Paper Group ANR 478
Fast Eigenspace Approximation using Random Signals. Matching while Learning. Optimization on Submanifolds of Convolution Kernels in CNNs. Image Resolution Enhancement by Using Interpolation Followed by Iterative Back Projection. SelQA: A New Benchmark for Selection-based Question Answering. Aligning Coordinated Text Streams through Burst Informatio …
Fast Eigenspace Approximation using Random Signals
| Title | Fast Eigenspace Approximation using Random Signals |
| Authors | Johan Paratte, Lionel Martin |
| Abstract | We focus in this work on the estimation of the first $k$ eigenvectors of any graph Laplacian using filtering of Gaussian random signals. We prove that we only need $k$ such signals to be able to exactly recover as many of the smallest eigenvectors, regardless of the number of nodes in the graph. In addition, we address key issues in implementing the theoretical concepts in practice using accurate approximated methods. We also propose fast algorithms both for eigenspace approximation and for the determination of the $k$th smallest eigenvalue $\lambda_k$. The latter proves to be extremely efficient under the assumption of locally uniform distribution of the eigenvalue over the spectrum. Finally, we present experiments which show the validity of our method in practice and compare it to state-of-the-art methods for clustering and visualization both on synthetic small-scale datasets and larger real-world problems of millions of nodes. We show that our method allows a better scaling with the number of nodes than all previous methods while achieving an almost perfect reconstruction of the eigenspace formed by the first $k$ eigenvectors. |
| Tasks | |
| Published | 2016-11-03 |
| URL | http://arxiv.org/abs/1611.00938v2 |
| http://arxiv.org/pdf/1611.00938v2.pdf | |
| PWC | https://paperswithcode.com/paper/fast-eigenspace-approximation-using-random |
| Repo | |
| Framework | |
Matching while Learning
| Title | Matching while Learning |
| Authors | Ramesh Johari, Vijay Kamble, Yash Kanoria |
| Abstract | We consider the problem faced by a service platform that needs to match supply with demand, but also to learn attributes of new arrivals in order to match them better in the future. We introduce a benchmark model with heterogeneous workers and jobs that arrive over time. Job types are known to the platform, but worker types are unknown and must be learned by observing match outcomes. Workers depart after performing a certain number of jobs. The payoff from a match depends on the pair of types and the goal is to maximize the steady-state rate of accumulation of payoff. Our main contribution is a complete characterization of the structure of the optimal policy in the limit that each worker performs many jobs. The platform faces a trade-off for each worker between myopically maximizing payoffs (exploitation) and learning the type of the worker (\emph{exploration}). This creates a multitude of multi-armed bandit problems, one for each worker, coupled together by the constraint on the availability of jobs of different types (capacity constraints). We find that the platform should estimate a shadow price for each job type, and use the payoffs adjusted by these prices, first, to determine its learning goals and then, for each worker, (i) to balance learning with payoffs during the “exploration phase”, and (ii) to myopically match after it has achieved its learning goals during the “exploitation phase.” |
| Tasks | |
| Published | 2016-03-15 |
| URL | https://arxiv.org/abs/1603.04549v5 |
| https://arxiv.org/pdf/1603.04549v5.pdf | |
| PWC | https://paperswithcode.com/paper/matching-while-learning |
| Repo | |
| Framework | |
Optimization on Submanifolds of Convolution Kernels in CNNs
| Title | Optimization on Submanifolds of Convolution Kernels in CNNs |
| Authors | Mete Ozay, Takayuki Okatani |
