Paper Group ANR 641
Efficient Anomaly Detection via Matrix Sketching. Distant Supervision for Relation Extraction with Linear Attenuation Simulation and Non-IID Relevance Embedding. A Unified Coded Deep Neural Network Training Strategy Based on Generalized PolyDot Codes for Matrix Multiplication. Troy: Give Attention to Saliency and for Saliency. The Web as a Knowledg …
Efficient Anomaly Detection via Matrix Sketching
| Title | Efficient Anomaly Detection via Matrix Sketching |
| Authors | Vatsal Sharan, Parikshit Gopalan, Udi Wieder |
| Abstract | We consider the problem of finding anomalies in high-dimensional data using popular PCA based anomaly scores. The naive algorithms for computing these scores explicitly compute the PCA of the covariance matrix which uses space quadratic in the dimensionality of the data. We give the first streaming algorithms that use space that is linear or sublinear in the dimension. We prove general results showing that \emph{any} sketch of a matrix that satisfies a certain operator norm guarantee can be used to approximate these scores. We instantiate these results with powerful matrix sketching techniques such as Frequent Directions and random projections to derive efficient and practical algorithms for these problems, which we validate over real-world data sets. Our main technical contribution is to prove matrix perturbation inequalities for operators arising in the computation of these measures. |
| Tasks | Anomaly Detection |
| Published | 2018-04-09 |
| URL | http://arxiv.org/abs/1804.03065v2 |
| http://arxiv.org/pdf/1804.03065v2.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-anomaly-detection-via-matrix |
| Repo | |
| Framework | |
Distant Supervision for Relation Extraction with Linear Attenuation Simulation and Non-IID Relevance Embedding
| Title | Distant Supervision for Relation Extraction with Linear Attenuation Simulation and Non-IID Relevance Embedding |
| Authors | Changsen Yuan, Heyan Huang, Chong Feng, Xiao Liu, Xiaochi Wei |
| Abstract | Distant supervision for relation extraction is an efficient method to reduce labor costs and has been widely used to seek novel relational facts in large corpora, which can be identified as a multi-instance multi-label problem. However, existing distant supervision methods suffer from selecting important words in the sentence and extracting valid sentences in the bag. Towards this end, we propose a novel approach to address these problems in this paper. Firstly, we propose a linear attenuation simulation to reflect the importance of words in the sentence with respect to the distances between entities and words. Secondly, we propose a non-independent and identically distributed (non-IID) relevance embedding to capture the relevance of sentences in the bag. Our method can not only capture complex information of words about hidden relations, but also express the mutual information of instances in the bag. Extensive experiments on a benchmark dataset have well-validated the effectiveness of the proposed method. |
| Tasks | Relation Extraction |
| Published | 2018-12-22 |
| URL | http://arxiv.org/abs/1812.09516v1 |
| http://arxiv.org/pdf/1812.09516v1.pdf | |
| PWC | https://paperswithcode.com/paper/distant-supervision-for-relation-extraction-2 |
| Repo | |
| Framework | |
A Unified Coded Deep Neural Network Training Strategy Based on Generalized PolyDot Codes for Matrix Multiplication
| Title | A Unified Coded Deep Neural Network Training Strategy Based on Generalized PolyDot Codes for Matrix Multiplication |
| Authors | Sanghamitra Dutta, Ziqian Bai, Haewon Jeong, Tze Meng Low, Pulkit Grover |
| Abstract | This paper has two contributions. First, we propose a novel coded matrix multiplication technique called Generalized PolyDot codes that advances on existing methods for coded matrix multiplication under storage and communication constraints. This technique uses “garbage alignment,” i.e., aligning computations in coded computing that are not a part of the desired output. Generalized PolyDot codes bridge between Polynomial codes and MatDot codes, trading off between recovery threshold and communication costs. Second, we demonstrate that Generalized PolyDot can be used for training large Deep Neural Networks (DNNs) on unreliable nodes prone to soft-errors. This requires us to address three additional challenges: (i) prohibitively large overhead of coding the weight matrices in each layer of the DNN at each iteration; (ii) nonlinear operations during training, which are incompatible with linear coding; and (iii) not assuming presence of an error-free master node, requiring us to architect a fully decentralized implementation without any “single point of failure.” We allow all primary DNN training steps, namely, matrix multiplication, nonlinear activation, Hadamard product, and update steps as well as the encoding/decoding to be error-prone. We consider the case of mini-batch size $B=1$, as well as $B>1$, leveraging coded matrix-vector products, and matrix-matrix products respectively. The problem of DNN training under soft-errors also motivates an interesting, probabilistic error model under which a real number $(P,Q)$ MDS code is shown to correct $P-Q-1$ errors with probability $1$ as compared to $\lfloor \frac{P-Q}{2} \rfloor$ for the more conventional, adversarial error model. We also demonstrate that our proposed strategy can provide unbounded gains in error tolerance over a competing replication strategy and a preliminary MDS-code-based strategy for both these error models. |
