May 7, 2019

3220 words 16 mins read

Paper Group AWR 97

Neural Combinatorial Optimization with Reinforcement Learning. Deep Learning and Its Applications to Machine Health Monitoring: A Survey. Local Subspace-Based Outlier Detection using Global Neighbourhoods. Modeling cognitive deficits following neurodegenerative diseases and traumatic brain injuries with deep convolutional neural networks. SIFT Meet …

Neural Combinatorial Optimization with Reinforcement Learning


Title	Neural Combinatorial Optimization with Reinforcement Learning
Authors	Irwan Bello, Hieu Pham, Quoc V. Le, Mohammad Norouzi, Samy Bengio
Abstract	This paper presents a framework to tackle combinatorial optimization problems using neural networks and reinforcement learning. We focus on the traveling salesman problem (TSP) and train a recurrent network that, given a set of city coordinates, predicts a distribution over different city permutations. Using negative tour length as the reward signal, we optimize the parameters of the recurrent network using a policy gradient method. We compare learning the network parameters on a set of training graphs against learning them on individual test graphs. Despite the computational expense, without much engineering and heuristic designing, Neural Combinatorial Optimization achieves close to optimal results on 2D Euclidean graphs with up to 100 nodes. Applied to the KnapSack, another NP-hard problem, the same method obtains optimal solutions for instances with up to 200 items.
Tasks	Combinatorial Optimization
Published	2016-11-29
URL	http://arxiv.org/abs/1611.09940v3
PDF	http://arxiv.org/pdf/1611.09940v3.pdf
PWC	https://paperswithcode.com/paper/neural-combinatorial-optimization-with
Repo	https://github.com/zhengsr3/Reinforcement_Learning_Pointer_Networks_TSP_Pytorch
Framework	pytorch

Deep Learning and Its Applications to Machine Health Monitoring: A Survey


Title	Deep Learning and Its Applications to Machine Health Monitoring: A Survey
Authors	Rui Zhao, Ruqiang Yan, Zhenghua Chen, Kezhi Mao, Peng Wang, Robert X. Gao
Abstract	Since 2006, deep learning (DL) has become a rapidly growing research direction, redefining state-of-the-art performances in a wide range of areas such as object recognition, image segmentation, speech recognition and machine translation. In modern manufacturing systems, data-driven machine health monitoring is gaining in popularity due to the widespread deployment of low-cost sensors and their connection to the Internet. Meanwhile, deep learning provides useful tools for processing and analyzing these big machinery data. The main purpose of this paper is to review and summarize the emerging research work of deep learning on machine health monitoring. After the brief introduction of deep learning techniques, the applications of deep learning in machine health monitoring systems are reviewed mainly from the following aspects: Auto-encoder (AE) and its variants, Restricted Boltzmann Machines and its variants including Deep Belief Network (DBN) and Deep Boltzmann Machines (DBM), Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). Finally, some new trends of DL-based machine health monitoring methods are discussed.
Tasks	Machine Translation, Object Recognition, Semantic Segmentation, Speech Recognition
Published	2016-12-16
URL	http://arxiv.org/abs/1612.07640v1
PDF	http://arxiv.org/pdf/1612.07640v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-and-its-applications-to-machine
Repo	https://github.com/lifesailor/data-driven-predictive-maintenance
Framework	none

Local Subspace-Based Outlier Detection using Global Neighbourhoods


Title	Local Subspace-Based Outlier Detection using Global Neighbourhoods
Authors	Bas van Stein, Matthijs van Leeuwen, Thomas Bäck
Abstract	Outlier detection in high-dimensional data is a challenging yet important task, as it has applications in, e.g., fraud detection and quality control. State-of-the-art density-based algorithms perform well because they 1) take the local neighbourhoods of data points into account and 2) consider feature subspaces. In highly complex and high-dimensional data, however, existing methods are likely to overlook important outliers because they do not explicitly take into account that the data is often a mixture distribution of multiple components. We therefore introduce GLOSS, an algorithm that performs local subspace outlier detection using global neighbourhoods. Experiments on synthetic data demonstrate that GLOSS more accurately detects local outliers in mixed data than its competitors. Moreover, experiments on real-world data show that our approach identifies relevant outliers overlooked by existing methods, confirming that one should keep an eye on the global perspective even when doing local outlier detection.
Tasks	Fraud Detection, Outlier Detection
Published	2016-11-01
URL	http://arxiv.org/abs/1611.00183v1
PDF	http://arxiv.org/pdf/1611.00183v1.pdf
PWC	https://paperswithcode.com/paper/local-subspace-based-outlier-detection-using
Repo	https://github.com/Basvanstein/Gloss
Framework	none

