January 26, 2020

3227 words 16 mins read

Paper Group ANR 1564

Safe, Efficient, and Comfortable Velocity Control based on Reinforcement Learning for Autonomous Driving. On the bias of H-scores for comparing biclusters, and how to correct it. Pun-GAN: Generative Adversarial Network for Pun Generation. Semantic Head Enhanced Pedestrian Detection in a Crowd. Portable system for the prediction of anemia based on t …

Safe, Efficient, and Comfortable Velocity Control based on Reinforcement Learning for Autonomous Driving


Title	Safe, Efficient, and Comfortable Velocity Control based on Reinforcement Learning for Autonomous Driving
Authors	Meixin Zhu, Yinhai Wang, Ziyuan Pu, Jingyun Hu, Xuesong Wang, Ruimin Ke
Abstract	A model used for velocity control during car following was proposed based on deep reinforcement learning (RL). To fulfil the multi-objectives of car following, a reward function reflecting driving safety, efficiency, and comfort was constructed. With the reward function, the RL agent learns to control vehicle speed in a fashion that maximizes cumulative rewards, through trials and errors in the simulation environment. A total of 1,341 car-following events extracted from the Next Generation Simulation (NGSIM) dataset were used to train the model. Car-following behavior produced by the model were compared with that observed in the empirical NGSIM data, to demonstrate the model’s ability to follow a lead vehicle safely, efficiently, and comfortably. Results show that the model demonstrates the capability of safe, efficient, and comfortable velocity control in that it 1) has small percentages (8%) of dangerous minimum time to collision values (\textless\ 5s) than human drivers in the NGSIM data (35%); 2) can maintain efficient and safe headways in the range of 1s to 2s; and 3) can follow the lead vehicle comfortably with smooth acceleration. The results indicate that reinforcement learning methods could contribute to the development of autonomous driving systems.
Tasks	Autonomous Driving
Published	2019-01-29
URL	https://arxiv.org/abs/1902.00089v2
PDF	https://arxiv.org/pdf/1902.00089v2.pdf
PWC	https://paperswithcode.com/paper/safe-efficient-and-comfortable-velocity
Repo
Framework

On the bias of H-scores for comparing biclusters, and how to correct it


Title	On the bias of H-scores for comparing biclusters, and how to correct it
Authors	Jacopo Di Iorio, Francesca Chiaromonte, Marzia A. Cremona
Abstract	In the last two decades several biclustering methods have been developed as new unsupervised learning techniques to simultaneously cluster rows and columns of a data matrix. These algorithms play a central role in contemporary machine learning and in many applications, e.g. to computational biology and bioinformatics. The H-score is the evaluation score underlying the seminal biclustering algorithm by Cheng and Church, as well as many other subsequent biclustering methods. In this paper, we characterize a potentially troublesome bias in this score, that can distort biclustering results. We prove, both analytically and by simulation, that the average H-score increases with the number of rows/columns in a bicluster. This makes the H-score, and hence all algorithms based on it, biased towards small clusters. Based on our analytical proof, we are able to provide a straightforward way to correct this bias, allowing users to accurately compare biclusters.
Tasks
Published	2019-07-24
URL	https://arxiv.org/abs/1907.11142v1
PDF	https://arxiv.org/pdf/1907.11142v1.pdf
PWC	https://paperswithcode.com/paper/on-the-bias-of-h-scores-for-comparing
Repo
Framework

Pun-GAN: Generative Adversarial Network for Pun Generation


Title	Pun-GAN: Generative Adversarial Network for Pun Generation
Authors	Fuli Luo, Shunyao Li, Pengcheng Yang, Lei li, Baobao Chang, Zhifang Sui, Xu Sun
Abstract	In this paper, we focus on the task of generating a pun sentence given a pair of word senses. A major challenge for pun generation is the lack of large-scale pun corpus to guide the supervised learning. To remedy this, we propose an adversarial generative network for pun generation (Pun-GAN), which does not require any pun corpus. It consists of a generator to produce pun sentences, and a discriminator to distinguish between the generated pun sentences and the real sentences with specific word senses. The output of the discriminator is then used as a reward to train the generator via reinforcement learning, encouraging it to produce pun sentences that can support two word senses simultaneously. Experiments show that the proposed Pun-GAN can generate sentences that are more ambiguous and diverse in both automatic and human evaluation.
Tasks
Published	2019-10-24
URL	https://arxiv.org/abs/1910.10950v1
PDF	https://arxiv.org/pdf/1910.10950v1.pdf
PWC	https://paperswithcode.com/paper/pun-gan-generative-adversarial-network-for
Repo
Framework

