Repo
Framework

A Deep Learning Spatiotemporal Prediction Framework for Mobile Crowdsourced Services


Title	A Deep Learning Spatiotemporal Prediction Framework for Mobile Crowdsourced Services
Authors	Ahmed Ben Said, Abdelkarim Erradi, Azadeh Ghari Neiat, Athman Bouguettaya
Abstract	This papers presents a deep learning-based framework to predict crowdsourced service availability spatially and temporally. A novel two-stage prediction model is introduced based on historical spatio-temporal traces of mobile crowdsourced services. The prediction model first clusters mobile crowdsourced services into regions. The availability prediction of a mobile crowdsourced service at a certain location and time is then formulated as a classification problem. To determine the availability duration of predicted mobile crowdsourced services, we formulate a forecasting task of time series using the Gramian Angular Field. We validated the effectiveness of the proposed framework through multiple experiments.
Tasks	Time Series
Published	2018-09-04
URL	http://arxiv.org/abs/1809.00811v1
PDF	http://arxiv.org/pdf/1809.00811v1.pdf
PWC	https://paperswithcode.com/paper/a-deep-learning-spatiotemporal-prediction
Repo
Framework

Group Communication Analysis: A Computational Linguistics Approach for Detecting Sociocognitive Roles in Multi-Party Interactions


Title	Group Communication Analysis: A Computational Linguistics Approach for Detecting Sociocognitive Roles in Multi-Party Interactions
Authors	Nia Dowell, Tristian Nixon, Arthur Graesser
Abstract	Roles are one of the most important concepts in understanding human sociocognitive behavior. During group interactions, members take on different roles within the discussion. Roles have distinct patterns of behavioral engagement (i.e., active or passive, leading or following), contribution characteristics (i.e., providing new information or echoing given material), and social orientation (i.e., individual or group). Different combinations of these roles can produce characteristically different group outcomes, being either less or more productive towards collective goals. In online collaborative learning environments, this can lead to better or worse learning outcomes for the individual participants. In this study, we propose and validate a novel approach for detecting emergent roles from the participants’ contributions and patterns of interaction. Specifically, we developed a group communication analysis (GCA) by combining automated computational linguistic techniques with analyses of the sequential interactions of online group communication. The GCA was applied to three large collaborative interaction datasets (participant N = 2,429; group N = 3,598). Cluster analyses and linear mixed-effects modeling were used to assess the validity of the GCA approach and the influence of learner roles on student and group performance. The results indicate that participants’ patterns in linguistic coordination and cohesion are representative of the roles that individuals play in collaborative discussions. More broadly, GCA provides a framework for researchers to explore the micro intra- and interpersonal patterns associated with the participants’ roles and the sociocognitive processes related to successful collaboration.
Tasks
Published	2018-01-07
URL	http://arxiv.org/abs/1801.03563v1
PDF	http://arxiv.org/pdf/1801.03563v1.pdf
PWC	https://paperswithcode.com/paper/group-communication-analysis-a-computational
Repo
Framework

Computational Histological Staining and Destaining of Prostate Core Biopsy RGB Images with Generative Adversarial Neural Networks


Title	Computational Histological Staining and Destaining of Prostate Core Biopsy RGB Images with Generative Adversarial Neural Networks
Authors	Aman Rana, Gregory Yauney, Alarice Lowe, Pratik Shah
Abstract	Histopathology tissue samples are widely available in two states: paraffin-embedded unstained and non-paraffin-embedded stained whole slide RGB images (WSRI). Hematoxylin and eosin stain (H&E) is one of the principal stains in histology but suffers from several shortcomings related to tissue preparation, staining protocols, slowness and human error. We report two novel approaches for training machine learning models for the computational H&E staining and destaining of prostate core biopsy RGB images. The staining model uses a conditional generative adversarial network that learns hierarchical non-linear mappings between whole slide RGB image (WSRI) pairs of prostate core biopsy before and after H&E staining. The trained staining model can then generate computationally H&E-stained prostate core WSRIs using previously unseen non-stained biopsy images as input. The destaining model, by learning mappings between an H&E stained WSRI and a non-stained WSRI of the same biopsy, can computationally destain previously unseen H&E-stained images. Structural and anatomical details of prostate tissue and colors, shapes, geometries, locations of nuclei, stroma, vessels, glands and other cellular components were generated by both models with structural similarity indices of 0.68 (staining) and 0.84 (destaining). The proposed staining and destaining models can engender computational H&E staining and destaining of WSRI biopsies without additional equipment and devices.
Tasks
Published	2018-10-26
URL	http://arxiv.org/abs/1811.02642v2
PDF	http://arxiv.org/pdf/1811.02642v2.pdf
PWC	https://paperswithcode.com/paper/computational-histological-staining-and
Repo
Framework

Leveraging Elastic Demand for Forecasting


Title	Leveraging Elastic Demand for Forecasting
Authors	Houtao Deng, Ganesh Krishnan, Ji Chen, Dong Liang
Abstract	Demand variance can result in a mismatch between planned supply and actual demand. Demand shaping strategies such as pricing can be used to shift elastic demand to reduce the imbalance. In this work, we propose to consider elastic demand in the forecasting phase. We present a method to reallocate the historical elastic demand to reduce variance, thus making forecasting and supply planning more effective.
Tasks
Published	2018-09-09
URL	http://arxiv.org/abs/1809.03018v1
PDF	http://arxiv.org/pdf/1809.03018v1.pdf
PWC	https://paperswithcode.com/paper/leveraging-elastic-demand-for-forecasting
Repo
Framework