Modeling cognitive deficits following neurodegenerative diseases and traumatic brain injuries with deep convolutional neural networks


Title	Modeling cognitive deficits following neurodegenerative diseases and traumatic brain injuries with deep convolutional neural networks
Authors	Bethany Lusch, Jake Weholt, Pedro D. Maia, J. Nathan Kutz
Abstract	The accurate diagnosis and assessment of neurodegenerative disease and traumatic brain injuries (TBI) remain open challenges. Both cause cognitive and functional deficits due to focal axonal swellings (FAS), but it is difficult to deliver a prognosis due to our limited ability to assess damaged neurons at a cellular level in vivo. We simulate the effects of neurodegenerative disease and TBI using convolutional neural networks (CNNs) as our model of cognition. We utilize biophysically relevant statistical data on FAS to damage the connections in CNNs in a functionally relevant way. We incorporate energy constraints on the brain by pruning the CNNs to be less over-engineered. Qualitatively, we demonstrate that damage leads to human-like mistakes. Our experiments also provide quantitative assessments of how accuracy is affected by various types and levels of damage. The deficit resulting from a fixed amount of damage greatly depends on which connections are randomly injured, providing intuition for why it is difficult to predict impairments. There is a large degree of subjectivity when it comes to interpreting cognitive deficits from complex systems such as the human brain. However, we provide important insight and a quantitative framework for disorders in which FAS are implicated.
Tasks
Published	2016-12-13
URL	http://arxiv.org/abs/1612.04423v1
PDF	http://arxiv.org/pdf/1612.04423v1.pdf
PWC	https://paperswithcode.com/paper/modeling-cognitive-deficits-following
Repo	https://github.com/BethanyL/damaged_cnns
Framework	tf

SIFT Meets CNN: A Decade Survey of Instance Retrieval


Title	SIFT Meets CNN: A Decade Survey of Instance Retrieval
Authors	Liang Zheng, Yi Yang, Qi Tian
Abstract	In the early days, content-based image retrieval (CBIR) was studied with global features. Since 2003, image retrieval based on local descriptors (de facto SIFT) has been extensively studied for over a decade due to the advantage of SIFT in dealing with image transformations. Recently, image representations based on the convolutional neural network (CNN) have attracted increasing interest in the community and demonstrated impressive performance. Given this time of rapid evolution, this article provides a comprehensive survey of instance retrieval over the last decade. Two broad categories, SIFT-based and CNN-based methods, are presented. For the former, according to the codebook size, we organize the literature into using large/medium-sized/small codebooks. For the latter, we discuss three lines of methods, i.e., using pre-trained or fine-tuned CNN models, and hybrid methods. The first two perform a single-pass of an image to the network, while the last category employs a patch-based feature extraction scheme. This survey presents milestones in modern instance retrieval, reviews a broad selection of previous works in different categories, and provides insights on the connection between SIFT and CNN-based methods. After analyzing and comparing retrieval performance of different categories on several datasets, we discuss promising directions towards generic and specialized instance retrieval.
Tasks	Content-Based Image Retrieval, Image Retrieval
Published	2016-08-05
URL	http://arxiv.org/abs/1608.01807v2
PDF	http://arxiv.org/pdf/1608.01807v2.pdf
PWC	https://paperswithcode.com/paper/sift-meets-cnn-a-decade-survey-of-instance
Repo	https://github.com/ChuuyaZZZ/6787-Final-project
Framework	none

Web-based Argumentation


Title	Web-based Argumentation
Authors	Kenrick
Abstract	Assumption-Based Argumentation (ABA) is an argumentation framework that has been proposed in the late 20th century. Since then, there was still no solver implemented in a programming language which is easy to setup and no solver have been interfaced to the web, which impedes the interests of the public. This project aims to implement an ABA solver in a modern programming language that performs reasonably well and interface it to the web for easier access by the public. This project has demonstrated the novelty of development of an ABA solver, that computes conflict-free, stable, admissible, grounded, ideal, and complete semantics, in Python programming language which can be used via an easy-to-use web interface for visualization of the argument and dispute trees. Experiments were conducted to determine the project’s best configurations and to compare this project with proxdd, a state-of-the-art ABA solver, which has no web interface and computes less number of semantics. From the results of the experiments, this project’s best configuration is achieved by utilizing “pickle” technique and tree caching technique. Using this project’s best configuration, this project achieved a lower average runtime compared to proxdd. On other aspect, this project encountered more cases with exceptions compared to proxdd, which might be caused by this project computing more semantics and hence requires more resources to do so. Hence, it can be said that this project run comparably well to the state-of-the-art ABA solver proxdd. Future works of this project include computational complexity analysis and efficiency analysis of algorithms implemented, implementation of more semantics in argumentation framework, and usability testing of the web interface.
Tasks
Published	2016-12-14
URL	http://arxiv.org/abs/1612.04469v1
PDF	http://arxiv.org/pdf/1612.04469v1.pdf
PWC	https://paperswithcode.com/paper/web-based-argumentation
Repo	https://github.com/kenrick95/aba-web
Framework	none

