October 18, 2019

3200 words 16 mins read

Paper Group ANR 455

How would surround vehicles move? A Unified Framework for Maneuver Classification and Motion Prediction. Implicit regularization and solution uniqueness in over-parameterized matrix sensing. Action Machine: Rethinking Action Recognition in Trimmed Videos. ComQA: A Community-sourced Dataset for Complex Factoid Question Answering with Paraphrase Clus …

How would surround vehicles move? A Unified Framework for Maneuver Classification and Motion Prediction


Title	How would surround vehicles move? A Unified Framework for Maneuver Classification and Motion Prediction
Authors	Nachiket Deo, Akshay Rangesh, Mohan M. Trivedi
Abstract	Reliable prediction of surround vehicle motion is a critical requirement for path planning for autonomous vehicles. In this paper we propose a unified framework for surround vehicle maneuver classification and motion prediction that exploits multiple cues, namely, the estimated motion of vehicles, an understanding of typical motion patterns of freeway traffic and inter-vehicle interaction. We report our results in terms of maneuver classification accuracy and mean and median absolute error of predicted trajectories against the ground truth for real traffic data collected using vehicle mounted sensors on freeways. An ablative analysis is performed to analyze the relative importance of each cue for trajectory prediction. Additionally, an analysis of execution time for the components of the framework is presented. Finally, we present multiple case studies analyzing the outputs of our model for complex traffic scenarios
Tasks	Autonomous Vehicles, motion prediction, Trajectory Prediction
Published	2018-01-19
URL	http://arxiv.org/abs/1801.06523v1
PDF	http://arxiv.org/pdf/1801.06523v1.pdf
PWC	https://paperswithcode.com/paper/how-would-surround-vehicles-move-a-unified
Repo
Framework

Implicit regularization and solution uniqueness in over-parameterized matrix sensing


Title	Implicit regularization and solution uniqueness in over-parameterized matrix sensing
Authors	Kelly Geyer, Anastasios Kyrillidis, Amir Kalev
Abstract	We consider whether algorithmic choices in over-parameterized linear matrix factorization introduce implicit regularization. We focus on noiseless matrix sensing over rank-$r$ positive semi-definite (PSD) matrices in $\mathbb{R}^{n \times n}$, with a sensing mechanism that satisfies restricted isometry properties (RIP). The algorithm we study is \emph{factored gradient descent}, where we model the low-rankness and PSD constraints with the factorization $UU^\top$, for $U \in \mathbb{R}^{n \times r}$. Surprisingly, recent work argues that the choice of $r \leq n$ is not pivotal: even setting $U \in \mathbb{R}^{n \times n}$ is sufficient for factored gradient descent to find the rank-$r$ solution, which suggests that operating over the factors leads to an implicit regularization. In this contribution, we provide a different perspective to the problem of implicit regularization. We show that under certain conditions, the PSD constraint by itself is sufficient to lead to a unique rank-$r$ matrix recovery, without implicit or explicit low-rank regularization. \emph{I.e.}, under assumptions, the set of PSD matrices, that are consistent with the observed data, is a singleton, regardless of the algorithm used.
Tasks
Published	2018-06-06
URL	https://arxiv.org/abs/1806.02046v2
PDF	https://arxiv.org/pdf/1806.02046v2.pdf
PWC	https://paperswithcode.com/paper/implicit-regularization-and-solution
Repo
Framework

Action Machine: Rethinking Action Recognition in Trimmed Videos


Title	Action Machine: Rethinking Action Recognition in Trimmed Videos
Authors	Jiagang Zhu, Wei Zou, Liang Xu, Yiming Hu, Zheng Zhu, Manyu Chang, Junjie Huang, Guan Huang, Dalong Du
Abstract	Existing methods in video action recognition mostly do not distinguish human body from the environment and easily overfit the scenes and objects. In this work, we present a conceptually simple, general and high-performance framework for action recognition in trimmed videos, aiming at person-centric modeling. The method, called Action Machine, takes as inputs the videos cropped by person bounding boxes. It extends the Inflated 3D ConvNet (I3D) by adding a branch for human pose estimation and a 2D CNN for pose-based action recognition, being fast to train and test. Action Machine can benefit from the multi-task training of action recognition and pose estimation, the fusion of predictions from RGB images and poses. On NTU RGB-D, Action Machine achieves the state-of-the-art performance with top-1 accuracies of 97.2% and 94.3% on cross-view and cross-subject respectively. Action Machine also achieves competitive performance on another three smaller action recognition datasets: Northwestern UCLA Multiview Action3D, MSR Daily Activity3D and UTD-MHAD. Code will be made available.
Tasks	Action Recognition In Videos, Multimodal Activity Recognition, Pose Estimation, Skeleton Based Action Recognition, Temporal Action Localization
Published	2018-12-14
URL	http://arxiv.org/abs/1812.05770v2
PDF	http://arxiv.org/pdf/1812.05770v2.pdf
PWC	https://paperswithcode.com/paper/action-machine-rethinking-action-recognition
Repo
Framework