Semantic Head Enhanced Pedestrian Detection in a Crowd


Title	Semantic Head Enhanced Pedestrian Detection in a Crowd
Authors	Ruiqi Lu, Huimin Ma
Abstract	Pedestrian detection in the crowd is a challenging task because of intra-class occlusion. More prior information is needed for the detector to be robust against it. Human head area is naturally a strong cue because of its stable appearance, visibility and relative location to body. Inspired by it, we adopt an extra branch to conduct semantic head detection in parallel with traditional body branch. Instead of manually labeling the head regions, we use weak annotations inferred directly from body boxes, which is named as `semantic head’. In this way, the head detection is formulated into using a special part of labeled box to detect the corresponding part of human body, which surprisingly improves the performance and robustness to occlusion. Moreover, the head-body alignment structure is explicitly explored by introducing Alignment Loss, which functions in a self-supervised manner. Based on these, we propose the head-body alignment net (HBAN) in this work, which aims to enhance pedestrian detection by fully utilizing the human head prior. Comprehensive evaluations are conducted to demonstrate the effectiveness of HBAN on CityPersons dataset. \|
Tasks	Head Detection, Pedestrian Detection
Published	2019-11-27
URL	https://arxiv.org/abs/1911.11985v1
PDF	https://arxiv.org/pdf/1911.11985v1.pdf
PWC	https://paperswithcode.com/paper/semantic-head-enhanced-pedestrian-detection
Repo
Framework

Portable system for the prediction of anemia based on the ocular conjunctiva using Artificial Intelligence


Title	Portable system for the prediction of anemia based on the ocular conjunctiva using Artificial Intelligence
Authors	Bryan Saldivar-Espinoza, Dennis Núñez-Fernández, Franklin Porras-Barrientos, Alicia Alva-Mantari, Lisa Suzanne Leslie, Mirko Zimic
Abstract	Anemia is a major health burden worldwide. Examining the hemoglobin level of blood is an important way to achieve the diagnosis of anemia, but it requires blood drawing and a blood test. In this work we propose a non-invasive, fast, and cost-effective screening test for iron-deficiency anemia in Peruvian young children. Our initial results show promising evidence for detecting conjunctival pallor anemia and Artificial Intelligence techniques with photos taken with a popular smartphone.
Tasks
Published	2019-10-25
URL	https://arxiv.org/abs/1910.12399v1
PDF	https://arxiv.org/pdf/1910.12399v1.pdf
PWC	https://paperswithcode.com/paper/portable-system-for-the-prediction-of-anemia
Repo
Framework

A Review of Point Cloud Semantic Segmentation


Title	A Review of Point Cloud Semantic Segmentation
Authors	Yuxing Xie, Jiaojiao Tian, Xiao Xiang Zhu
Abstract	3D Point Cloud Semantic Segmentation (PCSS) is attracting increasing interest, due to its applicability in remote sensing, computer vision and robotics, and due to the new possibilities offered by deep learning techniques. In order to provide a needed up-to-date review of recent developments in PCSS, this article summarizes existing studies on this topic. Firstly, we outline the acquisition and evolution of the 3D point cloud from the perspective of remote sensing and computer vision, as well as the published benchmarks for PCSS studies. Then, traditional and advanced techniques used for Point Cloud Segmentation (PCS) and PCSS are reviewed and compared. Finally, important issues and open questions in PCSS studies are discussed.
Tasks	Semantic Segmentation
Published	2019-08-23
URL	https://arxiv.org/abs/1908.08854v2
PDF	https://arxiv.org/pdf/1908.08854v2.pdf
PWC	https://paperswithcode.com/paper/a-review-of-point-cloud-semantic-segmentation
Repo
Framework

