Paper Group ANR 699
Self-Net: Lifelong Learning via Continual Self-Modeling. LMap: Shape-Preserving Local Mappings for Biomedical Visualization. Curvature-based Comparison of Two Neural Networks. Automated detection and segmentation of non-mass enhancing breast tumors with dynamic contrast-enhanced magnetic resonance imaging. A Univariate Bound of Area Under ROC. Grap …
Self-Net: Lifelong Learning via Continual Self-Modeling
Title | Self-Net: Lifelong Learning via Continual Self-Modeling |
Authors | Blake Camp, Jaya Krishna Mandivarapu, Rolando Estrada |
Abstract | Learning a set of tasks over time, also known as continual learning (CL), is one of the most challenging problems in artificial intelligence. While recent approaches achieve some degree of CL in deep neural networks, they either (1) grow the network parameters linearly with the number of tasks, (2) require storing training data from previous tasks, or (3) restrict the network’s ability to learn new tasks. To address these issues, we propose a novel framework, Self-Net, that uses an autoencoder to learn a set of low-dimensional representations of the weights learned for different tasks. We demonstrate that these low-dimensional vectors can then be used to generate high-fidelity recollections of the original weights. Self-Net can incorporate new tasks over time with little retraining and with minimal loss in performance for older tasks. Our system does not require storing prior training data and its parameters grow only logarithmically with the number of tasks. We show that our technique outperforms current state-of-the-art approaches on numerous datasets—including continual versions of MNIST, CIFAR10, CIFAR100, and Atari—and we demonstrate that our method can achieve over 10X storage compression in a continual fashion. To the best of our knowledge, we are the first to use autoencoders to sequentially encode sets of network weights to enable continual learning. |
Tasks | Continual Learning |
Published | 2018-05-25 |
URL | https://arxiv.org/abs/1805.10354v3 |
https://arxiv.org/pdf/1805.10354v3.pdf | |
PWC | https://paperswithcode.com/paper/self-net-lifelong-learning-via-continual-self |
Repo | |
Framework | |
LMap: Shape-Preserving Local Mappings for Biomedical Visualization
Title | LMap: Shape-Preserving Local Mappings for Biomedical Visualization |
Authors | Saad Nadeem, Xianfeng Gu, Arie Kaufman |
Abstract | Visualization of medical organs and biological structures is a challenging task because of their complex geometry and the resultant occlusions. Global spherical and planar mapping techniques simplify the complex geometry and resolve the occlusions to aid in visualization. However, while resolving the occlusions these techniques do not preserve the geometric context, making them less suitable for mission-critical biomedical visualization tasks. In this paper, we present a shape-preserving local mapping technique for resolving occlusions locally while preserving the overall geometric context. More specifically, we present a novel visualization algorithm, LMap, for conformally parameterizing and deforming a selected local region-of-interest (ROI) on an arbitrary surface. The resultant shape-preserving local mappings help to visualize complex surfaces while preserving the overall geometric context. The algorithm is based on the robust and efficient extrinsic Ricci flow technique, and uses the dynamic Ricci flow algorithm to guarantee the existence of a local map for a selected ROI on an arbitrary surface. We show the effectiveness and efficacy of our method in three challenging use cases: (1) multimodal brain visualization, (2) optimal coverage of virtual colonoscopy centerline flythrough, and (3) molecular surface visualization. |
Tasks | |
Published | 2018-09-17 |
URL | http://arxiv.org/abs/1809.06442v2 |
http://arxiv.org/pdf/1809.06442v2.pdf | |
PWC | https://paperswithcode.com/paper/lmap-shape-preserving-local-mappings-for |
Repo | |
Framework | |
Curvature-based Comparison of Two Neural Networks
Title | Curvature-based Comparison of Two Neural Networks |
Authors | Tao Yu, Huan Long, John E. Hopcroft |
Abstract | In this paper we show the similarities and differences of two deep neural networks by comparing the manifolds composed of activation vectors in each fully connected layer of them. The main contribution of this paper includes 1) a new data generating algorithm which is crucial for determining the dimension of manifolds; 2) a systematic strategy to compare manifolds. Especially, we take Riemann curvature and sectional curvature as part of criterion, which can reflect the intrinsic geometric properties of manifolds. Some interesting results and phenomenon are given, which help in specifying the similarities and differences between the features extracted by two networks and demystifying the intrinsic mechanism of deep neural networks. |
