January 29, 2020

3436 words 17 mins read

Paper Group ANR 524

Depth Camera Based Particle Filter for Robotic Osteotomy Navigation. Unsupervised Detection of Distinctive Regions on 3D Shapes. Deep 3D Convolutional Neural Network for Automated Lung Cancer Diagnosis. Governance by Glass-Box: Implementing Transparent Moral Bounds for AI Behaviour. Towards Structured Evaluation of Deep Neural Network Supervisors. …


Title	Depth Camera Based Particle Filter for Robotic Osteotomy Navigation
Authors	Tim Übelhör, Jonas Gesenhues, Nassim Ayoub, Ali Modabber, Dirk Abel
Abstract	Active surgical robots lack acceptance in clinical practice, because they do not offer the flexibility and usability required for a versatile usage: the systems require a large installation space or a complicated registration step, where the preoperative plan is aligned to the patient and transformed to the base frame of the robot. In this paper, a navigation system for robotic osteotomies is designed, which uses the raw depth images from a camera mounted on the flange of a lightweight robot arm. Consequently, the system does not require any rigid attachment of the robot or fiducials to the bone and the time-consuming registration step is eliminated. Instead, only a coarse initialization is required which improves the usability in surgery. The full six dimensional pose of the iliac crest bone is estimated with a particle filter at a maximum rate of 90 Hz. The presented method is robust against changing lighting conditions, blood or tissue on the bone surface and partial occlusions caused by the surgeons. Proof of the usability in a clinical environment is successfully provided in a corpse study, where surgeons used an augmented reality osteotomy template, which was aligned to bone via the particle filters pose estimates for the resection of transplants from the iliac crest.
Tasks
Published	2019-10-24
URL	https://arxiv.org/abs/1910.11116v1
PDF	https://arxiv.org/pdf/1910.11116v1.pdf
PWC	https://paperswithcode.com/paper/depth-camera-based-particle-filter-for
Repo
Framework

Unsupervised Detection of Distinctive Regions on 3D Shapes


Title	Unsupervised Detection of Distinctive Regions on 3D Shapes
Authors	Xianzhi Li, Lequan Yu, Chi-Wing Fu, Daniel Cohen-Or, Pheng-Ann Heng
Abstract	This paper presents a novel approach to learn and detect distinctive regions on 3D shapes. Unlike previous works, which require labeled data, our method is unsupervised. We conduct the analysis on point sets sampled from 3D shapes and train a deep neural network for an unsupervised shape clustering task to learn local and global features for distinguishing shapes relative to a given shape set. To drive the network to learn in an unsupervised manner, we design a clustering-based nonparametric softmax classifier with an iterative re-clustering of shapes, and an adapted contrastive loss for enhancing the feature embedding quality and stabilizing the learning process. By then, we encourage the network to learn the point distinctiveness on the input shapes. We extensively evaluate various aspects of our approach and present its applications for distinctiveness-guided shape retrieval, sampling, and view selection in 3D scenes.
Tasks
Published	2019-05-05
URL	https://arxiv.org/abs/1905.01684v1
PDF	https://arxiv.org/pdf/1905.01684v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-detection-of-distinctive-regions
Repo
Framework

Deep 3D Convolutional Neural Network for Automated Lung Cancer Diagnosis


Title	Deep 3D Convolutional Neural Network for Automated Lung Cancer Diagnosis
Authors	Sumita Mishra, Naresh Kumar Chaudhary, Pallavi Asthana, Anil Kumar
Abstract	Computer Aided Diagnosis has emerged as an indispensible technique for validating the opinion of radiologists in CT interpretation. This paper presents a deep 3D Convolutional Neural Network (CNN) architecture for automated CT scan-based lung cancer detection system. It utilizes three dimensional spatial information to learn highly discriminative 3 dimensional features instead of 2D features like texture or geometric shape whick need to be generated manually. The proposed deep learning method automatically extracts the 3D features on the basis of spatio-temporal statistics.The developed model is end-to-end and is able to predict malignancy of each voxel for given input scan. Simulation results demonstrate the effectiveness of proposed 3D CNN network for classification of lung nodule in-spite of limited computational capabilities.
Tasks	Lung Cancer Diagnosis
Published	2019-05-04
URL	https://arxiv.org/abs/1906.01054v1
PDF	https://arxiv.org/pdf/1906.01054v1.pdf
PWC	https://paperswithcode.com/paper/190601054
Repo
Framework

