April 2, 2020

2996 words 15 mins read

Paper Group ANR 327

Paper Group ANR 327

Automata for Hyperlanguages. Learning to See: You Are What You See. Efficiently Calibrating Cable-Driven Surgical Robots With RGBD Sensing, Temporal Windowing, and Linear and Recurrent Neural Network Compensation. Tensor-Based Grading: A Novel Patch-Based Grading Approach for the Analysis of Deformation Fields in Huntington’s Disease. TED: A Pretra …

Automata for Hyperlanguages

Title Automata for Hyperlanguages
Authors Borzoo Bonakdarpour, Sarai Sheinvald
Abstract Hyperproperties lift conventional trace properties from a set of execution traces to a set of sets of execution traces. Hyperproperties have been shown to be a powerful formalism for expressing and reasoning about information-flow security policies and important properties of cyber-physical systems such as sensitivity and robustness, as well as consistency conditions in distributed computing such as linearizability. Although there is an extensive body of work on automata-based representation of trace properties, we currently lack such characterization for hyperproperties. We introduce hyperautomata for em hyperlanguages, which are languages over sets of words. Essentially, hyperautomata allow running multiple quantified words over an automaton. We propose a specific type of hyperautomata called nondeterministic finite hyperautomata (NFH), which accept regular hyperlanguages. We demonstrate the ability of regular hyperlanguages to express hyperproperties for finite traces. We then explore the fundamental properties of NFH and show their closure under the Boolean operations. We show that while nonemptiness is undecidable in general, it is decidable for several fragments of NFH. We further show the decidability of the membership problem for finite sets and regular languages for NFH, as well as the containment problem for several fragments of NFH. Finally, we introduce learning algorithms based on Angluin’s L-star algorithm for the fragments NFH in which the quantification is either strictly universal or strictly existential.
Published 2020-02-23
URL https://arxiv.org/abs/2002.09877v1
PDF https://arxiv.org/pdf/2002.09877v1.pdf
PWC https://paperswithcode.com/paper/automata-for-hyperlanguages

Learning to See: You Are What You See

Title Learning to See: You Are What You See
Authors Memo Akten, Rebecca Fiebrink, Mick Grierson
Abstract The authors present a visual instrument developed as part of the creation of the artwork Learning to See. The artwork explores bias in artificial neural networks and provides mechanisms for the manipulation of specifically trained for real-world representations. The exploration of these representations acts as a metaphor for the process of developing a visual understanding and/or visual vocabulary of the world. These representations can be explored and manipulated in real time, and have been produced in such a way so as to reflect specific creative perspectives that call into question the relationship between how both artificial neural networks and humans may construct meaning.
Published 2020-02-28
URL https://arxiv.org/abs/2003.00902v1
PDF https://arxiv.org/pdf/2003.00902v1.pdf
PWC https://paperswithcode.com/paper/learning-to-see-you-are-what-you-see

Efficiently Calibrating Cable-Driven Surgical Robots With RGBD Sensing, Temporal Windowing, and Linear and Recurrent Neural Network Compensation

Title Efficiently Calibrating Cable-Driven Surgical Robots With RGBD Sensing, Temporal Windowing, and Linear and Recurrent Neural Network Compensation
Authors Minho Hwang, Brijen Thananjeyan, Samuel Paradis, Daniel Seita, Jeffrey Ichnowski, Danyal Fer, Thomas Low, Ken Goldberg
Abstract Automation of surgical subtasks using cable-driven robotic surgical assistants (RSAs) such as Intuitive Surgical’s da Vinci Research Kit (dVRK) is challenging due to imprecision in control from cable-related effects such as backlash, stretch, and hysteresis. We propose a novel approach to efficiently calibrate a dVRK by placing a 3D printed fiducial coordinate frame on the arm and end-effector that is tracked using RGBD sensing. To measure the coupling effects between joints and history-dependent effects, we analyze data from sampled trajectories and consider 13 modeling approaches using LSTM recurrent neural networks and linear models with varying temporal window length to provide corrective feedback. With the proposed method, data collection takes 31 minutes to produce 1800 samples and model training takes less than a minute. Results suggest that the resulting model can reduce the mean tracking error of the physical robot from 2.96mm to 0.65mm on a test set of reference trajectories. We evaluate the model by executing open-loop trajectories of the FLS peg transfer surgeon training task. Results suggest that the best approach increases success rate from 39.4% to 96.7% comparable to the performance of an expert surgical resident. Supplementary material, including 3D-printable models, is available at https://sites.google.com/berkeley.edu/surgical-calibration.
Tasks Calibration
Published 2020-03-19
URL https://arxiv.org/abs/2003.08520v1
PDF https://arxiv.org/pdf/2003.08520v1.pdf
PWC https://paperswithcode.com/paper/efficiently-calibrating-cable-driven-surgical