Classification With an Edge: Improving Semantic Image Segmentation with Boundary Detection


Title	Classification With an Edge: Improving Semantic Image Segmentation with Boundary Detection
Authors	Dimitrios Marmanis, Konrad Schindler, Jan Dirk Wegner, Silvano Galliani, Mihai Datcu, Uwe Stilla
Abstract	We present an end-to-end trainable deep convolutional neural network (DCNN) for semantic segmentation with built-in awareness of semantically meaningful boundaries. Semantic segmentation is a fundamental remote sensing task, and most state-of-the-art methods rely on DCNNs as their workhorse. A major reason for their success is that deep networks learn to accumulate contextual information over very large windows (receptive fields). However, this success comes at a cost, since the associated loss of effecive spatial resolution washes out high-frequency details and leads to blurry object boundaries. Here, we propose to counter this effect by combining semantic segmentation with semantically informed edge detection, thus making class-boundaries explicit in the model, First, we construct a comparatively simple, memory-efficient model by adding boundary detection to the Segnet encoder-decoder architecture. Second, we also include boundary detection in FCN-type models and set up a high-end classifier ensemble. We show that boundary detection significantly improves semantic segmentation with CNNs. Our high-end ensemble achieves > 90% overall accuracy on the ISPRS Vaihingen benchmark.
Tasks	Boundary Detection, Edge Detection, Semantic Segmentation
Published	2016-12-05
URL	http://arxiv.org/abs/1612.01337v2
PDF	http://arxiv.org/pdf/1612.01337v2.pdf
PWC	https://paperswithcode.com/paper/classification-with-an-edge-improving
Repo	https://github.com/deep-unlearn/ISPRS-Classification-With-an-Edge
Framework	caffe2

Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening


Title	Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening
Authors	Frank S. He, Yang Liu, Alexander G. Schwing, Jian Peng
Abstract	We propose a novel training algorithm for reinforcement learning which combines the strength of deep Q-learning with a constrained optimization approach to tighten optimality and encourage faster reward propagation. Our novel technique makes deep reinforcement learning more practical by drastically reducing the training time. We evaluate the performance of our approach on the 49 games of the challenging Arcade Learning Environment, and report significant improvements in both training time and accuracy.
Tasks	Atari Games, Q-Learning
Published	2016-11-05
URL	http://arxiv.org/abs/1611.01606v1
PDF	http://arxiv.org/pdf/1611.01606v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-play-in-a-day-faster-deep
Repo	https://github.com/suyoung-lee/Episodic-Backward-Update
Framework	none

Dense Volume-to-Volume Vascular Boundary Detection


Title	Dense Volume-to-Volume Vascular Boundary Detection
Authors	Jameson Merkow, David Kriegman, Alison Marsden, Zhuowen Tu
Abstract	In this work, we present a novel 3D-Convolutional Neural Network (CNN) architecture called I2I-3D that predicts boundary location in volumetric data. Our fine-to-fine, deeply supervised framework addresses three critical issues to 3D boundary detection: (1) efficient, holistic, end-to-end volumetric label training and prediction (2) precise voxel-level prediction to capture fine scale structures prevalent in medical data and (3) directed multi-scale, multi-level feature learning. We evaluate our approach on a dataset consisting of 93 medical image volumes with a wide variety of anatomical regions and vascular structures. In the process, we also introduce HED-3D, a 3D extension of the state-of-the-art 2D edge detector (HED). We show that our deep learning approach out-performs, the current state-of-the-art in 3D vascular boundary detection (structured forests 3D), by a large margin, as well as HED applied to slices, and HED-3D while successfully localizing fine structures. With our approach, boundary detection takes about one minute on a typical 512x512x512 volume.
Tasks	Boundary Detection
Published	2016-05-26
URL	http://arxiv.org/abs/1605.08401v1
PDF	http://arxiv.org/pdf/1605.08401v1.pdf
PWC	https://paperswithcode.com/paper/dense-volume-to-volume-vascular-boundary
Repo	https://github.com/petteriTeikari/vesselNN
Framework	tf