ComQA: A Community-sourced Dataset for Complex Factoid Question Answering with Paraphrase Clusters


Title	ComQA: A Community-sourced Dataset for Complex Factoid Question Answering with Paraphrase Clusters
Authors	Abdalghani Abujabal, Rishiraj Saha Roy, Mohamed Yahya, Gerhard Weikum
Abstract	To bridge the gap between the capabilities of the state-of-the-art in factoid question answering (QA) and what users ask, we need large datasets of real user questions that capture the various question phenomena users are interested in, and the diverse ways in which these questions are formulated. We introduce ComQA, a large dataset of real user questions that exhibit different challenging aspects such as compositionality, temporal reasoning, and comparisons. ComQA questions come from the WikiAnswers community QA platform, which typically contains questions that are not satisfactorily answerable by existing search engine technology. Through a large crowdsourcing effort, we clean the question dataset, group questions into paraphrase clusters, and annotate clusters with their answers. ComQA contains 11,214 questions grouped into 4,834 paraphrase clusters. We detail the process of constructing ComQA, including the measures taken to ensure its high quality while making effective use of crowdsourcing. We also present an extensive analysis of the dataset and the results achieved by state-of-the-art systems on ComQA, demonstrating that our dataset can be a driver of future research on QA.
Tasks	Question Answering
Published	2018-09-25
URL	http://arxiv.org/abs/1809.09528v2
PDF	http://arxiv.org/pdf/1809.09528v2.pdf
PWC	https://paperswithcode.com/paper/comqa-a-community-sourced-dataset-for-complex
Repo
Framework

Lattice based Conceptual Spaces to Explore Cognitive Functionalities for Prosthetic Arm


Title	Lattice based Conceptual Spaces to Explore Cognitive Functionalities for Prosthetic Arm
Authors	M S Ishwarya, Aswani Kumar Cherukuri
Abstract	Upper limb Prosthetic can be viewed as an independent cognitive system in order to develop a conceptual space. In this paper, we provide a detailed analogical reasoning of prosthetic arm to build the conceptual spaces with the help of the theory called geometric framework of conceptual spaces proposed by Gardenfors. Terminologies of conceptual spaces such as concepts, similarities, properties, quality dimensions and prototype are applied for a specific prosthetic system and conceptual space is built for prosthetic arm. Concept lattice traversals are used on the lattice represented conceptual spaces. Cognitive functionalities such as generalization (Similarities) and specialization (Differences) are achieved in the lattice represented conceptual space. This might well prove to design intelligent prosthetics to assist challenged humans. Geometric framework of conceptual spaces holds similar concepts closer in geometric structures in a way similar to concept lattices. Hence, we also propose to use concept lattice to represent concepts of geometric framework of conceptual spaces. Also, we extend our discussion with our insights on conceptual spaces of bidirectional hand prosthetics.
Tasks
Published	2018-07-05
URL	http://arxiv.org/abs/1807.01953v1
PDF	http://arxiv.org/pdf/1807.01953v1.pdf
PWC	https://paperswithcode.com/paper/lattice-based-conceptual-spaces-to-explore
Repo
Framework