Governance by Glass-Box: Implementing Transparent Moral Bounds for AI Behaviour


Title	Governance by Glass-Box: Implementing Transparent Moral Bounds for AI Behaviour
Authors	Andrea Aler Tubella, Andreas Theodorou, Virginia Dignum, Frank Dignum
Abstract	Artificial Intelligence (AI) applications are being used to predict and assess behaviour in multiple domains, such as criminal justice and consumer finance, which directly affect human well-being. However, if AI is to improve people’s lives, then people must be able to trust AI, which means being able to understand what the system is doing and why. Even though transparency is often seen as the requirement in this case, realistically it might not always be possible or desirable, whereas the need to ensure that the system operates within set moral bounds remains. In this paper, we present an approach to evaluate the moral bounds of an AI system based on the monitoring of its inputs and outputs. We place a “glass box” around the system by mapping moral values into explicit verifiable norms that constrain inputs and outputs, in such a way that if these remain within the box we can guarantee that the system adheres to the value. The focus on inputs and outputs allows for the verification and comparison of vastly different intelligent systems; from deep neural networks to agent-based systems. The explicit transformation of abstract moral values into concrete norms brings great benefits in terms of explainability; stakeholders know exactly how the system is interpreting and employing relevant abstract moral human values and calibrate their trust accordingly. Moreover, by operating at a higher level we can check the compliance of the system with different interpretations of the same value. These advantages will have an impact on the well-being of AI systems users at large, building their trust and providing them with concrete knowledge on how systems adhere to moral values.
Tasks
Published	2019-04-30
URL	https://arxiv.org/abs/1905.04994v2
PDF	https://arxiv.org/pdf/1905.04994v2.pdf
PWC	https://paperswithcode.com/paper/190504994
Repo
Framework

Towards Structured Evaluation of Deep Neural Network Supervisors


Title	Towards Structured Evaluation of Deep Neural Network Supervisors
Authors	Jens Henriksson, Christian Berger, Markus Borg, Lars Tornberg, Cristofer Englund, Sankar Raman Sathyamoorthy, Stig Ursing
Abstract	Deep Neural Networks (DNN) have improved the quality of several non-safety related products in the past years. However, before DNNs should be deployed to safety-critical applications, their robustness needs to be systematically analyzed. A common challenge for DNNs occurs when input is dissimilar to the training set, which might lead to high confidence predictions despite proper knowledge of the input. Several previous studies have proposed to complement DNNs with a supervisor that detects when inputs are outside the scope of the network. Most of these supervisors, however, are developed and tested for a selected scenario using a specific performance metric. In this work, we emphasize the need to assess and compare the performance of supervisors in a structured way. We present a framework constituted by four datasets organized in six test cases combined with seven evaluation metrics. The test cases provide varying complexity and include data from publicly available sources as well as a novel dataset consisting of images from simulated driving scenarios. The latter we plan to make publicly available. Our framework can be used to support DNN supervisor evaluation, which in turn could be used to motive development, validation, and deployment of DNNs in safety-critical applications.
Tasks
Published	2019-03-04
URL	http://arxiv.org/abs/1903.01263v2
PDF	http://arxiv.org/pdf/1903.01263v2.pdf
PWC	https://paperswithcode.com/paper/towards-structured-evaluation-of-deep-neural
Repo
Framework

Response to NITRD, NCO, NSF Request for Information on “Update to the 2016 National Artificial Intelligence Research and Development Strategic Plan”


Title	Response to NITRD, NCO, NSF Request for Information on “Update to the 2016 National Artificial Intelligence Research and Development Strategic Plan”
Authors	J. Amundson, J. Annis, C. Avestruz, D. Bowring, J. Caldeira, G. Cerati, C. Chang, S. Dodelson, D. Elvira, A. Farahi, K. Genser, L. Gray, O. Gutsche, P. Harris, J. Kinney, J. B. Kowalkowski, R. Kutschke, S. Mrenna, B. Nord, A. Para, K. Pedro, G. N. Perdue, A. Scheinker, P. Spentzouris, J. St. John, N. Tran, S. Trivedi, L. Trouille, W. L. K. Wu, C. R. Bom
Abstract	We present a response to the 2018 Request for Information (RFI) from the NITRD, NCO, NSF regarding the “Update to the 2016 National Artificial Intelligence Research and Development Strategic Plan.” Through this document, we provide a response to the question of whether and how the National Artificial Intelligence Research and Development Strategic Plan (NAIRDSP) should be updated from the perspective of Fermilab, America’s premier national laboratory for High Energy Physics (HEP). We believe the NAIRDSP should be extended in light of the rapid pace of development and innovation in the field of Artificial Intelligence (AI) since 2016, and present our recommendations below. AI has profoundly impacted many areas of human life, promising to dramatically reshape society — e.g., economy, education, science — in the coming years. We are still early in this process. It is critical to invest now in this technology to ensure it is safe and deployed ethically. Science and society both have a strong need for accuracy, efficiency, transparency, and accountability in algorithms, making investments in scientific AI particularly valuable. Thus far the US has been a leader in AI technologies, and we believe as a national Laboratory it is crucial to help maintain and extend this leadership. Moreover, investments in AI will be important for maintaining US leadership in the physical sciences.
Tasks
Published	2019-11-05
URL	https://arxiv.org/abs/1911.05796v1
PDF	https://arxiv.org/pdf/1911.05796v1.pdf
PWC	https://paperswithcode.com/paper/response-to-nitrd-nco-nsf-request-for
Repo
Framework

