Paper Group AWR 6
SNeCT: Scalable network constrained Tucker decomposition for integrative multi-platform data analysis. A Hybrid Approach For Hindi-English Machine Translation. Using deep learning to reveal the neural code for images in primary visual cortex. Deep learning and the Schrödinger equation. Scalable Twin Neural Networks for Classification of Unbalanced …
SNeCT: Scalable network constrained Tucker decomposition for integrative multi-platform data analysis
| Title | SNeCT: Scalable network constrained Tucker decomposition for integrative multi-platform data analysis |
| Authors | Dongjin Choi, Lee Sael |
| Abstract | Motivation: How do we integratively analyze large-scale multi-platform genomic data that are high dimensional and sparse? Furthermore, how can we incorporate prior knowledge, such as the association between genes, in the analysis systematically? Method: To solve this problem, we propose a Scalable Network Constrained Tucker decomposition method we call SNeCT. SNeCT adopts parallel stochastic gradient descent approach on the proposed parallelizable network constrained optimization function. SNeCT decomposition is applied to tensor constructed from large scale multi-platform multi-cohort cancer data, PanCan12, constrained on a network built from PathwayCommons database. Results: The decomposed factor matrices are applied to stratify cancers, to search for top-k similar patients, and to illustrate how the matrices can be used for personalized interpretation. In the stratification test, combined twelve-cohort data is clustered to form thirteen subclasses. The thirteen subclasses have a high correlation to tissue of origin in addition to other interesting observations, such as clear separation of OV cancers to two groups, and high clinical correlation within subclusters formed in cohorts BRCA and UCEC. In the top-k search, a new patient’s genomic profile is generated and searched against existing patients based on the factor matrices. The similarity of the top-k patient to the query is high for 23 clinical features, including estrogen/progesterone receptor statuses of BRCA patients with average precision value ranges from 0.72 to 0.86 and from 0.68 to 0.86, respectively. We also provide an illustration of how the factor matrices can be used for interpretable personalized analysis of each patient. |
| Tasks | |
| Published | 2017-11-22 |
| URL | http://arxiv.org/abs/1711.08095v2 |
| http://arxiv.org/pdf/1711.08095v2.pdf | |
| PWC | https://paperswithcode.com/paper/snect-scalable-network-constrained-tucker |
| Repo | https://github.com/skywalker5/SNeCT |
| Framework | none |
A Hybrid Approach For Hindi-English Machine Translation
| Title | A Hybrid Approach For Hindi-English Machine Translation |
| Authors | Omkar Dhariya, Shrikant Malviya, Uma Shanker Tiwary |
| Abstract | In this paper, an extended combined approach of phrase based statistical machine translation (SMT), example based MT (EBMT) and rule based MT (RBMT) is proposed to develop a novel hybrid data driven MT system capable of outperforming the baseline SMT, EBMT and RBMT systems from which it is derived. In short, the proposed hybrid MT process is guided by the rule based MT after getting a set of partial candidate translations provided by EBMT and SMT subsystems. Previous works have shown that EBMT systems are capable of outperforming the phrase-based SMT systems and RBMT approach has the strength of generating structurally and morphologically more accurate results. This hybrid approach increases the fluency, accuracy and grammatical precision which improve the quality of a machine translation system. A comparison of the proposed hybrid machine translation (HTM) model with renowned translators i.e. Google, BING and Babylonian is also presented which shows that the proposed model works better on sentences with ambiguity as well as comprised of idioms than others. |
| Tasks | Machine Translation |
| Published | 2017-02-06 |
| URL | http://arxiv.org/abs/1702.01587v1 |
| http://arxiv.org/pdf/1702.01587v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-hybrid-approach-for-hindi-english-machine |
| Repo | https://github.com/PranotiDesai/MachineTranslation |
| Framework | tf |
Using deep learning to reveal the neural code for images in primary visual cortex
| Title | Using deep learning to reveal the neural code for images in primary visual cortex |
| Authors | William F. Kindel, Elijah D. Christensen, Joel Zylberberg |
| Abstract | Primary visual cortex (V1) is the first stage of cortical image processing, and a major effort in systems neuroscience is devoted to understanding how it encodes information about visual stimuli. Within V1, many neurons respond selectively to edges of a given preferred orientation: these are known as simple or complex cells, and they are well-studied. Other neurons respond to localized center-surround image features. Still others respond selectively to certain image stimuli, but the specific features that excite them are unknown. Moreover, even for the simple and complex cells– the best-understood V1 neurons– it is challenging to predict how they will respond to natural image stimuli. Thus, there are important gaps in our understanding of how V1 encodes images. To fill this gap, we train deep convolutional neural networks to predict the firing rates of V1 neurons in response to natural image stimuli, and find that 15% of these neurons are within 10% of their theoretical limit of predictability. For these well predicted neurons, we invert the predictor network to identify the image features (receptive fields) that cause the V1 neurons to spike. In addition to those with previously-characterized receptive fields (Gabor wavelet and center-surround), we identify neurons that respond predictably to higher-level textural image features that are not localized to any particular region of the image. |