| Tasks | |
| Published | 2018-11-27 |
| URL | http://arxiv.org/abs/1811.10751v1 |
| http://arxiv.org/pdf/1811.10751v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-unified-coded-deep-neural-network-training |
| Repo | |
| Framework | |
Troy: Give Attention to Saliency and for Saliency
| Title | Troy: Give Attention to Saliency and for Saliency |
| Authors | Pingping Zhang, Huchuan Lu, Chunhua Shen |
| Abstract | In addition, our work has text overlap with arXiv:1804.06242, arXiv:1705.00938 by other authors. We want to rewrite this paper for avoiding this fact. |
| Tasks | |
| Published | 2018-08-04 |
| URL | http://arxiv.org/abs/1808.02373v2 |
| http://arxiv.org/pdf/1808.02373v2.pdf | |
| PWC | https://paperswithcode.com/paper/troy-give-attention-to-saliency-and-for |
| Repo | |
| Framework | |
The Web as a Knowledge-base for Answering Complex Questions
| Title | The Web as a Knowledge-base for Answering Complex Questions |
| Authors | Alon Talmor, Jonathan Berant |
| Abstract | Answering complex questions is a time-consuming activity for humans that requires reasoning and integration of information. Recent work on reading comprehension made headway in answering simple questions, but tackling complex questions is still an ongoing research challenge. Conversely, semantic parsers have been successful at handling compositionality, but only when the information resides in a target knowledge-base. In this paper, we present a novel framework for answering broad and complex questions, assuming answering simple questions is possible using a search engine and a reading comprehension model. We propose to decompose complex questions into a sequence of simple questions, and compute the final answer from the sequence of answers. To illustrate the viability of our approach, we create a new dataset of complex questions, ComplexWebQuestions, and present a model that decomposes questions and interacts with the web to compute an answer. We empirically demonstrate that question decomposition improves performance from 20.8 precision@1 to 27.5 precision@1 on this new dataset. |
| Tasks | Reading Comprehension |
| Published | 2018-03-18 |
| URL | http://arxiv.org/abs/1803.06643v1 |
| http://arxiv.org/pdf/1803.06643v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-web-as-a-knowledge-base-for-answering |
| Repo | |
| Framework | |
Unsupervised Emergence of Spatial Structure from Sensorimotor Prediction
| Title | Unsupervised Emergence of Spatial Structure from Sensorimotor Prediction |
| Authors | Alban Laflaquière, Michael Garcia Ortiz |
| Abstract | Despite its omnipresence in robotics application, the nature of spatial knowledge and the mechanisms that underlie its emergence in autonomous agents are still poorly understood. Recent theoretical work suggests that the concept of space can be grounded by capturing invariants induced by the structure of space in an agent’s raw sensorimotor experience. Moreover, it is hypothesized that capturing these invariants is beneficial for a naive agent trying to predict its sensorimotor experience. Under certain exploratory conditions, spatial representations should thus emerge as a byproduct of learning to predict. We propose a simple sensorimotor predictive scheme, apply it to different agents and types of exploration, and evaluate the pertinence of this hypothesis. We show that a naive agent can capture the topology and metric regularity of its spatial configuration without any a priori knowledge, nor extraneous supervision. |
| Tasks | |
| Published | 2018-10-02 |
| URL | http://arxiv.org/abs/1810.01344v2 |
| http://arxiv.org/pdf/1810.01344v2.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-emergence-of-spatial-structure |
| Repo | |
| Framework | |
Vehicles Lane-changing Behavior Detection
| Title | Vehicles Lane-changing Behavior Detection |
| Authors | Iljoo Baek, Mengwen He |
| Abstract | The lane-level localization accuracy is very important for autonomous vehicles. The Global Navigation Satellite System (GNSS), e.g. GPS, is a generic localization method for vehicles, but is vulnerable to the multi-path interference in the urban environment. Integrating the vision-based relative localization result and a digital map with the GNSS is a common and cheap way to increase the global localization accuracy and thus to realize the lane-level localization. This project is to develop a mono-camera based lane-changing behavior detection module for the correction of lateral GPS localization. We implemented a Support Vector Machine (SVM) based framework to directly classify the driving behavior, including the lane keeping, left and right lane changing, from a sampled data of the raw image captured by the mono-camera installed behind the window shield. The training data was collected from the driving around Carnegie Mellon University, and we compared the trained SVM models w/ and w/o the Principle Component Analysis (PCA) dimension reduction technique. The performance of the SVM based classification method was compared with the CNN method. |
| Tasks | Autonomous Vehicles, Dimensionality Reduction |
| Published | 2018-08-22 |
| URL | http://arxiv.org/abs/1808.07518v1 |