Task Decomposition for Iterative Learning Model Predictive Control


Title	Task Decomposition for Iterative Learning Model Predictive Control
Authors	Charlott Vallon, Francesco Borrelli
Abstract	A task decomposition method for iterative learning model predictive control is presented. We consider a constrained nonlinear dynamical system and assume the availability of state-input pair datasets which solve a task T1. Our objective is to find a feasible model predictive control policy for a second task, T2, using stored data from T1. Our approach applies to tasks T2 which are composed of subtasks contained in T1. In this paper we propose a formal definition of subtasks and the task decomposition problem, and provide proofs of feasibility and iteration cost improvement over simple initializations. We demonstrate the effectiveness of the proposed method on autonomous racing and robotic manipulation experiments.
Tasks	Transfer Learning
Published	2019-03-16
URL	https://arxiv.org/abs/1903.07003v4
PDF	https://arxiv.org/pdf/1903.07003v4.pdf
PWC	https://paperswithcode.com/paper/model-based-task-transfer-learning
Repo
Framework

Data-Driven Microstructure Property Relations


Title	Data-Driven Microstructure Property Relations
Authors	Julian Lißner, Felix Fritzen
Abstract	An image based prediction of the effective heat conductivity for highly heterogeneous microstructured materials is presented. The synthetic materials under consideration show different inclusion morphology, orientation, volume fraction and topology. The prediction of the effective property is made exclusively based on image data with the main emphasis being put on the 2-point spatial correlation function. This task is implemented using both unsupervised and supervised machine learning methods. First, a snapshot proper orthogonal decomposition (POD) is used to analyze big sets of random microstructures and thereafter compress significant characteristics of the microstructure into a low-dimensional feature vector. In order to manage the related amount of data and computations, three different incremental snapshot POD methods are proposed. In the second step, the obtained feature vector is used to predict the effective material property by using feed forward neural networks. Numerical examples regarding the incremental basis identification and the prediction accuracy of the approach are presented. A Python code illustrating the application of the surrogate is freely available.
Tasks
Published	2019-03-26
URL	http://arxiv.org/abs/1903.10841v2
PDF	http://arxiv.org/pdf/1903.10841v2.pdf
PWC	https://paperswithcode.com/paper/data-driven-microstructure-property-relations
Repo
Framework

Recurrent Convolution for Compact and Cost-Adjustable Neural Networks: An Empirical Study


Title	Recurrent Convolution for Compact and Cost-Adjustable Neural Networks: An Empirical Study
Authors	Zhendong Zhang, Cheolkon Jung
Abstract	Recurrent convolution (RC) shares the same convolutional kernels and unrolls them multiple steps, which is originally proposed to model time-space signals. We argue that RC can be viewed as a model compression strategy for deep convolutional neural networks. RC reduces the redundancy across layers. However, the performance of an RC network is not satisfactory if we directly unroll the same kernels multiple steps. We propose a simple yet effective variant which improves the RC networks: the batch normalization layers of an RC module are learned independently (not shared) for different unrolling steps. Moreover, we verify that RC can perform cost-adjustable inference which is achieved by varying its unrolling steps. We learn double independent BN layers for cost-adjustable RC networks, i.e. independent w.r.t both the unrolling steps of current cell and upstream cell. We provide insights on why the proposed method works successfully. Experiments on both image classification and image denoise demonstrate the effectiveness of our method.
Tasks	Image Classification, Model Compression
Published	2019-02-26
URL	http://arxiv.org/abs/1902.09809v1
PDF	http://arxiv.org/pdf/1902.09809v1.pdf
PWC	https://paperswithcode.com/paper/recurrent-convolution-for-compact-and-cost
Repo
Framework