Combinatorial Attacks on Binarized Neural Networks


Title	Combinatorial Attacks on Binarized Neural Networks
Authors	Elias B. Khalil, Amrita Gupta, Bistra Dilkina
Abstract	Binarized Neural Networks (BNNs) have recently attracted significant interest due to their computational efficiency. Concurrently, it has been shown that neural networks may be overly sensitive to “attacks” - tiny adversarial changes in the input - which may be detrimental to their use in safety-critical domains. Designing attack algorithms that effectively fool trained models is a key step towards learning robust neural networks. The discrete, non-differentiable nature of BNNs, which distinguishes them from their full-precision counterparts, poses a challenge to gradient-based attacks. In this work, we study the problem of attacking a BNN through the lens of combinatorial and integer optimization. We propose a Mixed Integer Linear Programming (MILP) formulation of the problem. While exact and flexible, the MILP quickly becomes intractable as the network and perturbation space grow. To address this issue, we propose IProp, a decomposition-based algorithm that solves a sequence of much smaller MILP problems. Experimentally, we evaluate both proposed methods against the standard gradient-based attack (FGSM) on MNIST and Fashion-MNIST, and show that IProp performs favorably compared to FGSM, while scaling beyond the limits of the MILP.
Tasks
Published	2018-10-08
URL	http://arxiv.org/abs/1810.03538v1
PDF	http://arxiv.org/pdf/1810.03538v1.pdf
PWC	https://paperswithcode.com/paper/combinatorial-attacks-on-binarized-neural
Repo
Framework

The Resistance to Label Noise in K-NN and CNN Depends on its Concentration


Title	The Resistance to Label Noise in K-NN and CNN Depends on its Concentration
Authors	Amnon Drory, Oria Ratzon, Shai Avidan, Raja Giryes
Abstract	We investigate the multi-class classification performance of K-Nearest Neighbors (K-NN) and Convolutional Neural Networks (CNNs) in the presence of label noise. We first show empirically that a CNN’s prediction for a given test sample depends on the labels of the training samples in its local neighborhood. This motivates us to derive a realizable analytic expression that approximates the multi-class K-NN classification error in the presence of label noise, which is of independent importance. We then suggest that the expression for K-NN may serve as a first-order approximation for the CNN error. Finally, we demonstrate empirically the proximity of the developed expression to the observed performance of K-NN and CNN classifiers. Our results may explain the already observed surprising resistance of CNNs to some types of label noise. In particular, it charcterizes an important factor in this resistance, by showing that the more concentrated the noise is (in the data), the greater the degration in performance.
Tasks
Published	2018-03-30
URL	https://arxiv.org/abs/1803.11410v2
PDF	https://arxiv.org/pdf/1803.11410v2.pdf
PWC	https://paperswithcode.com/paper/on-the-resistance-of-neural-nets-to-label
Repo
Framework

Automatic Summarization of Natural Language


Title	Automatic Summarization of Natural Language
Authors	Marc Everett Johnson
Abstract	Automatic summarization of natural language is a current topic in computer science research and industry, studied for decades because of its usefulness across multiple domains. For example, summarization is necessary to create reviews such as this one. Research and applications have achieved some success in extractive summarization (where key sentences are curated), however, abstractive summarization (synthesis and re-stating) is a hard problem and generally unsolved in computer science. This literature review contrasts historical progress up through current state of the art, comparing dimensions such as: extractive vs. abstractive, supervised vs. unsupervised, NLP (Natural Language Processing) vs Knowledge-based, deep learning vs algorithms, structured vs. unstructured sources, and measurement metrics such as Rouge and BLEU. Multiple dimensions are contrasted since current research uses combinations of approaches as seen in the review matrix. Throughout this summary, synthesis and critique is provided. This review concludes with insights for improved abstractive summarization measurement, with surprising implications for detecting understanding and comprehension in general.
Tasks	Abstractive Text Summarization
Published	2018-12-18
URL	http://arxiv.org/abs/1812.10549v1
PDF	http://arxiv.org/pdf/1812.10549v1.pdf
PWC	https://paperswithcode.com/paper/automatic-summarization-of-natural-language
Repo
Framework

A Family of Maximum Margin Criterion for Adaptive Learning


Title	A Family of Maximum Margin Criterion for Adaptive Learning
Authors	Miao Cheng, Zunren Liu, Hongwei Zou, Ah Chung Tsoi
Abstract	In recent years, pattern analysis plays an important role in data mining and recognition, and many variants have been proposed to handle complicated scenarios. In the literature, it has been quite familiar with high dimensionality of data samples, but either such characteristics or large data have become usual sense in real-world applications. In this work, an improved maximum margin criterion (MMC) method is introduced firstly. With the new definition of MMC, several variants of MMC, including random MMC, layered MMC, 2D^2 MMC, are designed to make adaptive learning applicable. Particularly, the MMC network is developed to learn deep features of images in light of simple deep networks. Experimental results on a diversity of data sets demonstrate the discriminant ability of proposed MMC methods are compenent to be adopted in complicated application scenarios.
Tasks
Published	2018-10-09
URL	http://arxiv.org/abs/1810.04064v2
PDF	http://arxiv.org/pdf/1810.04064v2.pdf
PWC	https://paperswithcode.com/paper/a-family-of-maximum-margin-criterion-for
Repo
Framework