“Why Should I Trust You?": Explaining the Predictions of Any Classifier


Title	“Why Should I Trust You?": Explaining the Predictions of Any Classifier
Authors	Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin
Abstract	Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a prediction, or when choosing whether to deploy a new model. Such understanding also provides insights into the model, which can be used to transform an untrustworthy model or prediction into a trustworthy one. In this work, we propose LIME, a novel explanation technique that explains the predictions of any classifier in an interpretable and faithful manner, by learning an interpretable model locally around the prediction. We also propose a method to explain models by presenting representative individual predictions and their explanations in a non-redundant way, framing the task as a submodular optimization problem. We demonstrate the flexibility of these methods by explaining different models for text (e.g. random forests) and image classification (e.g. neural networks). We show the utility of explanations via novel experiments, both simulated and with human subjects, on various scenarios that require trust: deciding if one should trust a prediction, choosing between models, improving an untrustworthy classifier, and identifying why a classifier should not be trusted.
Tasks	Image Classification, Interpretable Machine Learning
Published	2016-02-16
URL	http://arxiv.org/abs/1602.04938v3
PDF	http://arxiv.org/pdf/1602.04938v3.pdf
PWC	https://paperswithcode.com/paper/why-should-i-trust-you-explaining-the
Repo	https://github.com/marcotcr/lime
Framework	pytorch

From Pixels to Sentiment: Fine-tuning CNNs for Visual Sentiment Prediction


Title	From Pixels to Sentiment: Fine-tuning CNNs for Visual Sentiment Prediction
Authors	Victor Campos, Brendan Jou, Xavier Giro-i-Nieto
Abstract	Visual multimedia have become an inseparable part of our digital social lives, and they often capture moments tied with deep affections. Automated visual sentiment analysis tools can provide a means of extracting the rich feelings and latent dispositions embedded in these media. In this work, we explore how Convolutional Neural Networks (CNNs), a now de facto computational machine learning tool particularly in the area of Computer Vision, can be specifically applied to the task of visual sentiment prediction. We accomplish this through fine-tuning experiments using a state-of-the-art CNN and via rigorous architecture analysis, we present several modifications that lead to accuracy improvements over prior art on a dataset of images from a popular social media platform. We additionally present visualizations of local patterns that the network learned to associate with image sentiment for insight into how visual positivity (or negativity) is perceived by the model.
Tasks	Sentiment Analysis, Visual Sentiment Prediction
Published	2016-04-12
URL	http://arxiv.org/abs/1604.03489v2
PDF	http://arxiv.org/pdf/1604.03489v2.pdf
PWC	https://paperswithcode.com/paper/from-pixels-to-sentiment-fine-tuning-cnns-for
Repo	https://github.com/imatge-upc/sentiment-2017-imavis
Framework	caffe2

VIME: Variational Information Maximizing Exploration


Title	VIME: Variational Information Maximizing Exploration
Authors	Rein Houthooft, Xi Chen, Yan Duan, John Schulman, Filip De Turck, Pieter Abbeel
Abstract	Scalable and effective exploration remains a key challenge in reinforcement learning (RL). While there are methods with optimality guarantees in the setting of discrete state and action spaces, these methods cannot be applied in high-dimensional deep RL scenarios. As such, most contemporary RL relies on simple heuristics such as epsilon-greedy exploration or adding Gaussian noise to the controls. This paper introduces Variational Information Maximizing Exploration (VIME), an exploration strategy based on maximization of information gain about the agent’s belief of environment dynamics. We propose a practical implementation, using variational inference in Bayesian neural networks which efficiently handles continuous state and action spaces. VIME modifies the MDP reward function, and can be applied with several different underlying RL algorithms. We demonstrate that VIME achieves significantly better performance compared to heuristic exploration methods across a variety of continuous control tasks and algorithms, including tasks with very sparse rewards.
Tasks	Continuous Control
Published	2016-05-31
URL	http://arxiv.org/abs/1605.09674v4
PDF	http://arxiv.org/pdf/1605.09674v4.pdf
PWC	https://paperswithcode.com/paper/vime-variational-information-maximizing
Repo	https://github.com/openai/vime
Framework	none