| http://arxiv.org/pdf/1808.07518v1.pdf | |
| PWC | https://paperswithcode.com/paper/vehicles-lane-changing-behavior-detection |
| Repo | |
| Framework | |
End-to-End Automatic Speech Translation of Audiobooks
| Title | End-to-End Automatic Speech Translation of Audiobooks |
| Authors | Alexandre Bérard, Laurent Besacier, Ali Can Kocabiyikoglu, Olivier Pietquin |
| Abstract | We investigate end-to-end speech-to-text translation on a corpus of audiobooks specifically augmented for this task. Previous works investigated the extreme case where source language transcription is not available during learning nor decoding, but we also study a midway case where source language transcription is available at training time only. In this case, a single model is trained to decode source speech into target text in a single pass. Experimental results show that it is possible to train compact and efficient end-to-end speech translation models in this setup. We also distribute the corpus and hope that our speech translation baseline on this corpus will be challenged in the future. |
| Tasks | |
| Published | 2018-02-12 |
| URL | http://arxiv.org/abs/1802.04200v1 |
| http://arxiv.org/pdf/1802.04200v1.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-automatic-speech-translation-of |
| Repo | |
| Framework | |
Extending Dynamic Bayesian Networks for Anomaly Detection in Complex Logs
| Title | Extending Dynamic Bayesian Networks for Anomaly Detection in Complex Logs |
| Authors | Stephen Pauwels, Toon Calders |
| Abstract | Checking various log files from different processes can be a tedious task as these logs contain lots of events, each with a (possibly large) number of attributes. We developed a way to automatically model log files and detect outlier traces in the data. For that we extend Dynamic Bayesian Networks to model the normal behavior found in log files. We introduce a new algorithm that is able to learn a model of a log file starting from the data itself. The model is capable of scoring traces even when new values or new combinations of values appear in the log file. |
| Tasks | Anomaly Detection |
| Published | 2018-05-18 |
| URL | http://arxiv.org/abs/1805.07107v2 |
| http://arxiv.org/pdf/1805.07107v2.pdf | |
| PWC | https://paperswithcode.com/paper/extending-dynamic-bayesian-networks-for |
| Repo | |
| Framework | |
Learning dynamical systems with particle stochastic approximation EM
| Title | Learning dynamical systems with particle stochastic approximation EM |
| Authors | Andreas Lindholm, Fredrik Lindsten |
| Abstract | We present the particle stochastic approximation EM (PSAEM) algorithm for learning of dynamical systems. The method builds on the EM algorithm, an iterative procedure for maximum likelihood inference in latent variable models. By combining stochastic approximation EM and particle Gibbs with ancestor sampling (PGAS), PSAEM obtains superior computational performance and convergence properties compared to plain particle-smoothing-based approximations of the EM algorithm. PSAEM can be used for plain maximum likelihood inference as well as for empirical Bayes learning of hyperparameters. Specifically, the latter point means that existing PGAS implementations easily can be extended with PSAEM to estimate hyperparameters at almost no extra computational cost. We discuss the convergence properties of the algorithm, and demonstrate it on several signal processing applications. |
| Tasks | Latent Variable Models |
| Published | 2018-06-25 |
| URL | https://arxiv.org/abs/1806.09548v2 |
| https://arxiv.org/pdf/1806.09548v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-dynamical-systems-with-particle |
| Repo | |
| Framework | |
Auto Deep Compression by Reinforcement Learning Based Actor-Critic Structure
| Title | Auto Deep Compression by Reinforcement Learning Based Actor-Critic Structure |
| Authors | Hamed Hakkak |
| Abstract | Model-based compression is an effective, facilitating, and expanded model of neural network models with limited computing and low power. However, conventional models of compression techniques utilize crafted features [2,3,12] and explore specialized areas for exploration and design of large spaces in terms of size, speed, and accuracy, which usually have returns Less and time is up. This paper will effectively analyze deep auto compression (ADC) and reinforcement learning strength in an effective sample and space design, and improve the compression quality of the model. The results of compression of the advanced model are obtained without any human effort and in a completely automated way. With a 4- fold reduction in FLOP, the accuracy of 2.8% is higher than the manual compression model for VGG-16 in ImageNet. |
| Tasks | |
| Published | 2018-07-08 |
| URL | http://arxiv.org/abs/1807.02886v1 |
| http://arxiv.org/pdf/1807.02886v1.pdf | |
| PWC | https://paperswithcode.com/paper/auto-deep-compression-by-reinforcement |
| Repo | |
| Framework | |
Hybrid Diffusion: Spectral-Temporal Graph Filtering for Manifold Ranking
| Title | Hybrid Diffusion: Spectral-Temporal Graph Filtering for Manifold Ranking |
| Authors | Ahmet Iscen, Yannis Avrithis, Giorgos Tolias, Teddy Furon, Ondrej Chum |