Multi-Target Embodied Question Answering


Title	Multi-Target Embodied Question Answering
Authors	Licheng Yu, Xinlei Chen, Georgia Gkioxari, Mohit Bansal, Tamara L. Berg, Dhruv Batra
Abstract	Embodied Question Answering (EQA) is a relatively new task where an agent is asked to answer questions about its environment from egocentric perception. EQA makes the fundamental assumption that every question, e.g., “what color is the car?", has exactly one target (“car”) being inquired about. This assumption puts a direct limitation on the abilities of the agent. We present a generalization of EQA - Multi-Target EQA (MT-EQA). Specifically, we study questions that have multiple targets in them, such as “Is the dresser in the bedroom bigger than the oven in the kitchen?", where the agent has to navigate to multiple locations (“dresser in bedroom”, “oven in kitchen”) and perform comparative reasoning (“dresser” bigger than “oven”) before it can answer a question. Such questions require the development of entirely new modules or components in the agent. To address this, we propose a modular architecture composed of a program generator, a controller, a navigator, and a VQA module. The program generator converts the given question into sequential executable sub-programs; the navigator guides the agent to multiple locations pertinent to the navigation-related sub-programs; and the controller learns to select relevant observations along its path. These observations are then fed to the VQA module to predict the answer. We perform detailed analysis for each of the model components and show that our joint model can outperform previous methods and strong baselines by a significant margin.
Tasks	Embodied Question Answering, Question Answering, Visual Question Answering
Published	2019-04-09
URL	http://arxiv.org/abs/1904.04686v1
PDF	http://arxiv.org/pdf/1904.04686v1.pdf
PWC	https://paperswithcode.com/paper/multi-target-embodied-question-answering
Repo
Framework

Best k-layer neural network approximations


Title	Best k-layer neural network approximations
Authors	Lek-Heng Lim, Mateusz Michalek, Yang Qi
Abstract	We show that the empirical risk minimization (ERM) problem for neural networks has no solution in general. Given a training set $s_1, \dots, s_n \in \mathbb{R}^p$ with corresponding responses $t_1,\dots,t_n \in \mathbb{R}^q$, fitting a $k$-layer neural network $\nu_\theta : \mathbb{R}^p \to \mathbb{R}^q$ involves estimation of the weights $\theta \in \mathbb{R}^m$ via an ERM: [ \inf_{\theta \in \mathbb{R}^m} ; \sum_{i=1}^n \lVert t_i - \nu_\theta(s_i) \rVert_2^2. ] We show that even for $k = 2$, this infimum is not attainable in general for common activations like ReLU, hyperbolic tangent, and sigmoid functions. A high-level explanation is like that for the nonexistence of best rank-$r$ approximations of higher-order tensors — the set of parameters is not a closed set — but the geometry involved for best $k$-layer neural networks approximations is more subtle. In addition, we show that for smooth activations $\sigma(x)= 1/\bigl(1 + \exp(-x)\bigr)$ and $\sigma(x)=\tanh(x)$, such failure to attain an infimum can happen on a positive-measured subset of responses. For the ReLU activation $\sigma(x)=\max(0,x)$, we completely classifying cases where the ERM for a best two-layer neural network approximation attains its infimum. As an aside, we obtain a precise description of the geometry of the space of two-layer neural networks with $d$ neurons in the hidden layer: it is the join locus of a line and the $d$-secant locus of a cone.
Tasks
Published	2019-07-02
URL	https://arxiv.org/abs/1907.01507v2
PDF	https://arxiv.org/pdf/1907.01507v2.pdf
PWC	https://paperswithcode.com/paper/best-k-layer-neural-network-approximations
Repo
Framework

Feasibility-Guided Learning for Robust Control in Constrained Optimal Control Problems


Title	Feasibility-Guided Learning for Robust Control in Constrained Optimal Control Problems
Authors	Wei Xiao, Calin A. Belta, Christos G. Cassandras
Abstract	Optimal control problems with constraints ensuring safety and convergence to desired states can be mapped onto a sequence of real time optimization problems through the use of Control Barrier Functions (CBFs) and Control Lyapunov Functions (CLFs). One of the main challenges in these approaches is ensuring the feasibility of the resulting quadratic programs (QPs) if the system is affine in controls. The recently proposed penalty method has the potential to improve the existence of feasible solutions to such problems. In this paper, we further improve the feasibility robustness (i.e., feasibility maintenance in the presence of time-varying and unknown unsafe sets) through the definition of a High Order CBF (HOCBF) that works for arbitrary relative degree constraints; this is achieved by a proposed feasibility-guided learning approach. Specifically, we apply machine learning techniques to classify the parameter space of a HOCBF into feasible and infeasible sets, and get a differentiable classifier that is then added to the learning process. The proposed feasibility-guided learning approach is compared with the gradient-descent method on a robot control problem. The simulation results show an improved ability of the feasibility-guided learning approach over the gradient-decent method to determine the optimal parameters in the definition of a HOCBF for the feasibility robustness, as well as show the potential of the CBF method for robot safe navigation in an unknown environment.
Tasks
Published	2019-12-06
URL	https://arxiv.org/abs/1912.04066v1
PDF	https://arxiv.org/pdf/1912.04066v1.pdf
PWC	https://paperswithcode.com/paper/feasibility-guided-learning-for-robust
Repo
Framework