| Tasks | |
| Published | 2017-06-19 |
| URL | http://arxiv.org/abs/1706.06208v1 |
| http://arxiv.org/pdf/1706.06208v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-deep-learning-to-reveal-the-neural-code |
| Repo | https://github.com/jzlab/v1_predictor |
| Framework | tf |
Deep learning and the Schrödinger equation
| Title | Deep learning and the Schrödinger equation |
| Authors | Kyle Mills, Michael Spanner, Isaac Tamblyn |
| Abstract | We have trained a deep (convolutional) neural network to predict the ground-state energy of an electron in four classes of confining two-dimensional electrostatic potentials. On randomly generated potentials, for which there is no analytic form for either the potential or the ground-state energy, the neural network model was able to predict the ground-state energy to within chemical accuracy, with a median absolute error of 1.49 mHa. We also investigate the performance of the model in predicting other quantities such as the kinetic energy and the first excited-state energy of random potentials. |
| Tasks | |
| Published | 2017-02-05 |
| URL | http://arxiv.org/abs/1702.01361v3 |
| http://arxiv.org/pdf/1702.01361v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-and-the-schrodinger-equation |
| Repo | https://github.com/DavorPenzar/diplomski |
| Framework | none |
Scalable Twin Neural Networks for Classification of Unbalanced Data
| Title | Scalable Twin Neural Networks for Classification of Unbalanced Data |
| Authors | Jayadeva, Himanshu Pant, Sumit Soman, Mayank Sharma |
| Abstract | Twin Support Vector Machines (TWSVMs) have emerged an efficient alternative to Support Vector Machines (SVM) for learning from imbalanced datasets. The TWSVM learns two non-parallel classifying hyperplanes by solving a couple of smaller sized problems. However, it is unsuitable for large datasets, as it involves matrix operations. In this paper, we discuss a Twin Neural Network (Twin NN) architecture for learning from large unbalanced datasets. The Twin NN also learns an optimal feature map, allowing for better discrimination between classes. We also present an extension of this network architecture for multiclass datasets. Results presented in the paper demonstrate that the Twin NN generalizes well and scales well on large unbalanced datasets. |
| Tasks | |
| Published | 2017-04-30 |
| URL | http://arxiv.org/abs/1705.00347v2 |
| http://arxiv.org/pdf/1705.00347v2.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-twin-neural-networks-for |
| Repo | https://github.com/panthimanshu/twinNeuralNets |
| Framework | none |
VoiceLoop: Voice Fitting and Synthesis via a Phonological Loop
| Title | VoiceLoop: Voice Fitting and Synthesis via a Phonological Loop |
| Authors | Yaniv Taigman, Lior Wolf, Adam Polyak, Eliya Nachmani |
| Abstract | We present a new neural text to speech (TTS) method that is able to transform text to speech in voices that are sampled in the wild. Unlike other systems, our solution is able to deal with unconstrained voice samples and without requiring aligned phonemes or linguistic features. The network architecture is simpler than those in the existing literature and is based on a novel shifting buffer working memory. The same buffer is used for estimating the attention, computing the output audio, and for updating the buffer itself. The input sentence is encoded using a context-free lookup table that contains one entry per character or phoneme. The speakers are similarly represented by a short vector that can also be fitted to new identities, even with only a few samples. Variability in the generated speech is achieved by priming the buffer prior to generating the audio. Experimental results on several datasets demonstrate convincing capabilities, making TTS accessible to a wider range of applications. In order to promote reproducibility, we release our source code and models. |
| Tasks | |
| Published | 2017-07-20 |
| URL | http://arxiv.org/abs/1707.06588v3 |
| http://arxiv.org/pdf/1707.06588v3.pdf | |
| PWC | https://paperswithcode.com/paper/voiceloop-voice-fitting-and-synthesis-via-a |
| Repo | https://github.com/facebookresearch/loop |
| Framework | pytorch |
Deep Learning for Unsupervised Insider Threat Detection in Structured Cybersecurity Data Streams
| Title | Deep Learning for Unsupervised Insider Threat Detection in Structured Cybersecurity Data Streams |
| Authors | Aaron Tuor, Samuel Kaplan, Brian Hutchinson, Nicole Nichols, Sean Robinson |