Tensor-Based Grading: A Novel Patch-Based Grading Approach for the Analysis of Deformation Fields in Huntington’s Disease

Title Tensor-Based Grading: A Novel Patch-Based Grading Approach for the Analysis of Deformation Fields in Huntington’s Disease
Authors Kilian Hett, Hans Johnson, Pierrick Coupé, Jane Paulsen, Jeffrey Long, Ipek Oguz
Abstract The improvements in magnetic resonance imaging have led to the development of numerous techniques to better detect structural alterations caused by neurodegenerative diseases. Among these, the patch-based grading framework has been proposed to model local patterns of anatomical changes. This approach is attractive because of its low computational cost and its competitive performance. Other studies have proposed to analyze the deformations of brain structures using tensor-based morphometry, which is a highly interpretable approach. In this work, we propose to combine the advantages of these two approaches by extending the patch-based grading framework with a new tensor-based grading method that enables us to model patterns of local deformation using a log-Euclidean metric. We evaluate our new method in a study of the putamen for the classification of patients with pre-manifest Huntington’s disease and healthy controls. Our experiments show a substantial increase in classification accuracy (87.5 $\pm$ 0.5 vs. 81.3 $\pm$ 0.6) compared to the existing patch-based grading methods, and a good complement to putamen volume, which is a primary imaging-based marker for the study of Huntington’s disease.
Published 2020-01-23
URL https://arxiv.org/abs/2001.08651v1
PDF https://arxiv.org/pdf/2001.08651v1.pdf
PWC https://paperswithcode.com/paper/tensor-based-grading-a-novel-patch-based

TED: A Pretrained Unsupervised Summarization Model with Theme Modeling and Denoising

Title TED: A Pretrained Unsupervised Summarization Model with Theme Modeling and Denoising
Authors Ziyi Yang, Chenguang Zhu, Robert Gmyr, Michael Zeng, Xuedong Huang, Eric Darve
Abstract Text summarization aims to extract essential information from a piece of text and transform it into a concise version. Existing unsupervised abstractive summarization models use recurrent neural networks framework and ignore abundant unlabeled corpora resources. In order to address these issues, we propose TED, a transformer-based unsupervised summarization system with pretraining on large-scale data. We first leverage the lead bias in news articles to pretrain the model on large-scale corpora. Then, we finetune TED on target domains through theme modeling and a denoising autoencoder to enhance the quality of summaries. Notably, TED outperforms all unsupervised abstractive baselines on NYT, CNN/DM and English Gigaword datasets with various document styles. Further analysis shows that the summaries generated by TED are abstractive and containing even higher proportions of novel tokens than those from supervised models.
Tasks Abstractive Text Summarization, Denoising, Text Summarization
Published 2020-01-03
URL https://arxiv.org/abs/2001.00725v2
PDF https://arxiv.org/pdf/2001.00725v2.pdf
PWC https://paperswithcode.com/paper/ted-a-pretrained-unsupervised-summarization-1