Neural Text Generation from Rich Semantic Representations


Title	Neural Text Generation from Rich Semantic Representations
Authors	Valerie Hajdik, Jan Buys, Michael W. Goodman, Emily M. Bender
Abstract	We propose neural models to generate high-quality text from structured representations based on Minimal Recursion Semantics (MRS). MRS is a rich semantic representation that encodes more precise semantic detail than other representations such as Abstract Meaning Representation (AMR). We show that a sequence-to-sequence model that maps a linearization of Dependency MRS, a graph-based representation of MRS, to English text can achieve a BLEU score of 66.11 when trained on gold data. The performance can be improved further using a high-precision, broad coverage grammar-based parser to generate a large silver training corpus, achieving a final BLEU score of 77.17 on the full test set, and 83.37 on the subset of test data most closely matching the silver data domain. Our results suggest that MRS-based representations are a good choice for applications that need both structured semantics and the ability to produce natural language text as output.
Tasks	Text Generation
Published	2019-04-25
URL	http://arxiv.org/abs/1904.11564v1
PDF	http://arxiv.org/pdf/1904.11564v1.pdf
PWC	https://paperswithcode.com/paper/neural-text-generation-from-rich-semantic
Repo
Framework

Subsampling Bias and The Best-Discrepancy Systematic Cross Validation


Title	Subsampling Bias and The Best-Discrepancy Systematic Cross Validation
Authors	Liang Guo, Jianya Liu, Ruodan Lu
Abstract	Statistical machine learning models should be evaluated and validated before putting to work. Conventional k-fold Monte Carlo Cross-Validation (MCCV) procedure uses a pseudo-random sequence to partition instances into k subsets, which usually causes subsampling bias, inflates generalization errors and jeopardizes the reliability and effectiveness of cross-validation. Based on ordered systematic sampling theory in statistics and low-discrepancy sequence theory in number theory, we propose a new k-fold cross-validation procedure by replacing a pseudo-random sequence with a best-discrepancy sequence, which ensures low subsampling bias and leads to more precise Expected-Prediction-Error estimates. Experiments with 156 benchmark datasets and three classifiers (logistic regression, decision tree and naive bayes) show that in general, our cross-validation procedure can extrude subsampling bias in the MCCV by lowering the EPE around 7.18% and the variances around 26.73%. In comparison, the stratified MCCV can reduce the EPE and variances of the MCCV around 1.58% and 11.85% respectively. The Leave-One-Out (LOO) can lower the EPE around 2.50% but its variances are much higher than the any other CV procedure. The computational time of our cross-validation procedure is just 8.64% of the MCCV, 8.67% of the stratified MCCV and 16.72% of the LOO. Experiments also show that our approach is more beneficial for datasets characterized by relatively small size and large aspect ratio. This makes our approach particularly pertinent when solving bioscience classification problems. Our proposed systematic subsampling technique could be generalized to other machine learning algorithms that involve random subsampling mechanism.
Tasks
Published	2019-07-04
URL	https://arxiv.org/abs/1907.02437v1
PDF	https://arxiv.org/pdf/1907.02437v1.pdf
PWC	https://paperswithcode.com/paper/subsampling-bias-and-the-best-discrepancy
Repo
Framework

Exploiting Dual-Gate Ambipolar CNFETs for Scalable Machine Learning Classification


Title	Exploiting Dual-Gate Ambipolar CNFETs for Scalable Machine Learning Classification
Authors	Farid Kenarangi, Xuan Hu, Yihan Liu, Jean Anne C. Incorvia, Joseph S. Friedman, Inna Partin-Vaisband
Abstract	Ambipolar carbon nanotube based field-effect transistors (AP-CNFETs) exhibit unique electrical characteristics, such as tri-state operation and bi-directionality, enabling systems with complex and reconfigurable computing. In this paper, AP-CNFETs are used to design a mixed-signal machine learning (ML) classifier. The classifier is designed in SPICE with feature size of 15 nm and operates at 250 MHz. The system is demonstrated based on MNIST digit dataset, yielding 90% accuracy and no accuracy degradation as compared with the classification of this dataset in Python. The system also exhibits lower power consumption and smaller physical size as compared with the state-of-the-art CMOS and memristor based mixed-signal classifiers.
Tasks
Published	2019-12-09
URL	https://arxiv.org/abs/1912.04068v1
PDF	https://arxiv.org/pdf/1912.04068v1.pdf
PWC	https://paperswithcode.com/paper/exploiting-dual-gate-ambipolar-cnfets-for
Repo
Framework