Tasks | |
Published | 2018-01-21 |
URL | http://arxiv.org/abs/1801.06801v1 |
http://arxiv.org/pdf/1801.06801v1.pdf | |
PWC | https://paperswithcode.com/paper/curvature-based-comparison-of-two-neural |
Repo | |
Framework | |
Automated detection and segmentation of non-mass enhancing breast tumors with dynamic contrast-enhanced magnetic resonance imaging
Title | Automated detection and segmentation of non-mass enhancing breast tumors with dynamic contrast-enhanced magnetic resonance imaging |
Authors | Ignacio Alvarez Illan, Javier Ramirez, Juan M. Gorriz, Maria Adele Marino, Daly Avendaño, Thomas Helbich, Pascal Baltzer, Katja Pinker, Anke Meyer-Baese |
Abstract | Non-mass enhancing lesions (NME) constitute a diagnostic challenge in dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) of the breast. Computer Aided Diagnosis (CAD) systems provide physicians with advanced tools for analysis, assessment and evaluation that have a significant impact on the diagnostic performance. Here, we propose a new approach to address the challenge of NME detection and segmentation, taking advantage of independent component analysis (ICA) to extract data-driven dynamic lesion characterizations. A set of independent sources was obtained from DCE-MRI dataset of breast patients, and the dynamic behavior of the different tissues was described by multiple dynamic curves, together with a set of eigenimages describing the scores for each voxel. A new test image is projected onto the independent source space using the unmixing matrix, and each voxel is classified by a support vector machine (SVM) that has already been trained with manually delineated data. A solution to the high false positive rate problem is proposed by controlling the SVM hyperplane location, outperforming previously published approaches. |
Tasks | |
Published | 2018-03-12 |
URL | http://arxiv.org/abs/1803.04200v2 |
http://arxiv.org/pdf/1803.04200v2.pdf | |
PWC | https://paperswithcode.com/paper/automated-detection-and-segmentation-of-non |
Repo | |
Framework | |
A Univariate Bound of Area Under ROC
Title | A Univariate Bound of Area Under ROC |
Authors | Siwei Lyu, Yiming Ying |
Abstract | Area under ROC (AUC) is an important metric for binary classification and bipartite ranking problems. However, it is difficult to directly optimizing AUC as a learning objective, so most existing algorithms are based on optimizing a surrogate loss to AUC. One significant drawback of these surrogate losses is that they require pairwise comparisons among training data, which leads to slow running time and increasing local storage for online learning. In this work, we describe a new surrogate loss based on a reformulation of the AUC risk, which does not require pairwise comparison but rankings of the predictions. We further show that the ranking operation can be avoided, and the learning objective obtained based on this surrogate enjoys linear complexity in time and storage. We perform experiments to demonstrate the effectiveness of the online and batch algorithms for AUC optimization based on the proposed surrogate loss. |
Tasks | |
Published | 2018-04-16 |
URL | http://arxiv.org/abs/1804.05981v2 |
http://arxiv.org/pdf/1804.05981v2.pdf | |
PWC | https://paperswithcode.com/paper/a-univariate-bound-of-area-under-roc |
Repo | |
Framework | |
Graphlet Count Estimation via Convolutional Neural Networks
Title | Graphlet Count Estimation via Convolutional Neural Networks |
Authors | Xutong Liu, Yu-Zhen Janice Chen, John C. S. Lui, Konstantin Avrachenkov |
Abstract | Graphlets are defined as k-node connected induced subgraph patterns. For an undirected graph, 3-node graphlets include close triangle and open triangle. When k = 4, there are six types of graphlets, e.g., tailed-triangle and clique are two possible 4-node graphlets. The number of each graphlet, called graphlet count, is a signature which characterizes the local network structure of a given graph. Graphlet count plays a prominent role in network analysis of many fields, most notably bioinformatics and social science. However, computing exact graphlet count is inherently difficult and computational expensive because the number of graphlets grows exponentially large as the graph size and/or graphlet size k grow. To deal with this difficulty, many sampling methods were proposed to estimate graphlet count with bounded error. Nevertheless, these methods require large number of samples to be statistically reliable, which is still computationally demanding. Moreover, they have to repeat laborious counting procedure even if a new graph is similar or exactly the same as previous studied graphs. Intuitively, learning from historic graphs can make estimation more accurate and avoid many repetitive counting to reduce computational cost. Based on this idea, we propose a convolutional neural network (CNN) framework and two preprocessing techniques to estimate graphlet count. Extensive experiments on two types of random graphs and real world biochemistry graphs show that our framework can offer substantial speedup on estimating graphlet count of new graphs with high accuracy. |