| Abstract | Kernel normalization methods have been employed to improve robustness of optimization methods to reparametrization of convolution kernels, covariate shift, and to accelerate training of Convolutional Neural Networks (CNNs). However, our understanding of theoretical properties of these methods has lagged behind their success in applications. We develop a geometric framework to elucidate underlying mechanisms of a diverse range of kernel normalization methods. Our framework enables us to expound and identify geometry of space of normalized kernels. We analyze and delineate how state-of-the-art kernel normalization methods affect the geometry of search spaces of the stochastic gradient descent (SGD) algorithms in CNNs. Following our theoretical results, we propose a SGD algorithm with assurance of almost sure convergence of the methods to a solution at single minimum of classification loss of CNNs. Experimental results show that the proposed method achieves state-of-the-art performance for major image classification benchmarks with CNNs. |
| Tasks | Image Classification |
| Published | 2016-10-22 |
| URL | http://arxiv.org/abs/1610.07008v1 |
| http://arxiv.org/pdf/1610.07008v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimization-on-submanifolds-of-convolution |
| Repo | |
| Framework | |
Image Resolution Enhancement by Using Interpolation Followed by Iterative Back Projection
| Title | Image Resolution Enhancement by Using Interpolation Followed by Iterative Back Projection |
| Authors | Pejman Rasti, Hasan Demirel, Gholamreza Anbarjafari |
| Abstract | In this paper, we propose a new super resolution technique based on the interpolation followed by registering them using iterative back projection (IBP). Low resolution images are being interpolated and then the interpolated images are being registered in order to generate a sharper high resolution image. The proposed technique has been tested on Lena, Elaine, Pepper, and Baboon. The quantitative peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) results as well as the visual results show the superiority of the proposed technique over the conventional and state-of-art image super resolution techniques. For Lena’s image, the PSNR is 6.52 dB higher than the bicubic interpolation. |
| Tasks | Image Super-Resolution, Super-Resolution |
| Published | 2016-01-03 |
| URL | http://arxiv.org/abs/1601.00260v1 |
| http://arxiv.org/pdf/1601.00260v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-resolution-enhancement-by-using |
| Repo | |
| Framework | |
SelQA: A New Benchmark for Selection-based Question Answering
| Title | SelQA: A New Benchmark for Selection-based Question Answering |
| Authors | Tomasz Jurczyk, Michael Zhai, Jinho D. Choi |
| Abstract | This paper presents a new selection-based question answering dataset, SelQA. The dataset consists of questions generated through crowdsourcing and sentence length answers that are drawn from the ten most prevalent topics in the English Wikipedia. We introduce a corpus annotation scheme that enhances the generation of large, diverse, and challenging datasets by explicitly aiming to reduce word co-occurrences between the question and answers. Our annotation scheme is composed of a series of crowdsourcing tasks with a view to more effectively utilize crowdsourcing in the creation of question answering datasets in various domains. Several systems are compared on the tasks of answer sentence selection and answer triggering, providing strong baseline results for future work to improve upon. |
| Tasks | Question Answering |
| Published | 2016-06-27 |
| URL | http://arxiv.org/abs/1606.08513v3 |
| http://arxiv.org/pdf/1606.08513v3.pdf | |
| PWC | https://paperswithcode.com/paper/selqa-a-new-benchmark-for-selection-based |
| Repo | |
| Framework | |
Aligning Coordinated Text Streams through Burst Information Network Construction and Decipherment
| Title | Aligning Coordinated Text Streams through Burst Information Network Construction and Decipherment |
| Authors | Tao Ge, Qing Dou, Xiaoman Pan, Heng Ji, Lei Cui, Baobao Chang, Zhifang Sui, Ming Zhou |
