May 6, 2019

2850 words 14 mins read

Paper Group ANR 370

Modeling Time Series Similarity with Siamese Recurrent Networks. Multi-task learning with deep model based reinforcement learning. Cognitive state classification using transformed fMRI data. PixelVAE: A Latent Variable Model for Natural Images. How is a data-driven approach better than random choice in label space division for multi-label classific …

Modeling Time Series Similarity with Siamese Recurrent Networks


Title	Modeling Time Series Similarity with Siamese Recurrent Networks
Authors	Wenjie Pei, David M. J. Tax, Laurens van der Maaten
Abstract	Traditional techniques for measuring similarities between time series are based on handcrafted similarity measures, whereas more recent learning-based approaches cannot exploit external supervision. We combine ideas from time-series modeling and metric learning, and study siamese recurrent networks (SRNs) that minimize a classification loss to learn a good similarity measure between time series. Specifically, our approach learns a vectorial representation for each time series in such a way that similar time series are modeled by similar representations, and dissimilar time series by dissimilar representations. Because it is a similarity prediction models, SRNs are particularly well-suited to challenging scenarios such as signature recognition, in which each person is a separate class and very few examples per class are available. We demonstrate the potential merits of SRNs in within-domain and out-of-domain classification experiments and in one-shot learning experiments on tasks such as signature, voice, and sign language recognition.
Tasks	Metric Learning, One-Shot Learning, Sign Language Recognition, Time Series
Published	2016-03-15
URL	http://arxiv.org/abs/1603.04713v1
PDF	http://arxiv.org/pdf/1603.04713v1.pdf
PWC	https://paperswithcode.com/paper/modeling-time-series-similarity-with-siamese
Repo
Framework

Multi-task learning with deep model based reinforcement learning


Title	Multi-task learning with deep model based reinforcement learning
Authors	Asier Mujika
Abstract	In recent years, model-free methods that use deep learning have achieved great success in many different reinforcement learning environments. Most successful approaches focus on solving a single task, while multi-task reinforcement learning remains an open problem. In this paper, we present a model based approach to deep reinforcement learning which we use to solve different tasks simultaneously. We show that our approach not only does not degrade but actually benefits from learning multiple tasks. For our model, we also present a new kind of recurrent neural network inspired by residual networks that decouples memory from computation allowing to model complex environments that do not require lots of memory.
Tasks	Multi-Task Learning
Published	2016-11-04
URL	http://arxiv.org/abs/1611.01457v4
PDF	http://arxiv.org/pdf/1611.01457v4.pdf
PWC	https://paperswithcode.com/paper/multi-task-learning-with-deep-model-based
Repo
Framework

Cognitive state classification using transformed fMRI data


Title	Cognitive state classification using transformed fMRI data
Authors	Hariharan Ramasangu, Neelam Sinha
Abstract	One approach, for understanding human brain functioning, is to analyze the changes in the brain while performing cognitive tasks. Towards this, Functional Magnetic Resonance (fMR) images of subjects performing well-defined tasks are widely utilized for task-specific analyses. In this work, we propose a procedure to enable classification between two chosen cognitive tasks, using their respective fMR image sequences. The time series of expert-marked anatomically-mapped relevant voxels are processed and fed as input to the classical Naive Bayesian and SVM classifiers. The processing involves use of random sieve function, phase information in the data transformed using Fourier and Hilbert transformations. This processing results in improved classification, as against using the voxel intensities directly, as illustrated. The novelty of the proposed method lies in utilizing the phase information in the transformed domain, for classifying between the cognitive tasks along with random sieve function chosen with a particular probability distribution. The proposed classification procedure is applied on a publicly available dataset, StarPlus data, with 6 subjects performing the two distinct cognitive tasks of watching either a picture or a sentence. The classification accuracy stands at an average of 65.6%(using Naive Bayes classifier) and 76.4%(using SVM classifier) for raw data. The corresponding classification accuracy stands at 96.8% and 97.5% for Fourier transformed data. For Hilbert transformed data, it is 93.7% and 99%, for 6 subjects, on 2 cognitive tasks.
Tasks	Time Series
Published	2016-04-19
URL	http://arxiv.org/abs/1604.05413v1
PDF	http://arxiv.org/pdf/1604.05413v1.pdf
PWC	https://paperswithcode.com/paper/cognitive-state-classification-using
Repo
Framework