| Abstract | Analysis of an organization’s computer network activity is a key component of early detection and mitigation of insider threat, a growing concern for many organizations. Raw system logs are a prototypical example of streaming data that can quickly scale beyond the cognitive power of a human analyst. As a prospective filter for the human analyst, we present an online unsupervised deep learning approach to detect anomalous network activity from system logs in real time. Our models decompose anomaly scores into the contributions of individual user behavior features for increased interpretability to aid analysts reviewing potential cases of insider threat. Using the CERT Insider Threat Dataset v6.2 and threat detection recall as our performance metric, our novel deep and recurrent neural network models outperform Principal Component Analysis, Support Vector Machine and Isolation Forest based anomaly detection baselines. For our best model, the events labeled as insider threat activity in our dataset had an average anomaly score in the 95.53 percentile, demonstrating our approach’s potential to greatly reduce analyst workloads. |
| Tasks | Anomaly Detection |
| Published | 2017-10-02 |
| URL | http://arxiv.org/abs/1710.00811v2 |
| http://arxiv.org/pdf/1710.00811v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-unsupervised-insider-threat |
| Repo | https://github.com/pnnl/safekit |
| Framework | tf |
A dissimilarity-based approach to predictive maintenance with application to HVAC systems
| Title | A dissimilarity-based approach to predictive maintenance with application to HVAC systems |
| Authors | Riccardo Satta, Stefano Cavallari, Eraldo Pomponi, Daniele Grasselli, Davide Picheo, Carlo Annis |
| Abstract | The goal of predictive maintenance is to forecast the occurrence of faults of an appliance, in order to proactively take the necessary actions to ensure its availability. In many application scenarios, predictive maintenance is applied to a set of homogeneous appliances. In this paper, we firstly review taxonomies and main methodologies currently used for condition-based maintenance; secondly, we argue that the mutual dissimilarities of the behaviours of all appliances of this set (the “cohort”) can be exploited to detect upcoming faults. Specifically, inspired by dissimilarity-based representations, we propose a novel machine learning approach based on the analysis of concurrent mutual differences of the measurements coming from the cohort. We evaluate our method over one year of historical data from a cohort of 17 HVAC (Heating, Ventilation and Air Conditioning) systems installed in an Italian hospital. We show that certain kinds of faults can be foreseen with an accuracy, measured in terms of area under the ROC curve, as high as 0.96. |
| Tasks | |
| Published | 2017-01-13 |
| URL | http://arxiv.org/abs/1701.03633v1 |
| http://arxiv.org/pdf/1701.03633v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-dissimilarity-based-approach-to-predictive |
| Repo | https://github.com/smrjan/predictive-maintainance |
| Framework | none |
Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach
| Title | Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach |
| Authors | Sergi Valverde, Mariano Cabezas, Eloy Roura, Sandra González-Villà, Deborah Pareto, Joan-Carles Vilanova, LLuís Ramió-Torrentà, Àlex Rovira, Arnau Oliver, Xavier Lladó |
| Abstract | In this paper, we present a novel automated method for White Matter (WM) lesion segmentation of Multiple Sclerosis (MS) patient images. Our approach is based on a cascade of two 3D patch-wise convolutional neural networks (CNN). The first network is trained to be more sensitive revealing possible candidate lesion voxels while the second network is trained to reduce the number of misclassified voxels coming from the first network. This cascaded CNN architecture tends to learn well from small sets of training data, which can be very interesting in practice, given the difficulty to obtain manual label annotations and the large amount of available unlabeled Magnetic Resonance Imaging (MRI) data. We evaluate the accuracy of the proposed method on the public MS lesion segmentation challenge MICCAI2008 dataset, comparing it with respect to other state-of-the-art MS lesion segmentation tools. Furthermore, the proposed method is also evaluated on two private MS clinical datasets, where the performance of our method is also compared with different recent public available state-of-the-art MS lesion segmentation methods. At the time of writing this paper, our method is the best ranked approach on the MICCAI2008 challenge, outperforming the rest of 60 participant methods when using all the available input modalities (T1-w, T2-w and FLAIR), while still in the top-rank (3rd position) when using only T1-w and FLAIR modalities. On clinical MS data, our approach exhibits a significant increase in the accuracy segmenting of WM lesions when compared with the rest of evaluated methods, highly correlating ($r \ge 0.97$) also with the expected lesion volume. |
| Tasks | Lesion Segmentation |
| Published | 2017-02-16 |
| URL | http://arxiv.org/abs/1702.04869v1 |