| Abstract | Aligning coordinated text streams from multiple sources and multiple languages has opened many new research venues on cross-lingual knowledge discovery. In this paper we aim to advance state-of-the-art by: (1). extending coarse-grained topic-level knowledge mining to fine-grained information units such as entities and events; (2). following a novel Data-to-Network-to-Knowledge (D2N2K) paradigm to construct and utilize network structures to capture and propagate reliable evidence. We introduce a novel Burst Information Network (BINet) representation that can display the most important information and illustrate the connections among bursty entities, events and keywords in the corpus. We propose an effective approach to construct and decipher BINets, incorporating novel criteria based on multi-dimensional clues from pronunciation, translation, burst, neighbor and graph topological structure. The experimental results on Chinese and English coordinated text streams show that our approach can accurately decipher the nodes with high confidence in the BINets and that the algorithm can be efficiently run in parallel, which makes it possible to apply it to huge amounts of streaming data for never-ending language and information decipherment. |
| Tasks | |
| Published | 2016-09-27 |
| URL | http://arxiv.org/abs/1609.08237v1 |
| http://arxiv.org/pdf/1609.08237v1.pdf | |
| PWC | https://paperswithcode.com/paper/aligning-coordinated-text-streams-through |
| Repo | |
| Framework | |
Learning to Hash with Binary Deep Neural Network
| Title | Learning to Hash with Binary Deep Neural Network |
| Authors | Thanh-Toan Do, Anh-Dzung Doan, Ngai-Man Cheung |
| Abstract | This work proposes deep network models and learning algorithms for unsupervised and supervised binary hashing. Our novel network design constrains one hidden layer to directly output the binary codes. This addresses a challenging issue in some previous works: optimizing non-smooth objective functions due to binarization. Moreover, we incorporate independence and balance properties in the direct and strict forms in the learning. Furthermore, we include similarity preserving property in our objective function. Our resulting optimization with these binary, independence, and balance constraints is difficult to solve. We propose to attack it with alternating optimization and careful relaxation. Experimental results on three benchmark datasets show that our proposed methods compare favorably with the state of the art. |
| Tasks | |
| Published | 2016-07-18 |
| URL | http://arxiv.org/abs/1607.05140v1 |
| http://arxiv.org/pdf/1607.05140v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-hash-with-binary-deep-neural |
| Repo | |
| Framework | |
Energetics of the brain and AI
| Title | Energetics of the brain and AI |
| Authors | Anders Sandberg |
| Abstract | Does the energy requirements for the human brain give energy constraints that give reason to doubt the feasibility of artificial intelligence? This report will review some relevant estimates of brain bioenergetics and analyze some of the methods of estimating brain emulation energy requirements. Turning to AI, there are reasons to believe the energy requirements for de novo AI to have little correlation with brain (emulation) energy requirements since cost could depend merely of the cost of processing higher-level representations rather than billions of neural firings. Unless one thinks the human way of thinking is the most optimal or most easily implementable way of achieving software intelligence, we should expect de novo AI to make use of different, potentially very compressed and fast, processes. |
| Tasks | |
| Published | 2016-02-12 |
| URL | http://arxiv.org/abs/1602.04019v1 |
| http://arxiv.org/pdf/1602.04019v1.pdf | |
| PWC | https://paperswithcode.com/paper/energetics-of-the-brain-and-ai |
| Repo | |
| Framework | |
Scout-It: Interior tomography using modified scout acquisition
| Title | Scout-It: Interior tomography using modified scout acquisition |
| Authors | Kriti Sen Sharma |
| Abstract | Global scout views have been previously used to reduce interior reconstruction artifacts in high-resolution micro-CT and C-arm systems. However these methods cannot be directly used in the all-important domain of clinical CT. This is because when the CT scan is truncated, the scout views are also truncated. However many cases of truncation in clinical CT involve partial truncation, where the anterio-posterior (AP) scout is truncated, but the medio-lateral (ML) scout is non-truncated. In this paper, we show that in such cases of partially truncated CT scans, a modified configuration may be used to acquire non-truncated AP scout view, and ultimately allow for highly accurate interior reconstruction. |
| Tasks | |
| Published | 2016-08-14 |
| URL | http://arxiv.org/abs/1608.04059v1 |