PixelVAE: A Latent Variable Model for Natural Images


Title	PixelVAE: A Latent Variable Model for Natural Images
Authors	Ishaan Gulrajani, Kundan Kumar, Faruk Ahmed, Adrien Ali Taiga, Francesco Visin, David Vazquez, Aaron Courville
Abstract	Natural image modeling is a landmark challenge of unsupervised learning. Variational Autoencoders (VAEs) learn a useful latent representation and model global structure well but have difficulty capturing small details. PixelCNN models details very well, but lacks a latent code and is difficult to scale for capturing large structures. We present PixelVAE, a VAE model with an autoregressive decoder based on PixelCNN. Our model requires very few expensive autoregressive layers compared to PixelCNN and learns latent codes that are more compressed than a standard VAE while still capturing most non-trivial structure. Finally, we extend our model to a hierarchy of latent variables at different scales. Our model achieves state-of-the-art performance on binarized MNIST, competitive performance on 64x64 ImageNet, and high-quality samples on the LSUN bedrooms dataset.
Tasks
Published	2016-11-15
URL	http://arxiv.org/abs/1611.05013v1
PDF	http://arxiv.org/pdf/1611.05013v1.pdf
PWC	https://paperswithcode.com/paper/pixelvae-a-latent-variable-model-for-natural
Repo
Framework

How is a data-driven approach better than random choice in label space division for multi-label classification?


Title	How is a data-driven approach better than random choice in label space division for multi-label classification?
Authors	Piotr Szymański, Tomasz Kajdanowicz, Kristian Kersting
Abstract	We propose using five data-driven community detection approaches from social networks to partition the label space for the task of multi-label classification as an alternative to random partitioning into equal subsets as performed by RAkELd: modularity-maximizing fastgreedy and leading eigenvector, infomap, walktrap and label propagation algorithms. We construct a label co-occurence graph (both weighted an unweighted versions) based on training data and perform community detection to partition the label set. We include Binary Relevance and Label Powerset classification methods for comparison. We use gini-index based Decision Trees as the base classifier. We compare educated approaches to label space divisions against random baselines on 12 benchmark data sets over five evaluation measures. We show that in almost all cases seven educated guess approaches are more likely to outperform RAkELd than otherwise in all measures, but Hamming Loss. We show that fastgreedy and walktrap community detection methods on weighted label co-occurence graphs are 85-92% more likely to yield better F1 scores than random partitioning. Infomap on the unweighted label co-occurence graphs is on average 90% of the times better than random paritioning in terms of Subset Accuracy and 89% when it comes to Jaccard similarity. Weighted fastgreedy is better on average than RAkELd when it comes to Hamming Loss.
Tasks	Community Detection, Multi-Label Classification
Published	2016-06-07
URL	http://arxiv.org/abs/1606.02346v1
PDF	http://arxiv.org/pdf/1606.02346v1.pdf
PWC	https://paperswithcode.com/paper/how-is-a-data-driven-approach-better-than
Repo
Framework

Automatically extracting, ranking and visually summarizing the treatments for a disease


Title	Automatically extracting, ranking and visually summarizing the treatments for a disease
Authors	Prakash Reddy Putta, John J. Dzak III, Siddhartha R. Jonnalagadda
Abstract	Clinicians are expected to have up-to-date and broad knowledge of disease treatment options for a patient. Online health knowledge resources contain a wealth of information. However, because of the time investment needed to disseminate and rank pertinent information, there is a need to summarize the information in a more concise format. Our aim of the study is to provide clinicians with a concise overview of popular treatments for a given disease using information automatically computed from Medline abstracts. We analyzed the treatments of two disorders - Atrial Fibrillation and Congestive Heart Failure. We calculated the precision, recall, and f-scores of our two ranking methods to measure the accuracy of the results. For Atrial Fibrillation disorder, maximum f-score for the New Treatments weighing method is 0.611, which occurs at 60 treatments. For Congestive Heart Failure disorder, maximum f-score for the New Treatments weighing method is 0.503, which occurs at 80 treatments.
Tasks
Published	2016-09-06
URL	http://arxiv.org/abs/1609.01574v1
PDF	http://arxiv.org/pdf/1609.01574v1.pdf
PWC	https://paperswithcode.com/paper/automatically-extracting-ranking-and-visually
Repo
Framework

Neural Networks for Joint Sentence Classification in Medical Paper Abstracts


Title	Neural Networks for Joint Sentence Classification in Medical Paper Abstracts
Authors	Franck Dernoncourt, Ji Young Lee, Peter Szolovits
Abstract	Existing models based on artificial neural networks (ANNs) for sentence classification often do not incorporate the context in which sentences appear, and classify sentences individually. However, traditional sentence classification approaches have been shown to greatly benefit from jointly classifying subsequent sentences, such as with conditional random fields. In this work, we present an ANN architecture that combines the effectiveness of typical ANN models to classify sentences in isolation, with the strength of structured prediction. Our model achieves state-of-the-art results on two different datasets for sequential sentence classification in medical abstracts.
Tasks	Sentence Classification, Structured Prediction
Published	2016-12-15
URL	http://arxiv.org/abs/1612.05251v1
PDF	http://arxiv.org/pdf/1612.05251v1.pdf
PWC	https://paperswithcode.com/paper/neural-networks-for-joint-sentence
Repo
Framework