Tasks | |
Published | 2018-10-07 |
URL | http://arxiv.org/abs/1810.03078v1 |
http://arxiv.org/pdf/1810.03078v1.pdf | |
PWC | https://paperswithcode.com/paper/graphlet-count-estimation-via-convolutional |
Repo | |
Framework | |
Before Name-calling: Dynamics and Triggers of Ad Hominem Fallacies in Web Argumentation
Title | Before Name-calling: Dynamics and Triggers of Ad Hominem Fallacies in Web Argumentation |
Authors | Ivan Habernal, Henning Wachsmuth, Iryna Gurevych, Benno Stein |
Abstract | Arguing without committing a fallacy is one of the main requirements of an ideal debate. But even when debating rules are strictly enforced and fallacious arguments punished, arguers often lapse into attacking the opponent by an ad hominem argument. As existing research lacks solid empirical investigation of the typology of ad hominem arguments as well as their potential causes, this paper fills this gap by (1) performing several large-scale annotation studies, (2) experimenting with various neural architectures and validating our working hypotheses, such as controversy or reasonableness, and (3) providing linguistic insights into triggers of ad hominem using explainable neural network architectures. |
Tasks | |
Published | 2018-02-19 |
URL | http://arxiv.org/abs/1802.06613v2 |
http://arxiv.org/pdf/1802.06613v2.pdf | |
PWC | https://paperswithcode.com/paper/before-name-calling-dynamics-and-triggers-of |
Repo | |
Framework | |
Investigating the Evolvability of Web Page Load Time
Title | Investigating the Evolvability of Web Page Load Time |
Authors | Brendan Cody-Kenny, Umberto Manganiello, John Farrelly, Adrian Ronayne, Eoghan Considine, Thomas McGuire, Michael O’Neill |
Abstract | Client-side Javascript execution environments (browsers) allow anonymous functions and event-based programming concepts such as callbacks. We investigate whether a mutate-and-test approach can be used to optimise web page load time in these environments. First, we characterise a web page load issue in a benchmark web page and derive performance metrics from page load event traces. We parse Javascript source code to an AST and make changes to method calls which appear in a web page load event trace. We present an operator based solely on code deletion and evaluate an existing “community-contributed” performance optimising code transform. By exploring Javascript code changes and exploiting combinations of non-destructive changes, we can optimise page load time by 41% in our benchmark web page. |
Tasks | |
Published | 2018-02-22 |
URL | http://arxiv.org/abs/1803.01683v1 |
http://arxiv.org/pdf/1803.01683v1.pdf | |
PWC | https://paperswithcode.com/paper/investigating-the-evolvability-of-web-page |
Repo | |
Framework | |
Quantum Inspired High Dimensional Conceptual Space as KID Model for Elderly Assistance
Title | Quantum Inspired High Dimensional Conceptual Space as KID Model for Elderly Assistance |
Authors | Ishwarya M S, Aswani Kumar Ch |
Abstract | In this paper, we propose a cognitive system that acquires knowledge on elderly daily activities to ensure their wellness in a smart home using a Knowledge-Information-Data (KID) model. The novel cognitive framework called high dimensional conceptual space is proposed and used as KID model. This KID model is built using geometrical framework of conceptual spaces and formal concept analysis (FCA) to overcome imprecise concept notation of conceptual space with the help of topology based FCA. By doing so, conceptual space can be represented using Hilbert space. This high dimensional conceptual space is quantum inspired in terms of its concept representation. The knowledge learnt by the KID model recognizes the daily activities of the elderly. Consequently, the model identifies the scenario on which the wellness of the elderly has to be ensured. |
Tasks | |
Published | 2018-11-19 |
URL | http://arxiv.org/abs/1811.07603v1 |
http://arxiv.org/pdf/1811.07603v1.pdf | |
PWC | https://paperswithcode.com/paper/quantum-inspired-high-dimensional-conceptual |