| http://arxiv.org/pdf/1608.04059v1.pdf | |
| PWC | https://paperswithcode.com/paper/scout-it-interior-tomography-using-modified |
| Repo | |
| Framework | |
Network Volume Anomaly Detection and Identification in Large-scale Networks based on Online Time-structured Traffic Tensor Tracking
| Title | Network Volume Anomaly Detection and Identification in Large-scale Networks based on Online Time-structured Traffic Tensor Tracking |
| Authors | Hiroyuki Kasai, Wolfgang Kellerer, Martin Kleinsteuber |
| Abstract | This paper addresses network anomography, that is, the problem of inferring network-level anomalies from indirect link measurements. This problem is cast as a low-rank subspace tracking problem for normal flows under incomplete observations, and an outlier detection problem for abnormal flows. Since traffic data is large-scale time-structured data accompanied with noise and outliers under partial observations, an efficient modeling method is essential. To this end, this paper proposes an online subspace tracking of a Hankelized time-structured traffic tensor for normal flows based on the Candecomp/PARAFAC decomposition exploiting the recursive least squares (RLS) algorithm. We estimate abnormal flows as outlier sparse flows via sparsity maximization in the underlying under-constrained linear-inverse problem. A major advantage is that our algorithm estimates normal flows by low-dimensional matrices with time-directional features as well as the spatial correlation of multiple links without using the past observed measurements and the past model parameters. Extensive numerical evaluations show that the proposed algorithm achieves faster convergence per iteration of model approximation, and better volume anomaly detection performance compared to state-of-the-art algorithms. |
| Tasks | Anomaly Detection, Outlier Detection |
| Published | 2016-08-19 |
| URL | http://arxiv.org/abs/1608.05493v1 |
| http://arxiv.org/pdf/1608.05493v1.pdf | |
| PWC | https://paperswithcode.com/paper/network-volume-anomaly-detection-and |
| Repo | |
| Framework | |
Proceedings Fifteenth Conference on Theoretical Aspects of Rationality and Knowledge
| Title | Proceedings Fifteenth Conference on Theoretical Aspects of Rationality and Knowledge |
| Authors | R Ramanujam |
| Abstract | The 15th Conference on Theoretical Aspects of Rationality and Knowledge (TARK) took place in Carnegie Mellon University, Pittsburgh, USA from June 4 to 6, 2015. The mission of the TARK conferences is to bring together researchers from a wide variety of fields, including Artificial Intelligence, Cryptography, Distributed Computing, Economics and Game Theory, Linguistics, Philosophy, and Psychology, in order to further our understanding of interdisciplinary issues involving reasoning about rationality and knowledge. These proceedings consist of a subset of the papers / abstracts presented at the TARK conference. |
| Tasks | |
| Published | 2016-06-23 |
| URL | http://arxiv.org/abs/1606.07295v1 |
| http://arxiv.org/pdf/1606.07295v1.pdf | |
| PWC | https://paperswithcode.com/paper/proceedings-fifteenth-conference-on |
| Repo | |
| Framework | |
Structured Feature Learning for Pose Estimation
| Title | Structured Feature Learning for Pose Estimation |
| Authors | Xiao Chu, Wanli Ouyang, Hongsheng Li, Xiaogang Wang |
| Abstract | In this paper, we propose a structured feature learning framework to reason the correlations among body joints at the feature level in human pose estimation. Different from existing approaches of modelling structures on score maps or predicted labels, feature maps preserve substantially richer descriptions of body joints. The relationships between feature maps of joints are captured with the introduced geometrical transform kernels, which can be easily implemented with a convolution layer. Features and their relationships are jointly learned in an end-to-end learning system. A bi-directional tree structured model is proposed, so that the feature channels at a body joint can well receive information from other joints. The proposed framework improves feature learning substantially. With very simple post processing, it reaches the best mean PCP on the LSP and FLIC datasets. Compared with the baseline of learning features at each joint separately with ConvNet, the mean PCP has been improved by 18% on FLIC. The code is released to the public. |