Submodular Learning and Covering with Response-Dependent Costs


Title	Submodular Learning and Covering with Response-Dependent Costs
Authors	Sivan Sabato
Abstract	We consider interactive learning and covering problems, in a setting where actions may incur different costs, depending on the response to the action. We propose a natural greedy algorithm for response-dependent costs. We bound the approximation factor of this greedy algorithm in active learning settings as well as in the general setting. We show that a different property of the cost function controls the approximation factor in each of these scenarios. We further show that in both settings, the approximation factor of this greedy algorithm is near-optimal among all greedy algorithms. Experiments demonstrate the advantages of the proposed algorithm in the response-dependent cost setting.
Tasks	Active Learning
Published	2016-02-23
URL	http://arxiv.org/abs/1602.07120v3
PDF	http://arxiv.org/pdf/1602.07120v3.pdf
PWC	https://paperswithcode.com/paper/submodular-learning-and-covering-with
Repo
Framework

Convex Optimization for Linear Query Processing under Approximate Differential Privacy


Title	Convex Optimization for Linear Query Processing under Approximate Differential Privacy
Authors	Ganzhao Yuan, Yin Yang, Zhenjie Zhang, Zhifeng Hao
Abstract	Differential privacy enables organizations to collect accurate aggregates over sensitive data with strong, rigorous guarantees on individuals’ privacy. Previous work has found that under differential privacy, computing multiple correlated aggregates as a batch, using an appropriate \emph{strategy}, may yield higher accuracy than computing each of them independently. However, finding the best strategy that maximizes result accuracy is non-trivial, as it involves solving a complex constrained optimization program that appears to be non-linear and non-convex. Hence, in the past much effort has been devoted in solving this non-convex optimization program. Existing approaches include various sophisticated heuristics and expensive numerical solutions. None of them, however, guarantees to find the optimal solution of this optimization problem. This paper points out that under ($\epsilon$, $\delta$)-differential privacy, the optimal solution of the above constrained optimization problem in search of a suitable strategy can be found, rather surprisingly, by solving a simple and elegant convex optimization program. Then, we propose an efficient algorithm based on Newton’s method, which we prove to always converge to the optimal solution with linear global convergence rate and quadratic local convergence rate. Empirical evaluations demonstrate the accuracy and efficiency of the proposed solution.
Tasks
Published	2016-02-13
URL	http://arxiv.org/abs/1602.04302v3
PDF	http://arxiv.org/pdf/1602.04302v3.pdf
PWC	https://paperswithcode.com/paper/convex-optimization-for-linear-query
Repo
Framework

Audio Event Detection using Weakly Labeled Data


Title	Audio Event Detection using Weakly Labeled Data
Authors	Anurag Kumar, Bhiksha Raj
Abstract	Acoustic event detection is essential for content analysis and description of multimedia recordings. The majority of current literature on the topic learns the detectors through fully-supervised techniques employing strongly labeled data. However, the labels available for majority of multimedia data are generally weak and do not provide sufficient detail for such methods to be employed. In this paper we propose a framework for learning acoustic event detectors using only weakly labeled data. We first show that audio event detection using weak labels can be formulated as an Multiple Instance Learning problem. We then suggest two frameworks for solving multiple-instance learning, one based on support vector machines, and the other on neural networks. The proposed methods can help in removing the time consuming and expensive process of manually annotating data to facilitate fully supervised learning. Moreover, it can not only detect events in a recording but can also provide temporal locations of events in the recording. This helps in obtaining a complete description of the recording and is notable since temporal information was never known in the first place in weakly labeled data.
Tasks	Multiple Instance Learning
Published	2016-05-09
URL	http://arxiv.org/abs/1605.02401v3
PDF	http://arxiv.org/pdf/1605.02401v3.pdf
PWC	https://paperswithcode.com/paper/audio-event-detection-using-weakly-labeled
Repo
Framework

Deep Neural Networks for HDR imaging


Title	Deep Neural Networks for HDR imaging
Authors	Kshiteej Sheth
Abstract	We propose novel methods of solving two tasks using Convolutional Neural Networks, firstly the task of generating HDR map of a static scene using differently exposed LDR images of the scene captured using conventional cameras and secondly the task of finding an optimal tone mapping operator that would give a better score on the TMQI metric compared to the existing methods. We quantitatively show the performance of our networks and illustrate the cases where our networks performs good as well as bad.
Tasks
Published	2016-09-04
URL	http://arxiv.org/abs/1611.00591v1
PDF	http://arxiv.org/pdf/1611.00591v1.pdf
PWC	https://paperswithcode.com/paper/deep-neural-networks-for-hdr-imaging
Repo
Framework