Bridging Bayesian and Minimax Mean Square Error Estimation via Wasserstein Distributionally Robust Optimization


Title	Bridging Bayesian and Minimax Mean Square Error Estimation via Wasserstein Distributionally Robust Optimization
Authors	Viet Anh Nguyen, Soroosh Shafieezadeh-Abadeh, Daniel Kuhn, Peyman Mohajerin Esfahani
Abstract	We introduce a distributionally robust minimium mean square error estimation model with a Wasserstein ambiguity set to recover an unknown signal from a noisy observation. The proposed model can be viewed as a zero-sum game between a statistician choosing an estimator—that is, a measurable function of the observation—and a fictitious adversary choosing a prior—that is, a pair of signal and noise distributions ranging over independent Wasserstein balls—with the goal to minimize and maximize the expected squared estimation error, respectively. We show that if the Wasserstein balls are centered at normal distributions, then the zero-sum game admits a Nash equilibrium, where the players’ optimal strategies are given by an {\em affine} estimator and a {\em normal} prior, respectively. We further prove that this Nash equilibrium can be computed by solving a tractable convex program. Finally, we develop a Frank-Wolfe algorithm that can solve this convex program orders of magnitude faster than state-of-the-art general purpose solvers. We show that this algorithm enjoys a linear convergence rate and that its direction-finding subproblems can be solved in quasi-closed form.
Tasks
Published	2019-11-08
URL	https://arxiv.org/abs/1911.03539v1
PDF	https://arxiv.org/pdf/1911.03539v1.pdf
PWC	https://paperswithcode.com/paper/bridging-bayesian-and-minimax-mean-square
Repo
Framework

Implicitly Learning to Reason in First-Order Logic


Title	Implicitly Learning to Reason in First-Order Logic
Authors	Vaishak Belle, Brendan Juba
Abstract	We consider the problem of answering queries about formulas of first-order logic based on background knowledge partially represented explicitly as other formulas, and partially represented as examples independently drawn from a fixed probability distribution. PAC semantics, introduced by Valiant, is one rigorous, general proposal for learning to reason in formal languages: although weaker than classical entailment, it allows for a powerful model theoretic framework for answering queries while requiring minimal assumptions about the form of the distribution in question. To date, however, the most significant limitation of that approach, and more generally most machine learning approaches with robustness guarantees, is that the logical language is ultimately essentially propositional, with finitely many atoms. Indeed, the theoretical findings on the learning of relational theories in such generality have been resoundingly negative. This is despite the fact that first-order logic is widely argued to be most appropriate for representing human knowledge. In this work, we present a new theoretical approach to robustly learning to reason in first-order logic, and consider universally quantified clauses over a countably infinite domain. Our results exploit symmetries exhibited by constants in the language, and generalize the notion of implicit learnability to show how queries can be computed against (implicitly) learned first-order background knowledge.
Tasks
Published	2019-06-24
URL	https://arxiv.org/abs/1906.10106v1
PDF	https://arxiv.org/pdf/1906.10106v1.pdf
PWC	https://paperswithcode.com/paper/implicitly-learning-to-reason-in-first-order
Repo
Framework

Fast High-Dimensional Kernel Filtering


Title	Fast High-Dimensional Kernel Filtering
Authors	Pravin Nair, Kunal N. Chaudhury
Abstract	The bilateral and nonlocal means filters are instances of kernel-based filters that are popularly used in image processing. It was recently shown that fast and accurate bilateral filtering of grayscale images can be performed using a low-rank approximation of the kernel matrix. More specifically, based on the eigendecomposition of the kernel matrix, the overall filtering was approximated using spatial convolutions, for which efficient algorithms are available. Unfortunately, this technique cannot be scaled to high-dimensional data such as color and hyperspectral images. This is simply because one needs to compute/store a large matrix and perform its eigendecomposition in this case. We show how this problem can be solved using the Nystr"om method, which is generally used for approximating the eigendecomposition of large matrices. The resulting algorithm can also be used for nonlocal means filtering. We demonstrate the effectiveness of our proposal for bilateral and nonlocal means filtering of color and hyperspectral images. In particular, our method is shown to be competitive with state-of-the-art fast algorithms, and moreover it comes with a theoretical guarantee on the approximation error.
Tasks
Published	2019-01-18
URL	http://arxiv.org/abs/1901.06112v1
PDF	http://arxiv.org/pdf/1901.06112v1.pdf
PWC	https://paperswithcode.com/paper/fast-high-dimensional-kernel-filtering
Repo
Framework