| Tasks | Pose Estimation |
| Published | 2016-03-30 |
| URL | http://arxiv.org/abs/1603.09065v1 |
| http://arxiv.org/pdf/1603.09065v1.pdf | |
| PWC | https://paperswithcode.com/paper/structured-feature-learning-for-pose |
| Repo | |
| Framework | |
X-CNN: Cross-modal Convolutional Neural Networks for Sparse Datasets
| Title | X-CNN: Cross-modal Convolutional Neural Networks for Sparse Datasets |
| Authors | Petar Veličković, Duo Wang, Nicholas D. Lane, Pietro Liò |
| Abstract | In this paper we propose cross-modal convolutional neural networks (X-CNNs), a novel biologically inspired type of CNN architectures, treating gradient descent-specialised CNNs as individual units of processing in a larger-scale network topology, while allowing for unconstrained information flow and/or weight sharing between analogous hidden layers of the network—thus generalising the already well-established concept of neural network ensembles (where information typically may flow only between the output layers of the individual networks). The constituent networks are individually designed to learn the output function on their own subset of the input data, after which cross-connections between them are introduced after each pooling operation to periodically allow for information exchange between them. This injection of knowledge into a model (by prior partition of the input data through domain knowledge or unsupervised methods) is expected to yield greatest returns in sparse data environments, which are typically less suitable for training CNNs. For evaluation purposes, we have compared a standard four-layer CNN as well as a sophisticated FitNet4 architecture against their cross-modal variants on the CIFAR-10 and CIFAR-100 datasets with differing percentages of the training data being removed, and find that at lower levels of data availability, the X-CNNs significantly outperform their baselines (typically providing a 2–6% benefit, depending on the dataset size and whether data augmentation is used), while still maintaining an edge on all of the full dataset tests. |
| Tasks | Data Augmentation |
| Published | 2016-10-01 |
| URL | http://arxiv.org/abs/1610.00163v2 |
| http://arxiv.org/pdf/1610.00163v2.pdf | |
| PWC | https://paperswithcode.com/paper/x-cnn-cross-modal-convolutional-neural |
| Repo | |
| Framework | |
Universum Learning for SVM Regression
| Title | Universum Learning for SVM Regression |
| Authors | Sauptik Dhar, Vladimir Cherkassky |
| Abstract | This paper extends the idea of Universum learning [18, 19] to regression problems. We propose new Universum-SVM formulation for regression problems that incorporates a priori knowledge in the form of additional data samples. These additional data samples or Universum belong to the same application domain as the training samples, but they follow a different distribution. Several empirical comparisons are presented to illustrate the utility of the proposed approach. |
| Tasks | |
| Published | 2016-05-27 |
| URL | http://arxiv.org/abs/1605.08497v1 |
| http://arxiv.org/pdf/1605.08497v1.pdf | |
| PWC | https://paperswithcode.com/paper/universum-learning-for-svm-regression |
| Repo | |
| Framework | |
Geometry of Compositionality
| Title | Geometry of Compositionality |
| Authors | Hongyu Gong, Suma Bhat, Pramod Viswanath |
| Abstract | This paper proposes a simple test for compositionality (i.e., literal usage) of a word or phrase in a context-specific way. The test is computationally simple, relying on no external resources and only uses a set of trained word vectors. Experiments show that the proposed method is competitive with state of the art and displays high accuracy in context-specific compositionality detection of a variety of natural language phenomena (idiomaticity, sarcasm, metaphor) for different datasets in multiple languages. The key insight is to connect compositionality to a curious geometric property of word embeddings, which is of independent interest. |
| Tasks | Word Embeddings |
| Published | 2016-11-29 |
| URL | http://arxiv.org/abs/1611.09799v1 |
| http://arxiv.org/pdf/1611.09799v1.pdf | |
| PWC | https://paperswithcode.com/paper/geometry-of-compositionality |
| Repo | |
| Framework | |