| http://arxiv.org/pdf/1702.04869v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-automated-multiple-sclerosis-lesion |
| Repo | https://github.com/sergivalverde/cnn-ms-lesion-segmentation |
| Framework | none |
An Order Preserving Bilinear Model for Person Detection in Multi-Modal Data
| Title | An Order Preserving Bilinear Model for Person Detection in Multi-Modal Data |
| Authors | Oytun Ulutan, Benjamin S. Riggan, Nasser M. Nasrabadi, B. S. Manjunath |
| Abstract | We propose a new order preserving bilinear framework that exploits low-resolution video for person detection in a multi-modal setting using deep neural networks. In this setting cameras are strategically placed such that less robust sensors, e.g. geophones that monitor seismic activity, are located within the field of views (FOVs) of cameras. The primary challenge is being able to leverage sufficient information from videos where there are less than 40 pixels on targets, while also taking advantage of less discriminative information from other modalities, e.g. seismic. Unlike state-of-the-art methods, our bilinear framework retains spatio-temporal order when computing the vector outer products between pairs of features. Despite the high dimensionality of these outer products, we demonstrate that our order preserving bilinear framework yields better performance than recent orderless bilinear models and alternative fusion methods. |
| Tasks | Human Detection |
| Published | 2017-12-20 |
| URL | http://arxiv.org/abs/1712.07721v2 |
| http://arxiv.org/pdf/1712.07721v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-order-preserving-bilinear-model-for-person |
| Repo | https://github.com/oulutan/OP-Bilinear-Model |
| Framework | tf |
A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction
| Title | A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction |
| Authors | Yao Qin, Dongjin Song, Haifeng Chen, Wei Cheng, Guofei Jiang, Garrison Cottrell |
| Abstract | The Nonlinear autoregressive exogenous (NARX) model, which predicts the current value of a time series based upon its previous values as well as the current and past values of multiple driving (exogenous) series, has been studied for decades. Despite the fact that various NARX models have been developed, few of them can capture the long-term temporal dependencies appropriately and select the relevant driving series to make predictions. In this paper, we propose a dual-stage attention-based recurrent neural network (DA-RNN) to address these two issues. In the first stage, we introduce an input attention mechanism to adaptively extract relevant driving series (a.k.a., input features) at each time step by referring to the previous encoder hidden state. In the second stage, we use a temporal attention mechanism to select relevant encoder hidden states across all time steps. With this dual-stage attention scheme, our model can not only make predictions effectively, but can also be easily interpreted. Thorough empirical studies based upon the SML 2010 dataset and the NASDAQ 100 Stock dataset demonstrate that the DA-RNN can outperform state-of-the-art methods for time series prediction. |
| Tasks | Time Series, Time Series Prediction |
| Published | 2017-04-07 |
| URL | http://arxiv.org/abs/1704.02971v4 |
| http://arxiv.org/pdf/1704.02971v4.pdf | |
| PWC | https://paperswithcode.com/paper/a-dual-stage-attention-based-recurrent-neural |
| Repo | https://github.com/Zhenye-Na/DA-RNN |
| Framework | pytorch |
MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation
| Title | MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation |
| Authors | Xucong Zhang, Yusuke Sugano, Mario Fritz, Andreas Bulling |
| Abstract | Learning-based methods are believed to work well for unconstrained gaze estimation, i.e. gaze estimation from a monocular RGB camera without assumptions regarding user, environment, or camera. However, current gaze datasets were collected under laboratory conditions and methods were not evaluated across multiple datasets. Our work makes three contributions towards addressing these limitations. First, we present the MPIIGaze that contains 213,659 full face images and corresponding ground-truth gaze positions collected from 15 users during everyday laptop use over several months. An experience sampling approach ensured continuous gaze and head poses and realistic variation in eye appearance and illumination. To facilitate cross-dataset evaluations, 37,667 images were manually annotated with eye corners, mouth corners, and pupil centres. Second, we present an extensive evaluation of state-of-the-art gaze estimation methods on three current datasets, including MPIIGaze. We study key challenges including target gaze range, illumination conditions, and facial appearance variation. We show that image resolution and the use of both eyes affect gaze estimation performance while head pose and pupil centre information are less informative. Finally, we propose GazeNet, the first deep appearance-based gaze estimation method. GazeNet improves the state of the art by 22% percent (from a mean error of 13.9 degrees to 10.8 degrees) for the most challenging cross-dataset evaluation. |
| Tasks | Gaze Estimation |
| Published | 2017-11-24 |