Understanding Convolutional Networks with APPLE : Automatic Patch Pattern Labeling for Explanation


Title	Understanding Convolutional Networks with APPLE : Automatic Patch Pattern Labeling for Explanation
Authors	Sandeep Konam, Ian Quah, Stephanie Rosenthal, Manuela Veloso
Abstract	With the success of deep learning, recent efforts have been focused on analyzing how learned networks make their classifications. We are interested in analyzing the network output based on the network structure and information flow through the network layers. We contribute an algorithm for 1) analyzing a deep network to find neurons that are ‘important’ in terms of the network classification outcome, and 2)automatically labeling the patches of the input image that activate these important neurons. We propose several measures of importance for neurons and demonstrate that our technique can be used to gain insight into, and explain how a network decomposes an image to make its final classification.
Tasks
Published	2018-02-11
URL	http://arxiv.org/abs/1802.03675v1
PDF	http://arxiv.org/pdf/1802.03675v1.pdf
PWC	https://paperswithcode.com/paper/understanding-convolutional-networks-with
Repo
Framework

Intensive Preprocessing of KDD Cup 99 for Network Intrusion Classification Using Machine Learning Techniques


Title	Intensive Preprocessing of KDD Cup 99 for Network Intrusion Classification Using Machine Learning Techniques
Authors	Ibrahim Obeidat, Nabhan Hamadneh, Mouhammd Al-kasassbeh, Mohammad Almseidin
Abstract	Network security engineers work to keep services available all the time by handling intruder attacks. Intrusion Detection System (IDS) is one of the obtainable mechanism that used to sense and classify any abnormal actions. Therefore, the IDS must be always up to date with the latest intruder attacks signatures to preserve confidentiality, integrity and availability of the services. The speed of the IDS is very important issue as well learning the new attacks. This research work illustrates how the Knowledge Discovery and Data Mining (or Knowledge Discovery in Databases) KDD dataset is very handy for testing and evaluating different Machine Learning Techniques. It mainly focuses on the KDD preprocess part in order to prepare a decent and fair experimental data set. The techniques J48, Random Forest, Random Tree, MLP, Na"ive Bayes and Bayes Network classifiers have been chosen for this study. It has been proven that the Random forest classifier has achieved the highest accuracy rate for detecting and classifying all KDD dataset attacks, which are of type (DOS, R2L, U2R, and PROBE)
Tasks	Intrusion Detection
Published	2018-05-26
URL	http://arxiv.org/abs/1805.10458v2
PDF	http://arxiv.org/pdf/1805.10458v2.pdf
PWC	https://paperswithcode.com/paper/intensive-preprocessing-of-kdd-cup-99-for
Repo
Framework

Impossibility and Uncertainty Theorems in AI Value Alignment (or why your AGI should not have a utility function)


Title	Impossibility and Uncertainty Theorems in AI Value Alignment (or why your AGI should not have a utility function)
Authors	Peter Eckersley
Abstract	Utility functions or their equivalents (value functions, objective functions, loss functions, reward functions, preference orderings) are a central tool in most current machine learning systems. These mechanisms for defining goals and guiding optimization run into practical and conceptual difficulty when there are independent, multi-dimensional objectives that need to be pursued simultaneously and cannot be reduced to each other. Ethicists have proved several impossibility theorems that stem from this origin; those results appear to show that there is no way of formally specifying what it means for an outcome to be good for a population without violating strong human ethical intuitions (in such cases, the objective function is a social welfare function). We argue that this is a practical problem for any machine learning system (such as medical decision support systems or autonomous weapons) or rigidly rule-based bureaucracy that will make high stakes decisions about human lives: such systems should not use objective functions in the strict mathematical sense. We explore the alternative of using uncertain objectives, represented for instance as partially ordered preferences, or as probability distributions over total orders. We show that previously known impossibility theorems can be transformed into uncertainty theorems in both of those settings, and prove lower bounds on how much uncertainty is implied by the impossibility results. We close by proposing two conjectures about the relationship between uncertainty in objectives and severe unintended consequences from AI systems.
Tasks
Published	2018-12-31
URL	http://arxiv.org/abs/1901.00064v3
PDF	http://arxiv.org/pdf/1901.00064v3.pdf
PWC	https://paperswithcode.com/paper/impossibility-and-uncertainty-theorems-in-ai
Repo
Framework

Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning


Title	Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning
Authors	Max Ferguson, Ronay Ak, Yung-Tsun Tina Lee, Kincho H. Law
Abstract	Quality control is a fundamental component of many manufacturing processes, especially those involving casting or welding. However, manual quality control procedures are often time-consuming and error-prone. In order to meet the growing demand for high-quality products, the use of intelligent visual inspection systems is becoming essential in production lines. Recently, Convolutional Neural Networks (CNNs) have shown outstanding performance in both image classification and localization tasks. In this article, a system is proposed for the identification of casting defects in X-ray images, based on the Mask Region-based CNN architecture. The proposed defect detection system simultaneously performs defect detection and segmentation on input images, making it suitable for a range of defect detection tasks. It is shown that training the network to simultaneously perform defect detection and defect instance segmentation, results in a higher defect detection accuracy than training on defect detection alone. Transfer learning is leveraged to reduce the training data demands and increase the prediction accuracy of the trained model. More specifically, the model is first trained with two large openly-available image datasets before finetuning on a relatively small metal casting X-ray dataset. The accuracy of the trained model exceeds state-of-the art performance on the GRIMA database of X-ray images (GDXray) Castings dataset and is fast enough to be used in a production setting. The system also performs well on the GDXray Welds dataset. A number of in-depth studies are conducted to explore how transfer learning, multi-task learning, and multi-class learning influence the performance of the trained system.
Tasks	Image Classification, Instance Segmentation, Multi-Task Learning, Semantic Segmentation, Transfer Learning
Published	2018-08-07
URL	http://arxiv.org/abs/1808.02518v2
PDF	http://arxiv.org/pdf/1808.02518v2.pdf
PWC	https://paperswithcode.com/paper/detection-and-segmentation-of-manufacturing
Repo
Framework

Modeling sepsis progression using hidden Markov models


Title	Modeling sepsis progression using hidden Markov models
Authors	Brenden K. Petersen, Michael B. Mayhew, Kalvin O. E. Ogbuefi, John D. Greene, Vincent X. Liu, Priyadip Ray
Abstract	Characterizing a patient’s progression through stages of sepsis is critical for enabling risk stratification and adaptive, personalized treatment. However, commonly used sepsis diagnostic criteria fail to account for significant underlying heterogeneity, both between patients as well as over time in a single patient. We introduce a hidden Markov model of sepsis progression that explicitly accounts for patient heterogeneity. Benchmarked against two sepsis diagnostic criteria, the model provides a useful tool to uncover a patient’s latent sepsis trajectory and to identify high-risk patients in whom more aggressive therapy may be indicated.
Tasks
Published	2018-01-09
URL	http://arxiv.org/abs/1801.02736v1
PDF	http://arxiv.org/pdf/1801.02736v1.pdf
PWC	https://paperswithcode.com/paper/modeling-sepsis-progression-using-hidden
Repo
Framework

Multi-Source Neural Machine Translation with Missing Data


Title	Multi-Source Neural Machine Translation with Missing Data
Authors	Yuta Nishimura, Katsuhito Sudoh, Graham Neubig, Satoshi Nakamura
Abstract	Multi-source translation is an approach to exploit multiple inputs (e.g. in two different languages) to increase translation accuracy. In this paper, we examine approaches for multi-source neural machine translation (NMT) using an incomplete multilingual corpus in which some translations are missing. In practice, many multilingual corpora are not complete due to the difficulty to provide translations in all of the relevant languages (for example, in TED talks, most English talks only have subtitles for a small portion of the languages that TED supports). Existing studies on multi-source translation did not explicitly handle such situations. This study focuses on the use of incomplete multilingual corpora in multi-encoder NMT and mixture of NMT experts and examines a very simple implementation where missing source translations are replaced by a special symbol . These methods allow us to use incomplete corpora both at training time and test time. In experiments with real incomplete multilingual corpora of TED Talks, the multi-source NMT with the tokens achieved higher translation accuracies measured by BLEU than those by any one-to-one NMT systems.
Tasks	Machine Translation
Published	2018-06-07
URL	http://arxiv.org/abs/1806.02525v2
PDF	http://arxiv.org/pdf/1806.02525v2.pdf
PWC	https://paperswithcode.com/paper/multi-source-neural-machine-translation-with
Repo
Framework