Repo | |
Framework | |
On the Iteration Complexity Analysis of Stochastic Primal-Dual Hybrid Gradient Approach with High Probability
Title | On the Iteration Complexity Analysis of Stochastic Primal-Dual Hybrid Gradient Approach with High Probability |
Authors | Linbo Qiao, Tianyi Lin, Qi Qin, Xicheng Lu |
Abstract | In this paper, we propose a stochastic Primal-Dual Hybrid Gradient (PDHG) approach for solving a wide spectrum of regularized stochastic minimization problems, where the regularization term is composite with a linear function. It has been recognized that solving this kind of problem is challenging since the closed-form solution of the proximal mapping associated with the regularization term is not available due to the imposed linear composition, and the per-iteration cost of computing the full gradient of the expected objective function is extremely high when the number of input data samples is considerably large. Our new approach overcomes these issues by exploring the special structure of the regularization term and sampling a few data points at each iteration. Rather than analyzing the convergence in expectation, we provide the detailed iteration complexity analysis for the cases of both uniformly and non-uniformly averaged iterates with high probability. This strongly supports the good practical performance of the proposed approach. Numerical experiments demonstrate that the efficiency of stochastic PDHG, which outperforms other competing algorithms, as expected by the high-probability convergence analysis. |
Tasks | |
Published | 2018-01-22 |
URL | http://arxiv.org/abs/1801.06934v2 |
http://arxiv.org/pdf/1801.06934v2.pdf | |
PWC | https://paperswithcode.com/paper/on-the-iteration-complexity-analysis-of |
Repo | |
Framework | |
Traceability of Deep Neural Networks
Title | Traceability of Deep Neural Networks |
Authors | Vincent Aravantinos, Frederik Diehl |
Abstract | [Context.] The success of deep learning makes its usage more and more tempting in safety-critical applications. However such applications have historical standards (e.g., DO178, ISO26262) which typically do not envision the usage of machine learning. We focus in particular on \emph{requirements traceability} of software artifacts, i.e., code modules, functions, or statements (depending on the desired granularity). [Problem.] Both code and requirements are a problem when dealing with deep neural networks: code constituting the network is not comparable to classical code; furthermore, requirements for applications where neural networks are required are typically very hard to specify: even though high-level requirements can be defined, it is very hard to make such requirements concrete enough, that one can qualify them of low-level requirements. An additional problem is that deep learning is in practice very much based on trial-and-error, which makes the final result hard to explain without the previous iterations. [Proposed solution.] We investigate which artifacts could play a similar role to code or low-level requirements in neural network development and propose various traces which one could possibly consider as a replacement for classical notions. We also propose a form of traceability (and new artifacts) in order to deal with the particular trial-and-error development process for deep learning. |
Tasks | |
Published | 2018-12-17 |
URL | https://arxiv.org/abs/1812.06744v2 |
https://arxiv.org/pdf/1812.06744v2.pdf | |
PWC | https://paperswithcode.com/paper/traceability-of-deep-neural-networks |
Repo | |
Framework | |
Word Embedding based Edit Distance
Title | Word Embedding based Edit Distance |
Authors | Yilin Niu, Chao Qiao, Hang Li, Minlie Huang |
Abstract | Text similarity calculation is a fundamental problem in natural language processing and related fields. In recent years, deep neural networks have been developed to perform the task and high performances have been achieved. The neural networks are usually trained with labeled data in supervised learning, and creation of labeled data is usually very costly. In this short paper, we address unsupervised learning for text similarity calculation. We propose a new method called Word Embedding based Edit Distance (WED), which incorporates word embedding into edit distance. Experiments on three benchmark datasets show WED outperforms state-of-the-art unsupervised methods including edit distance, TF-IDF based cosine, word embedding based cosine, Jaccard index, etc. |
Tasks | |
Published | 2018-10-25 |
URL | http://arxiv.org/abs/1810.10752v1 |
http://arxiv.org/pdf/1810.10752v1.pdf | |
PWC | https://paperswithcode.com/paper/word-embedding-based-edit-distance |
Repo | |
Framework | |