| URL | http://arxiv.org/abs/1711.09017v1 |
| http://arxiv.org/pdf/1711.09017v1.pdf | |
| PWC | https://paperswithcode.com/paper/mpiigaze-real-world-dataset-and-deep |
| Repo | https://github.com/hysts/pytorch_mpiigaze_demo |
| Framework | none |
Multi-dimensional imaging data recovery via minimizing the partial sum of tubal nuclear norm
| Title | Multi-dimensional imaging data recovery via minimizing the partial sum of tubal nuclear norm |
| Authors | Tai-Xiang Jiang, Ting-Zhu Huang, Xi-Le Zhao, Liang-Jian Deng |
| Abstract | In this paper, we investigate tensor recovery problems within the tensor singular value decomposition (t-SVD) framework. We propose the partial sum of the tubal nuclear norm (PSTNN) of a tensor. The PSTNN is a surrogate of the tensor tubal multi-rank. We build two PSTNN-based minimization models for two typical tensor recovery problems, i.e., the tensor completion and the tensor principal component analysis. We give two algorithms based on the alternating direction method of multipliers (ADMM) to solve proposed PSTNN-based tensor recovery models. Experimental results on the synthetic data and real-world data reveal the superior of the proposed PSTNN. |
| Tasks | |
| Published | 2017-12-15 |
| URL | https://arxiv.org/abs/1712.05870v3 |
| https://arxiv.org/pdf/1712.05870v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-nonconvex-approach-to-recover-the-low |
| Repo | https://github.com/zhaoxile/PSTNN |
| Framework | none |
A Unified Parallel Algorithm for Regularized Group PLS Scalable to Big Data
| Title | A Unified Parallel Algorithm for Regularized Group PLS Scalable to Big Data |
| Authors | Pierre Lafaye de Micheaux, Benoit Liquet, Matthew Sutton |
| Abstract | Partial Least Squares (PLS) methods have been heavily exploited to analyse the association between two blocs of data. These powerful approaches can be applied to data sets where the number of variables is greater than the number of observations and in presence of high collinearity between variables. Different sparse versions of PLS have been developed to integrate multiple data sets while simultaneously selecting the contributing variables. Sparse modelling is a key factor in obtaining better estimators and identifying associations between multiple data sets. The cornerstone of the sparsity version of PLS methods is the link between the SVD of a matrix (constructed from deflated versions of the original matrices of data) and least squares minimisation in linear regression. We present here an accurate description of the most popular PLS methods, alongside their mathematical proofs. A unified algorithm is proposed to perform all four types of PLS including their regularised versions. Various approaches to decrease the computation time are offered, and we show how the whole procedure can be scalable to big data sets. |
| Tasks | Mathematical Proofs |
| Published | 2017-02-23 |
| URL | http://arxiv.org/abs/1702.07066v1 |
| http://arxiv.org/pdf/1702.07066v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-unified-parallel-algorithm-for-regularized |
| Repo | https://github.com/matt-sutton/bigsgPLS |
| Framework | none |
Learning to Multi-Task by Active Sampling
| Title | Learning to Multi-Task by Active Sampling |
| Authors | Sahil Sharma, Ashutosh Jha, Parikshit Hegde, Balaraman Ravindran |
| Abstract | One of the long-standing challenges in Artificial Intelligence for learning goal-directed behavior is to build a single agent which can solve multiple tasks. Recent progress in multi-task learning for goal-directed sequential problems has been in the form of distillation based learning wherein a student network learns from multiple task-specific expert networks by mimicking the task-specific policies of the expert networks. While such approaches offer a promising solution to the multi-task learning problem, they require supervision from large expert networks which require extensive data and computation time for training. In this work, we propose an efficient multi-task learning framework which solves multiple goal-directed tasks in an on-line setup without the need for expert supervision. Our work uses active learning principles to achieve multi-task learning by sampling the harder tasks more than the easier ones. We propose three distinct models under our active sampling framework. An adaptive method with extremely competitive multi-tasking performance. A UCB-based meta-learner which casts the problem of picking the next task to train on as a multi-armed bandit problem. A meta-learning method that casts the next-task picking problem as a full Reinforcement Learning problem and uses actor critic methods for optimizing the multi-tasking performance directly. We demonstrate results in the Atari 2600 domain on seven multi-tasking instances: three 6-task instances, one 8-task instance, two 12-task instances and one 21-task instance. |
| Tasks | Active Learning, Meta-Learning, Multi-Task Learning |
| Published | 2017-02-20 |
| URL | http://arxiv.org/abs/1702.06053v4 |
| http://arxiv.org/pdf/1702.06053v4.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-multi-task-by-active-sampling |
| Repo | https://github.com/andris955/diplomaterv |
| Framework | tf |