CPM R-CNN: Calibrating Point-guided Misalignment in Object Detection

Title CPM R-CNN: Calibrating Point-guided Misalignment in Object Detection
Authors Bin Zhu, Qing Song, Lu Yang, Zhihui Wang, Chun Liu, Mengjie Hu
Abstract In object detection, offset-guided and point-guided regression dominate anchor-based and anchor-free method separately. Recently, point-guided approach is introduced to anchor-based method. However, we observe points predicted by this way are misaligned with matched region of proposals and score of localization, causing a notable gap in performance. In this paper, we propose CPM R-CNN which contains three efficient modules to optimize anchor-based point-guided method. According to sufficient evaluations on the COCO dataset, CPM R-CNN is demonstrated efficient to improve the localization accuracy by calibrating mentioned misalignment. Compared with Faster R-CNN and Grid R-CNN based on ResNet-101 with FPN, our approach can substantially improve detection mAP by 3.3% and 1.5% respectively without whistles and bells. Moreover, our best model achieves improvement by a large margin to 49.9% on COCO test-dev. Code and models will be publicly available.
Tasks Object Detection
Published 2020-03-07
URL https://arxiv.org/abs/2003.03570v1
PDF https://arxiv.org/pdf/2003.03570v1.pdf
PWC https://paperswithcode.com/paper/cpm-r-cnn-calibrating-point-guided

Robust Deep Learning Framework For Predicting Respiratory Anomalies and Diseases

Title Robust Deep Learning Framework For Predicting Respiratory Anomalies and Diseases
Authors Lam Pham, Ian McLoughlin, Huy Phan, Minh Tran, Truc Nguyen, Ramaswamy Palaniappan
Abstract This paper presents a robust deep learning framework developed to detect respiratory diseases from recordings of respiratory sounds. The complete detection process firstly involves front end feature extraction where recordings are transformed into spectrograms that convey both spectral and temporal information. Then a back-end deep learning model classifies the features into classes of respiratory disease or anomaly. Experiments, conducted over the ICBHI benchmark dataset of respiratory sounds, evaluate the ability of the framework to classify sounds. Two main contributions are made in this paper. Firstly, we provide an extensive analysis of how factors such as respiratory cycle length, time resolution, and network architecture, affect final prediction accuracy. Secondly, a novel deep learning based framework is proposed for detection of respiratory diseases and shown to perform extremely well compared to state of the art methods.
Published 2020-01-21
URL https://arxiv.org/abs/2002.03894v1
PDF https://arxiv.org/pdf/2002.03894v1.pdf
PWC https://paperswithcode.com/paper/robust-deep-learning-framework-for-predicting

Mario Level Generation From Mechanics Using Scene Stitching

Title Mario Level Generation From Mechanics Using Scene Stitching
Authors Michael Cerny Green, Luvneesh Mugrai, Ahmed Khalifa, Julian Togelius
Abstract This paper presents a level generation method for Super Mario by stitching together pre-generated “scenes” that contain specific mechanics, using mechanic-sequences from agent playthroughs as input specifications. Given a sequence of mechanics, our system uses an FI-2Pop algorithm and a corpus of scenes to perform automated level authoring. The system outputs levels that have a similar mechanical sequence to the target mechanic sequence but with a different playthrough experience. We compare our system to a greedy method that selects scenes that maximize the target mechanics. Our system is able to maximize the number of matched mechanics while reducing emergent mechanics using the stitching process compared to the greedy approach.
Published 2020-02-07
URL https://arxiv.org/abs/2002.02992v1
PDF https://arxiv.org/pdf/2002.02992v1.pdf
PWC https://paperswithcode.com/paper/mario-level-generation-from-mechanics-using

Constraints in Developing a Complete Bengali Optical Character Recognition System

Title Constraints in Developing a Complete Bengali Optical Character Recognition System
Authors Abu Saleh Md. Abir, Sanjana Rahman, Samia Ellin, Maisha Farzana, Md Hridoy Manik, Chowdhury Rafeed Rahman
Abstract Technological advancement has led to digitizing hard copies of media effortlessly with optical character recognition (OCR) system. As OCR systems are being used constantly, converting printed or handwritten documents and books have become simple and time efficient. To be a fully functional structure, Bengali OCR system needs to overcome some constraints involved in pre-processing, segmentation and recognition phase. The aim of this research is to analyze the challenges prevalent in developing a Bengali OCR system through robust literature review and implementation.
Tasks Optical Character Recognition
Published 2020-03-18
URL https://arxiv.org/abs/2003.08384v2
PDF https://arxiv.org/pdf/2003.08384v2.pdf
PWC https://paperswithcode.com/paper/constraints-in-developing-a-complete-bengali