| Abstract | State of the art image retrieval performance is achieved with CNN features and manifold ranking using a k-NN similarity graph that is pre-computed off-line. The two most successful existing approaches are temporal filtering, where manifold ranking amounts to solving a sparse linear system online, and spectral filtering, where eigen-decomposition of the adjacency matrix is performed off-line and then manifold ranking amounts to dot-product search online. The former suffers from expensive queries and the latter from significant space overhead. Here we introduce a novel, theoretically well-founded hybrid filtering approach allowing full control of the space-time trade-off between these two extremes. Experimentally, we verify that our hybrid method delivers results on par with the state of the art, with lower memory demands compared to spectral filtering approaches and faster compared to temporal filtering. |
| Tasks | Image Retrieval |
| Published | 2018-07-23 |
| URL | http://arxiv.org/abs/1807.08692v2 |
| http://arxiv.org/pdf/1807.08692v2.pdf | |
| PWC | https://paperswithcode.com/paper/hybrid-diffusion-spectral-temporal-graph |
| Repo | |
| Framework | |
A Conversational Interface to Improve Medication Adherence: Towards AI Support in Patient’s Treatment
| Title | A Conversational Interface to Improve Medication Adherence: Towards AI Support in Patient’s Treatment |
| Authors | Ahmed Fadhil |
| Abstract | Medication adherence is of utmost importance for many chronic conditions, regardless of the disease type. Engaging patients in self-tracking their medication is a big challenge. One way to potentially reduce this burden is to use reminders to promote wellness throughout all stages of life and improve medication adherence. Chatbots have proven effectiveness in triggering users to engage in certain activity, such as medication adherence. In this paper, we discuss “Roborto”, a chatbot to create an engaging interactive and intelligent environment for patients and assist in positive lifestyle modification. We introduce a way for healthcare providers to track patients adherence and intervene whenever necessary. We describe the health, technical and behavioural approaches to the problem of medication non-adherence and propose a diagnostic and decision support tool. The proposed study will be implemented and validated through a pilot experiment with users to measure the efficacy of the proposed approach. |
| Tasks | Chatbot |
| Published | 2018-03-03 |
| URL | http://arxiv.org/abs/1803.09844v1 |
| http://arxiv.org/pdf/1803.09844v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-conversational-interface-to-improve |
| Repo | |
| Framework | |
Variational Calibration of Computer Models
| Title | Variational Calibration of Computer Models |
| Authors | Sébastien Marmin, Maurizio Filippone |
| Abstract | Bayesian calibration of black-box computer models offers an established framework to obtain a posterior distribution over model parameters. Traditional Bayesian calibration involves the emulation of the computer model and an additive model discrepancy term using Gaussian processes; inference is then carried out using MCMC. These choices pose computational and statistical challenges and limitations, which we overcome by proposing the use of approximate Deep Gaussian processes and variational inference techniques. The result is a practical and scalable framework for calibration, which obtains competitive performance compared to the state-of-the-art. |
| Tasks | Calibration, Gaussian Processes |
| Published | 2018-10-29 |
| URL | http://arxiv.org/abs/1810.12177v1 |
| http://arxiv.org/pdf/1810.12177v1.pdf | |
| PWC | https://paperswithcode.com/paper/variational-calibration-of-computer-models |
| Repo | |
| Framework | |
Action4D: Real-time Action Recognition in the Crowd and Clutter
| Title | Action4D: Real-time Action Recognition in the Crowd and Clutter |
| Authors | Quanzeng You, Hao Jiang |
| Abstract | Recognizing every person’s action in a crowded and cluttered environment is a challenging task. In this paper, we propose a real-time action recognition method, Action4D, which gives reliable and accurate results in the real-world settings. We propose to tackle the action recognition problem using a holistic 4D “scan” of a cluttered scene to include every detail about the people and environment. Recognizing multiple people’s actions in the cluttered 4D representation is a new problem. In this paper, we propose novel methods to solve this problem. We propose a new method to track people in 4D, which can reliably detect and follow each person in real time. We propose a new deep neural network, the Action4D-Net, to recognize the action of each tracked person. The Action4D-Net’s novel structure uses both the global feature and the focused attention to achieve state-of-the-art result. Our real-time method is invariant to camera view angles, resistant to clutter and able to handle crowd. The experimental results show that the proposed method is fast, reliable and accurate. Our method paves the way to action recognition in the real-world applications and is ready to be deployed to enable smart homes, smart factories and smart stores. |
| Tasks | Temporal Action Localization |
| Published | 2018-06-06 |
| URL | http://arxiv.org/abs/1806.02424v1 |
| http://arxiv.org/pdf/1806.02424v1.pdf | |
| PWC | https://paperswithcode.com/paper/action4d-real-time-action-recognition-in-the |
| Repo | |
| Framework | |