A Game-Theoretic Approach to Adversarial Linear Support Vector Classification


Title	A Game-Theoretic Approach to Adversarial Linear Support Vector Classification
Authors	Farhad Farokhi
Abstract	In this paper, we employ a game-theoretic model to analyze the interaction between an adversary and a classifier. There are two classes (i.e., positive and negative classes) to which data points can belong. The adversary is interested in maximizing the probability of miss-detection for the positive class (i.e., false negative probability). The adversary however does not want to significantly modify the data point so that it still maintains favourable traits of the original class. The classifier, on the other hand, is interested in maximizing the probability of correct detection for the positive class (i.e., true positive probability) subject to a lower-bound on the probability of correct detection for the negative class (i.e., true negative probability). For conditionally Gaussian data points (conditioned on the class) and linear support vector machine classifiers, we rewrite the optimization problems of the adversary and the classifier as convex optimization problems and use best response dynamics to learn an equilibrium of the game. This results in computing a linear support vector machine classifier that is robust against adversarial input manipulations. We illustrate the framework on a synthetic dataset and a public Cardiovascular Disease dataset.
Tasks
Published	2019-06-24
URL	https://arxiv.org/abs/1906.09721v1
PDF	https://arxiv.org/pdf/1906.09721v1.pdf
PWC	https://paperswithcode.com/paper/a-game-theoretic-approach-to-adversarial
Repo
Framework

Basic Principles of Clustering Methods


Title	Basic Principles of Clustering Methods
Authors	Alexander Jung, Ivan Baranov
Abstract	Clustering methods group a set of data points into a few coherent groups or clusters of similar data points. As an example, consider clustering pixels in an image (or video) if they belong to the same object. Different clustering methods are obtained by using different notions of similarity and different representations of data points.
Tasks
Published	2019-11-18
URL	https://arxiv.org/abs/1911.07891v2
PDF	https://arxiv.org/pdf/1911.07891v2.pdf
PWC	https://paperswithcode.com/paper/basic-principles-of-clustering-methods
Repo
Framework

Estimation of Absolute States of Human Skeletal Muscle via Standard B-Mode Ultrasound Imaging and Deep Convolutional Neural Networks


Title	Estimation of Absolute States of Human Skeletal Muscle via Standard B-Mode Ultrasound Imaging and Deep Convolutional Neural Networks
Authors	Ryan J. Cunningham, Ian D. Loram
Abstract	Objective: To test automated in vivo estimation of active and passive skeletal muscle states using ultrasonic imaging. Background: Current technology (electromyography, dynamometry, shear wave imaging) provides no general, non-invasive method for online estimation of skeletal intramuscular states. Ultrasound (US) allows non-invasive imaging of muscle, yet current computational approaches have never achieved simultaneous extraction nor generalisation of independently varying, active and passive states. We use deep learning to investigate the generalizable content of 2D US muscle images. Method: US data synchronized with electromyography of the calf muscles, with measures of joint moment/angle were recorded from 32 healthy participants (7 female, ages: 27.5, 19-65). We extracted a region of interest of medial gastrocnemius and soleus using our prior developed accurate segmentation algorithm. From the segmented images, a deep convolutional neural network was trained to predict three absolute, drift-free, components of the neurobiomechanical state (activity, joint angle, joint moment) during experimentally designed, simultaneous, independent variation of passive (joint angle) and active (electromyography) inputs. Results: For all 32 held-out participants (16-fold cross-validation) the ankle joint angle, electromyography, and joint moment were estimated to accuracy 55+-8%, 57+-11%, and 46+-9% respectively. Significance: With 2D US imaging, deep neural networks can encode in generalizable form, the activity-length-tension state relationship of muscle. Observation only, low power, 2D US imaging can provide a new category of technology for non-invasive estimation of neural output, length and tension in skeletal muscle. This proof of principle has value for personalised muscle diagnosis in pain, injury, neurological conditions, neuropathies, myopathies and ageing.
Tasks
Published	2019-07-02
URL	https://arxiv.org/abs/1907.01649v1
PDF	https://arxiv.org/pdf/1907.01649v1.pdf
PWC	https://paperswithcode.com/paper/estimation-of-absolute-states-of-human
Repo
Framework

Optimizing the Linear Fascicle Evaluation Algorithm for Multi-Core and Many-Core Systems