Prediction of Reynolds Stresses in High-Mach-Number Turbulent Boundary Layers using Physics-Informed Machine Learning
Title | Prediction of Reynolds Stresses in High-Mach-Number Turbulent Boundary Layers using Physics-Informed Machine Learning |
Authors | Jian-Xun Wang, Junji Huang, Lian Duan, Heng Xiao |
Abstract | Modeled Reynolds stress is a major source of model-form uncertainties in Reynolds-averaged Navier-Stokes (RANS) simulations. Recently, a physics-informed machine-learning (PIML) approach has been proposed for reconstructing the discrepancies in RANS-modeled Reynolds stresses. The merits of the PIML framework has been demonstrated in several canonical incompressible flows. However, its performance on high-Mach-number flows is still not clear. In this work we use the PIML approach to predict the discrepancies in RANS modeled Reynolds stresses in high-Mach-number flat-plate turbulent boundary layers by using an existing DNS database. Specifically, the discrepancy function is first constructed using a DNS training flow and then used to correct RANS-predicted Reynolds stresses under flow conditions different from the DNS. The machine-learning technique is shown to significantly improve RANS-modeled turbulent normal stresses, the turbulent kinetic energy, and the Reynolds-stress anisotropy. Improvements are consistently observed when different training datasets are used. Moreover, a high-dimensional visualization technique and distance metrics are used to provide a priori assessment of prediction confidence based only on RANS simulations. This study demonstrates that the PIML approach is a computationally affordable technique for improving the accuracy of RANS-modeled Reynolds stresses for high-Mach-number turbulent flows when there is a lack of experiments and high-fidelity simulations. |
Tasks | |
Published | 2018-08-19 |
URL | http://arxiv.org/abs/1808.07752v1 |
http://arxiv.org/pdf/1808.07752v1.pdf | |
PWC | https://paperswithcode.com/paper/prediction-of-reynolds-stresses-in-high-mach |
Repo | |
Framework | |
Scalable Unbalanced Optimal Transport using Generative Adversarial Networks
Title | Scalable Unbalanced Optimal Transport using Generative Adversarial Networks |
Authors | Karren D. Yang, Caroline Uhler |
Abstract | Generative adversarial networks (GANs) are an expressive class of neural generative models with tremendous success in modeling high-dimensional continuous measures. In this paper, we present a scalable method for unbalanced optimal transport (OT) based on the generative-adversarial framework. We formulate unbalanced OT as a problem of simultaneously learning a transport map and a scaling factor that push a source measure to a target measure in a cost-optimal manner. In addition, we propose an algorithm for solving this problem based on stochastic alternating gradient updates, similar in practice to GANs. We also provide theoretical justification for this formulation, showing that it is closely related to an existing static formulation by Liero et al. (2018), and perform numerical experiments demonstrating how this methodology can be applied to population modeling. |
Tasks | |
Published | 2018-10-26 |
URL | https://arxiv.org/abs/1810.11447v2 |
https://arxiv.org/pdf/1810.11447v2.pdf | |
PWC | https://paperswithcode.com/paper/scalable-unbalanced-optimal-transport-using |
Repo | |
Framework | |
A Reinforcement Learning Approach to Target Tracking in a Camera Network
Title | A Reinforcement Learning Approach to Target Tracking in a Camera Network |
Authors | Anil Sharma, Prabhat Kumar, Saket Anand, Sanjit K. Kaul |
Abstract | Target tracking in a camera network is an important task for surveillance and scene understanding. The task is challenging due to disjoint views and illumination variation in different cameras. In this direction, many graph-based methods were proposed using appearance-based features. However, the appearance information fades with high illumination variation in the different camera FOVs. We, in this paper, use spatial and temporal information as the state of the target to learn a policy that predicts the next camera given the current state. The policy is trained using Q-learning and it does not assume any information about the topology of the camera network. We will show that the policy learns the camera network topology. We demonstrate the performance of the proposed method on the NLPR MCT dataset. |
Tasks | Q-Learning, Scene Understanding |
Published | 2018-07-26 |
URL | http://arxiv.org/abs/1807.10336v2 |
http://arxiv.org/pdf/1807.10336v2.pdf | |
PWC | https://paperswithcode.com/paper/a-reinforcement-learning-approach-to-target |
Repo | |
Framework | |