PiP: Planning-informed Trajectory Prediction for Autonomous Driving

Title PiP: Planning-informed Trajectory Prediction for Autonomous Driving
Authors Haoran Song, Wenchao Ding, Yuxuan Chen, Shaojie Shen, Michael Yu Wang, Qifeng Chen
Abstract It is critical to predict the motion of surrounding vehicles for self-driving planning, especially in a socially compliant and flexible way. However, future prediction is challenging due to the interaction and uncertainty in driving behaviors. We propose planning-informed trajectory prediction (PiP) to tackle the prediction problem in the multi-agent setting. Our approach is differentiated from the traditional manner of prediction, which is only based on historical information and decoupled with planning. By informing the prediction process with the planning of ego vehicle, our method achieves the state-of-the-art performance of multi-agent forecasting on highway datasets. Moreover, our approach enables a novel pipeline which couples the prediction and planning, by conditioning PiP on multiple candidate trajectories of the ego vehicle, which is highly beneficial for autonomous driving in interactive scenarios.
Tasks Autonomous Driving, Future prediction, Trajectory Prediction
Published 2020-03-25
URL https://arxiv.org/abs/2003.11476v1
PDF https://arxiv.org/pdf/2003.11476v1.pdf
PWC https://paperswithcode.com/paper/pip-planning-informed-trajectory-prediction

Unsupervised Sequence Forecasting of 100,000 Points for Unsupervised Trajectory Forecasting

Title Unsupervised Sequence Forecasting of 100,000 Points for Unsupervised Trajectory Forecasting
Authors Xinshuo Weng, Jianren Wang, Sergey Levine, Kris Kitani, Nicholas Rhinehart
Abstract Predicting the future is a crucial first step to effective control, since systems that can predict the future can select plans that lead to desired outcomes. In this work, we study the problem of future prediction at the level of 3D scenes, represented by point clouds captured by a LiDAR sensor, i.e., directly learning to forecast the evolution of >100,000 points that comprise a complete scene. We term this Scene Point Cloud Sequence Forecasting (SPCSF). By directly predicting the densest-possible 3D representation of the future, the output contains richer information than other representations such as future object trajectories. We design a method, SPCSFNet, evaluate it on the KITTI and nuScenes datasets, and find that it demonstrates excellent performance on the SPCSF task. To show that SPCSF can benefit downstream tasks such as object trajectory forecasting, we present a new object trajectory forecasting pipeline leveraging SPCSFNet. Specifically, instead of forecasting at the object level as in conventional trajectory forecasting, we propose to forecast at the sensor level and then apply detection and tracking on the predicted sensor data. As a result, our new pipeline can remove the need of object trajectory labels and enable large-scale training with unlabeled sensor data. Surprisingly, we found our new pipeline based on SPCSFNet was able to outperform the conventional pipeline using state-of-the-art trajectory forecasting methods, all of which require future object trajectory labels. Finally, we propose a new evaluation procedure and two new metrics to measure the end-to-end performance of the trajectory forecasting pipeline. Our code will be made publicly available at https://github.com/xinshuoweng/SPCSF
Tasks Future prediction
Published 2020-03-18
URL https://arxiv.org/abs/2003.08376v2
PDF https://arxiv.org/pdf/2003.08376v2.pdf
PWC https://paperswithcode.com/paper/sequential-forecasting-of-100000-points

Social diversity and social preferences in mixed-motive reinforcement learning

Title Social diversity and social preferences in mixed-motive reinforcement learning
Authors Kevin R. McKee, Ian Gemp, Brian McWilliams, Edgar A. Duéñez-Guzmán, Edward Hughes, Joel Z. Leibo
Abstract Recent research on reinforcement learning in pure-conflict and pure-common interest games has emphasized the importance of population heterogeneity. In contrast, studies of reinforcement learning in mixed-motive games have primarily leveraged homogeneous approaches. Given the defining characteristic of mixed-motive games–the imperfect correlation of incentives between group members–we study the effect of population heterogeneity on mixed-motive reinforcement learning. We draw on interdependence theory from social psychology and imbue reinforcement learning agents with Social Value Orientation (SVO), a flexible formalization of preferences over group outcome distributions. We subsequently explore the effects of diversity in SVO on populations of reinforcement learning agents in two mixed-motive Markov games. We demonstrate that heterogeneity in SVO generates meaningful and complex behavioral variation among agents similar to that suggested by interdependence theory. Empirical results in these mixed-motive dilemmas suggest agents trained in heterogeneous populations develop particularly generalized, high-performing policies relative to those trained in homogeneous populations.
Published 2020-02-06
URL https://arxiv.org/abs/2002.02325v2
PDF https://arxiv.org/pdf/2002.02325v2.pdf
PWC https://paperswithcode.com/paper/social-diversity-and-social-preferences-in