Title	Optimizing the Linear Fascicle Evaluation Algorithm for Multi-Core and Many-Core Systems
Authors	Karan Aggarwal, Uday Bondhugula
Abstract	Sparse matrix-vector multiplication (SpMV) operations are commonly used in various scientific applications. The performance of the SpMV operation often depends on exploiting regularity patterns in the matrix. Various representations have been proposed to minimize the memory bandwidth bottleneck arising from the irregular memory access pattern involved. Among recent representation techniques, tensor decomposition is a popular one used for very large but sparse matrices. Post sparse-tensor decomposition, the new representation involves indirect accesses, making it challenging to optimize for multi-cores and GPUs. Computational neuroscience algorithms often involve sparse datasets while still performing long-running computations on them. The LiFE application is a popular neuroscience algorithm used for pruning brain connectivity graphs. The datasets employed herein involve the Sparse Tucker Decomposition (STD), a widely used tensor decomposition method. Using this decomposition leads to irregular array references, making it very difficult to optimize for both CPUs and GPUs. Recent codes of the LiFE algorithm show that its SpMV operations are the key bottleneck for performance and scaling. In this work, we first propose target-independent optimizations to optimize these SpMV operations, followed by target-dependent optimizations for CPU and GPU systems. The target-independent techniques include: (1) standard compiler optimizations, (2) data restructuring methods, and (3) methods to partition computations among threads. Then we present the optimizations for CPUs and GPUs to exploit platform-specific speed. Our highly optimized CPU code obtain a speedup of 27.12x over the original sequential CPU code running on 16-core Intel Xeon (Skylake-based) system, and our optimized GPU code achieves a speedup of 5.2x over a reference optimized GPU code version on NVIDIA’s GeForce RTX 2080 Ti GPU.
Tasks
Published	2019-05-14
URL	https://arxiv.org/abs/1905.06234v2
PDF	https://arxiv.org/pdf/1905.06234v2.pdf
PWC	https://paperswithcode.com/paper/optimizing-the-linear-fascicle-evaluation
Repo
Framework

A Novel User Representation Paradigm for Making Personalized Candidate Retrieval


Title	A Novel User Representation Paradigm for Making Personalized Candidate Retrieval
Authors	Zheng Liu, Yu Xing, Jianxun Lian, Defu Lian, Ziyao Li, Xing Xie
Abstract	Candidate retrieval is a fundamental issue in recommendation system. Given user’s recommendation request, relevant candidates need to be retrieved in realtime for subsequent ranking operations. Considering that the retrieval operation is conducted over considerable items, it has to be both precise and scalable so that high-quality candidates can be acquired within tolerable latency. Unfortunately, conventional methods would trade off precision for high running efficiency, which leads to inferior retrieval quality. In contrast, those deep learning-based approaches can be highly accurate in identifying relevant items; yet, they are unsuitable for candidate retrieval due to their inherent limitation on scalability. In this work, a novel framework is proposed to address the above challenges. The underlying intuition is to rely on a well-trained ranking model for the supervision of an efficient retrieval model, such that it will unify the scalability and precision as a whole. We have implemented our conceptual framework and made comprehensive evaluation for it, where promising results are achieved against representative baselines. Our work is undergoing a anonymous review, and it will soon be released after the notification. If you’re also interested in this problem, please feel free to contact us.
Tasks	Metric Learning
Published	2019-07-15
URL	https://arxiv.org/abs/1907.06323v2
PDF	https://arxiv.org/pdf/1907.06323v2.pdf
PWC	https://paperswithcode.com/paper/a-novel-user-representation-paradigm-for
Repo
Framework

Meta-Path Constrained Random Walk Inference for Large-Scale Heterogeneous Information Networks


Title	Meta-Path Constrained Random Walk Inference for Large-Scale Heterogeneous Information Networks
Authors	Chenguang Wang
Abstract	Heterogeneous information network (HIN) has shown its power of modeling real world data as a multi-typed entity-relation graph. Meta-path is the key contributor to this power since it enables inference by capturing the proximities between entities via rich semantic links. Previous HIN studies ask users to provide either 1) the meta-path(s) directly or 2) biased examples to generate the meta-path(s). However, lots of HINs (e.g., YAGO2 and Freebase) have rich schema consisting of a sophisticated and large number of types of entities and relations. It is impractical for users to provide the meta-path(s) to support the large scale inference, and biased examples will result in incorrect meta-path based inference, thus limit the power of the meta-path. In this paper, we propose a meta-path constrained inference framework to further release the ability of the meta-path, by efficiently learning the HIN inference patterns via a carefully designed tree structure; and performing unbiased random walk inference with little user guidance. The experiment results on YAGO2 and DBLP datasets show the state-of-the-art performance of the meta-path constrained inference framework.
Tasks
Published	2019-12-02
URL	https://arxiv.org/abs/1912.00634v1
PDF	https://arxiv.org/pdf/1912.00634v1.pdf
PWC	https://paperswithcode.com/paper/meta-path-constrained-random-walk-inference
Repo
Framework