Triplet Probabilistic Embedding for Face Verification and Clustering


Title	Triplet Probabilistic Embedding for Face Verification and Clustering
Authors	Swami Sankaranarayanan, Azadeh Alavi, Carlos Castillo, Rama Chellappa
Abstract	Despite significant progress made over the past twenty five years, unconstrained face verification remains a challenging problem. This paper proposes an approach that couples a deep CNN-based approach with a low-dimensional discriminative embedding learned using triplet probability constraints to solve the unconstrained face verification problem. Aside from yielding performance improvements, this embedding provides significant advantages in terms of memory and for post-processing operations like subject specific clustering. Experiments on the challenging IJB-A dataset show that the proposed algorithm performs comparably or better than the state of the art methods in verification and identification metrics, while requiring much less training data and training time. The superior performance of the proposed method on the CFP dataset shows that the representation learned by our deep CNN is robust to extreme pose variation. Furthermore, we demonstrate the robustness of the deep features to challenges including age, pose, blur and clutter by performing simple clustering experiments on both IJB-A and LFW datasets.
Tasks	Face Verification
Published	2016-04-19
URL	http://arxiv.org/abs/1604.05417v3
PDF	http://arxiv.org/pdf/1604.05417v3.pdf
PWC	https://paperswithcode.com/paper/triplet-probabilistic-embedding-for-face
Repo	https://github.com/Ananaskelly/TPE
Framework	none

FLASH: Fast Bayesian Optimization for Data Analytic Pipelines


Title	FLASH: Fast Bayesian Optimization for Data Analytic Pipelines
Authors	Yuyu Zhang, Mohammad Taha Bahadori, Hang Su, Jimeng Sun
Abstract	Modern data science relies on data analytic pipelines to organize interdependent computational steps. Such analytic pipelines often involve different algorithms across multiple steps, each with its own hyperparameters. To achieve the best performance, it is often critical to select optimal algorithms and to set appropriate hyperparameters, which requires large computational efforts. Bayesian optimization provides a principled way for searching optimal hyperparameters for a single algorithm. However, many challenges remain in solving pipeline optimization problems with high-dimensional and highly conditional search space. In this work, we propose Fast LineAr SearcH (FLASH), an efficient method for tuning analytic pipelines. FLASH is a two-layer Bayesian optimization framework, which firstly uses a parametric model to select promising algorithms, then computes a nonparametric model to fine-tune hyperparameters of the promising algorithms. FLASH also includes an effective caching algorithm which can further accelerate the search process. Extensive experiments on a number of benchmark datasets have demonstrated that FLASH significantly outperforms previous state-of-the-art methods in both search speed and accuracy. Using 50% of the time budget, FLASH achieves up to 20% improvement on test error rate compared to the baselines. FLASH also yields state-of-the-art performance on a real-world application for healthcare predictive modeling.
Tasks
Published	2016-02-20
URL	http://arxiv.org/abs/1602.06468v3
PDF	http://arxiv.org/pdf/1602.06468v3.pdf
PWC	https://paperswithcode.com/paper/flash-fast-bayesian-optimization-for-data
Repo	https://github.com/yuyuz/FLASH
Framework	none

Style-Transfer via Texture-Synthesis


Title	Style-Transfer via Texture-Synthesis
Authors	Michael Elad, Peyman Milanfar
Abstract	Style-transfer is a process of migrating a style from a given image to the content of another, synthesizing a new image which is an artistic mixture of the two. Recent work on this problem adopting Convolutional Neural-networks (CNN) ignited a renewed interest in this field, due to the very impressive results obtained. There exists an alternative path towards handling the style-transfer task, via generalization of texture-synthesis algorithms. This approach has been proposed over the years, but its results are typically less impressive compared to the CNN ones. In this work we propose a novel style-transfer algorithm that extends the texture-synthesis work of Kwatra et. al. (2005), while aiming to get stylized images that get closer in quality to the CNN ones. We modify Kwatra’s algorithm in several key ways in order to achieve the desired transfer, with emphasis on a consistent way for keeping the content intact in selected regions, while producing hallucinated and rich style in others. The results obtained are visually pleasing and diverse, shown to be competitive with the recent CNN style-transfer algorithms. The proposed algorithm is fast and flexible, being able to process any pair of content + style images.
Tasks	Style Transfer, Texture Synthesis
Published	2016-09-10
URL	http://arxiv.org/abs/1609.03057v3
PDF	http://arxiv.org/pdf/1609.03057v3.pdf
PWC	https://paperswithcode.com/paper/style-transfer-via-texture-synthesis
Repo	https://github.com/jsonkung/style-transfer-texture-synthesis
Framework	none