An Adaptive and Near Parameter-free Evolutionary Computation Approach Towards True Automation in AutoML

Title An Adaptive and Near Parameter-free Evolutionary Computation Approach Towards True Automation in AutoML
Authors Benjamin Patrick Evans, Bing Xue, Mengjie Zhang
Abstract A common claim of evolutionary computation methods is that they can achieve good results without the need for human intervention. However, one criticism of this is that there are still hyperparameters which must be tuned in order to achieve good performance. In this work, we propose a near “parameter-free” genetic programming approach, which adapts the hyperparameter values throughout evolution without ever needing to be specified manually. We apply this to the area of automated machine learning (by extending TPOT), to produce pipelines which can effectively be claimed to be free from human input, and show that the results are competitive with existing state-of-the-art which use hand-selected hyperparameter values. Pipelines begin with a randomly chosen estimator and evolve to competitive pipelines automatically. This work moves towards a truly automatic approach to AutoML.
Tasks AutoML
Published 2020-01-28
URL https://arxiv.org/abs/2001.10178v1
PDF https://arxiv.org/pdf/2001.10178v1.pdf
PWC https://paperswithcode.com/paper/an-adaptive-and-near-parameter-free

A Deep Reinforcement Learning Algorithm Using Dynamic Attention Model for Vehicle Routing Problems

Title A Deep Reinforcement Learning Algorithm Using Dynamic Attention Model for Vehicle Routing Problems
Authors Bo Peng, Jiahai Wang, Zizhen Zhang
Abstract Recent researches show that machine learning has the potential to learn better heuristics than the one designed by human for solving combinatorial optimization problems. The deep neural network is used to characterize the input instance for constructing a feasible solution incrementally. Recently, an attention model is proposed to solve routing problems. In this model, the state of an instance is represented by node features that are fixed over time. However, the fact is, the state of an instance is changed according to the decision that the model made at different construction steps, and the node features should be updated correspondingly. Therefore, this paper presents a dynamic attention model with dynamic encoder-decoder architecture, which enables the model to explore node features dynamically and exploit hidden structure information effectively at different construction steps. This paper focuses on a challenging NP-hard problem, vehicle routing problem. The experiments indicate that our model outperforms the previous methods and also shows a good generalization performance.
Tasks Combinatorial Optimization
Published 2020-02-09
URL https://arxiv.org/abs/2002.03282v1
PDF https://arxiv.org/pdf/2002.03282v1.pdf
PWC https://paperswithcode.com/paper/a-deep-reinforcement-learning-algorithm-using

Safe Screening for the Generalized Conditional Gradient Method

Title Safe Screening for the Generalized Conditional Gradient Method
Authors Yifan Sun, Francis Bach
Abstract The conditional gradient method (CGM) has been widely used for fast sparse approximation, having a low per iteration computational cost for structured sparse regularizers. We explore the sparsity acquiring properties of a generalized CGM (gCGM), where the constraint is replaced by a penalty function based on a gauge penalty; this can be done without significantly increasing the per-iteration computation, and applies to general notions of sparsity. Without assuming bounded iterates, we show $O(1/t)$ convergence of the function values and gap of gCGM. We couple this with a safe screening rule, and show that at a rate $O(1/(t\delta^2))$, the screened support matches the support at the solution, where $\delta \geq 0$ measures how close the problem is to being degenerate. In our experiments, we show that the gCGM for these modified penalties have similar feature selection properties as common penalties, but with potentially more stability over the choice of hyperparameter.
Tasks Feature Selection
Published 2020-02-22
URL https://arxiv.org/abs/2002.09718v1
PDF https://arxiv.org/pdf/2002.09718v1.pdf
PWC https://paperswithcode.com/paper/safe-screening-for-the-generalized
comments powered by Disqus