Joint Estimation and Inference for Data Integration Problems based on Multiple Multi-layered Gaussian Graphical Models


Title	Joint Estimation and Inference for Data Integration Problems based on Multiple Multi-layered Gaussian Graphical Models
Authors	Subhabrata Majumdar, George Michailidis
Abstract	The rapid development of high-throughput technologies has enabled the generation of data from biological or disease processes that span multiple layers, like genomic, proteomic or metabolomic data, and further pertain to multiple sources, like disease subtypes or experimental conditions. In this work, we propose a general statistical framework based on Gaussian graphical models for horizontal (i.e. across conditions or subtypes) and vertical (i.e. across different layers containing data on molecular compartments) integration of information in such datasets. We start with decomposing the multi-layer problem into a series of two-layer problems. For each two-layer problem, we model the outcomes at a node in the lower layer as dependent on those of other nodes in that layer, as well as all nodes in the upper layer. We use a combination of neighborhood selection and group-penalized regression to obtain sparse estimates of all model parameters. Following this, we develop a debiasing technique and asymptotic distributions of inter-layer directed edge weights that utilize already computed neighborhood selection coefficients for nodes in the upper layer. Subsequently, we establish global and simultaneous testing procedures for these edge weights. Performance of the proposed methodology is evaluated on synthetic data.
Tasks
Published	2018-03-09
URL	http://arxiv.org/abs/1803.03348v1
PDF	http://arxiv.org/pdf/1803.03348v1.pdf
PWC	https://paperswithcode.com/paper/joint-estimation-and-inference-for-data
Repo
Framework

Automatic hyperparameter selection in Autodock


Title	Automatic hyperparameter selection in Autodock
Authors	Hojjat Rakhshani, Lhassane Idoumghar, Julien Lepagnot, Mathieu Brevilliers, Edward Keedwell
Abstract	Autodock is a widely used molecular modeling tool which predicts how small molecules bind to a receptor of known 3D structure. The current version of AutoDock uses meta-heuristic algorithms in combination with local search methods for doing the conformation search. Appropriate settings of hyperparameters in these algorithms are important, particularly for novice users who often find it hard to identify the best configuration. In this work, we design a surrogate based multi-objective algorithm to help such users by automatically tuning hyperparameter settings. The proposed method iteratively uses a radial basis function model and non-dominated sorting to evaluate the sampled configurations during the search phase. Our experimental results using Autodock show that the introduced component is practical and effective.
Tasks
Published	2018-12-02
URL	http://arxiv.org/abs/1812.02618v1
PDF	http://arxiv.org/pdf/1812.02618v1.pdf
PWC	https://paperswithcode.com/paper/automatic-hyperparameter-selection-in
Repo
Framework

Deep multiscale convolutional feature learning for weakly supervised localization of chest pathologies in X-ray images


Title	Deep multiscale convolutional feature learning for weakly supervised localization of chest pathologies in X-ray images
Authors	Suman Sedai, Dwarikanath Mahapatra, Zongyuan Ge, Rajib Chakravorty, Rahil Garnavi
Abstract	Localization of chest pathologies in chest X-ray images is a challenging task because of their varying sizes and appearances. We propose a novel weakly supervised method to localize chest pathologies using class aware deep multiscale feature learning. Our method leverages intermediate feature maps from CNN layers at different stages of a deep network during the training of a classification model using image level annotations of pathologies. During the training phase, a set of \emph{layer relevance weights} are learned for each pathology class and the CNN is optimized to perform pathology classification by convex combination of feature maps from both shallow and deep layers using the learned weights. During the test phase, to localize the predicted pathology, the multiscale attention map is obtained by convex combination of class activation maps from each stage using the \emph{layer relevance weights} learned during the training phase. We have validated our method using 112000 X-ray images and compared with the state-of-the-art localization methods. We experimentally demonstrate that the proposed weakly supervised method can improve the localization performance of small pathologies such as nodule and mass while giving comparable performance for bigger pathologies e.g., Cardiomegaly
Tasks
Published	2018-08-22
URL	http://arxiv.org/abs/1808.08280v1
PDF	http://arxiv.org/pdf/1808.08280v1.pdf
PWC	https://paperswithcode.com/paper/deep-multiscale-convolutional-feature
Repo
Framework

Optimality of the final model found via Stochastic Gradient Descent


Title	Optimality of the final model found via Stochastic Gradient Descent
Authors	Andrea Schioppa
Abstract	We study convergence properties of Stochastic Gradient Descent (SGD) for convex objectives without assumptions on smoothness or strict convexity. We consider the question of establishing that with high probability the objective evaluated at the candidate minimizer returned by SGD is close to the minimal value of the objective. We compare this result concerning the final candidate minimzer (i.e. the final model parameters learned after all gradient steps) to the online learning techniques of [Zin03] that take a rolling average of the model parameters at the different steps of SGD.
Tasks
Published	2018-10-22
URL	http://arxiv.org/abs/1810.09418v1
PDF	http://arxiv.org/pdf/1810.09418v1.pdf
PWC	https://paperswithcode.com/paper/optimality-of-the-final-model-found-via
Repo
Framework