Manifold unwrapping using density ridges


Title	Manifold unwrapping using density ridges
Authors	Jonas Nordhaug Myhre, Matineh Shaker, Devrim Kaba, Robert Jenssen, Deniz Erdogmus
Abstract	Research on manifold learning within a density ridge estimation framework has shown great potential in recent work for both estimation and de-noising of manifolds, building on the intuitive and well-defined notion of principal curves and surfaces. However, the problem of unwrapping or unfolding manifolds has received relatively little attention within the density ridge approach, despite being an integral part of manifold learning in general. This paper proposes two novel algorithms for unwrapping manifolds based on estimated principal curves and surfaces for one- and multi-dimensional manifolds respectively. The methods of unwrapping are founded in the realization that both principal curves and principal surfaces will have inherent local maxima of the probability density function. Following this observation, coordinate systems that follow the shape of the manifold can be computed by following the integral curves of the gradient flow of a kernel density estimate on the manifold. Furthermore, since integral curves of the gradient flow of a kernel density estimate is inherently local, we propose to stitch together local coordinate systems using parallel transport along the manifold. We provide numerical experiments on both real and synthetic data that illustrates clear and intuitive unwrapping results comparable to state-of-the-art manifold learning algorithms.
Tasks
Published	2016-04-06
URL	http://arxiv.org/abs/1604.01602v2
PDF	http://arxiv.org/pdf/1604.01602v2.pdf
PWC	https://paperswithcode.com/paper/manifold-unwrapping-using-density-ridges
Repo
Framework

Emergence of foveal image sampling from learning to attend in visual scenes


Title	Emergence of foveal image sampling from learning to attend in visual scenes
Authors	Brian Cheung, Eric Weiss, Bruno Olshausen
Abstract	We describe a neural attention model with a learnable retinal sampling lattice. The model is trained on a visual search task requiring the classification of an object embedded in a visual scene amidst background distractors using the smallest number of fixations. We explore the tiling properties that emerge in the model’s retinal sampling lattice after training. Specifically, we show that this lattice resembles the eccentricity dependent sampling lattice of the primate retina, with a high resolution region in the fovea surrounded by a low resolution periphery. Furthermore, we find conditions where these emergent properties are amplified or eliminated providing clues to their function.
Tasks
Published	2016-11-28
URL	http://arxiv.org/abs/1611.09430v2
PDF	http://arxiv.org/pdf/1611.09430v2.pdf
PWC	https://paperswithcode.com/paper/emergence-of-foveal-image-sampling-from
Repo
Framework

Learning Bayesian Networks with Incomplete Data by Augmentation


Title	Learning Bayesian Networks with Incomplete Data by Augmentation
Authors	Tameem Adel, Cassio P. de Campos
Abstract	We present new algorithms for learning Bayesian networks from data with missing values using a data augmentation approach. An exact Bayesian network learning algorithm is obtained by recasting the problem into a standard Bayesian network learning problem without missing data. To the best of our knowledge, this is the first exact algorithm for this problem. As expected, the exact algorithm does not scale to large domains. We build on the exact method to create an approximate algorithm using a hill-climbing technique. This algorithm scales to large domains so long as a suitable standard structure learning method for complete data is available. We perform a wide range of experiments to demonstrate the benefits of learning Bayesian networks with such new approach.
Tasks	Data Augmentation
Published	2016-08-27
URL	http://arxiv.org/abs/1608.07734v2
PDF	http://arxiv.org/pdf/1608.07734v2.pdf
PWC	https://paperswithcode.com/paper/learning-bayesian-networks-with-incomplete
Repo
Framework

Single- and Multi-Task Architectures for Tool Presence Detection Challenge at M2CAI 2016


Title	Single- and Multi-Task Architectures for Tool Presence Detection Challenge at M2CAI 2016
Authors	Andru P. Twinanda, Didier Mutter, Jacques Marescaux, Michel de Mathelin, Nicolas Padoy
Abstract	The tool presence detection challenge at M2CAI 2016 consists of identifying the presence/absence of seven surgical tools in the images of cholecystectomy videos. Here, we propose to use deep architectures that are based on our previous work where we presented several architectures to perform multiple recognition tasks on laparoscopic videos. In this technical report, we present the tool presence detection results using two architectures: (1) a single-task architecture designed to perform solely the tool presence detection task and (2) a multi-task architecture designed to perform jointly phase recognition and tool presence detection. The results show that the multi-task network only slightly improves the tool presence detection results. In constrast, a significant improvement is obtained when there are more data available to train the networks. This significant improvement can be regarded as a call for action for other institutions to start working toward publishing more datasets into the community, so that better models could be generated to perform the task.
Tasks
Published	2016-10-27
URL	http://arxiv.org/abs/1610.08851v1
PDF	http://arxiv.org/pdf/1610.08851v1.pdf
PWC	https://paperswithcode.com/paper/single-and-multi-task-architectures-for-tool
Repo
Framework