Paper Group ANR 281
Proceedings of NIPS 2017 Symposium on Interpretable Machine Learning. Skin lesion detection based on an ensemble of deep convolutional neural network. Stochastic Multi-armed Bandits in Constant Space. Interpretable Machine Learning for Privacy-Preserving Pervasive Systems. R-PHOC: Segmentation-Free Word Spotting using CNN. Maritime situational awar …
Proceedings of NIPS 2017 Symposium on Interpretable Machine Learning
| Title | Proceedings of NIPS 2017 Symposium on Interpretable Machine Learning |
| Authors | Andrew Gordon Wilson, Jason Yosinski, Patrice Simard, Rich Caruana, William Herlands |
| Abstract | This is the Proceedings of NIPS 2017 Symposium on Interpretable Machine Learning, held in Long Beach, California, USA on December 7, 2017 |
| Tasks | Interpretable Machine Learning |
| Published | 2017-11-27 |
| URL | http://arxiv.org/abs/1711.09889v3 |
| http://arxiv.org/pdf/1711.09889v3.pdf | |
| PWC | https://paperswithcode.com/paper/proceedings-of-nips-2017-symposium-on |
| Repo | |
| Framework | |
Skin lesion detection based on an ensemble of deep convolutional neural network
| Title | Skin lesion detection based on an ensemble of deep convolutional neural network |
| Authors | Balazs Harangi |
| Abstract | Skin cancer is a major public health problem, with over 5 million newly diagnosed cases in the United States each year. Melanoma is the deadliest form of skin cancer, responsible for over 9,000 deaths each year. In this paper, we propose an ensemble of deep convolutional neural networks to classify dermoscopy images into three classes. To achieve the highest classification accuracy, we fuse the outputs of the softmax layers of four different neural architectures. For aggregation, we consider the individual accuracies of the networks weighted by the confidence values provided by their final softmax layers. This fusion-based approach outperformed all the individual neural networks regarding classification accuracy. |
| Tasks | |
| Published | 2017-05-09 |
| URL | http://arxiv.org/abs/1705.03360v1 |
| http://arxiv.org/pdf/1705.03360v1.pdf | |
| PWC | https://paperswithcode.com/paper/skin-lesion-detection-based-on-an-ensemble-of |
| Repo | |
| Framework | |
Stochastic Multi-armed Bandits in Constant Space
| Title | Stochastic Multi-armed Bandits in Constant Space |
| Authors | David Liau, Eric Price, Zhao Song, Ger Yang |
| Abstract | We consider the stochastic bandit problem in the sublinear space setting, where one cannot record the win-loss record for all $K$ arms. We give an algorithm using $O(1)$ words of space with regret [ \sum_{i=1}^{K}\frac{1}{\Delta_i}\log \frac{\Delta_i}{\Delta}\log T ] where $\Delta_i$ is the gap between the best arm and arm $i$ and $\Delta$ is the gap between the best and the second-best arms. If the rewards are bounded away from $0$ and $1$, this is within an $O(\log 1/\Delta)$ factor of the optimum regret possible without space constraints. |
| Tasks | Multi-Armed Bandits |
| Published | 2017-12-25 |
| URL | http://arxiv.org/abs/1712.09007v2 |
| http://arxiv.org/pdf/1712.09007v2.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-multi-armed-bandits-in-constant |
| Repo | |
| Framework | |
Interpretable Machine Learning for Privacy-Preserving Pervasive Systems
| Title | Interpretable Machine Learning for Privacy-Preserving Pervasive Systems |
| Authors | Benjamin Baron, Mirco Musolesi |
| Abstract | Our everyday interactions with pervasive systems generate traces that capture various aspects of human behavior and enable machine learning algorithms to extract latent information about users. In this paper, we propose a machine learning interpretability framework that enables users to understand how these generated traces violate their privacy. |
| Tasks | Interpretable Machine Learning |
| Published | 2017-10-23 |
| URL | https://arxiv.org/abs/1710.08464v6 |
| https://arxiv.org/pdf/1710.08464v6.pdf | |
| PWC | https://paperswithcode.com/paper/interpretable-machine-learning-for-privacy |
| Repo | |
| Framework | |
R-PHOC: Segmentation-Free Word Spotting using CNN
| Title | R-PHOC: Segmentation-Free Word Spotting using CNN |
| Authors | Suman Ghosh, Ernest Valveny |
| Abstract | This paper proposes a region based convolutional neural network for segmentation-free word spotting. Our net- work takes as input an image and a set of word candidate bound- ing boxes and embeds all bounding boxes into an embedding space, where word spotting can be casted as a simple nearest neighbour search between the query representation and each of the candidate bounding boxes. We make use of PHOC embedding as it has previously achieved significant success in segmentation- based word spotting. Word candidates are generated using a simple procedure based on grouping connected components using some spatial constraints. Experiments show that R-PHOC which operates on images directly can improve the current state-of- the-art in the standard GW dataset and performs as good as PHOCNET in some cases designed for segmentation based word spotting. |
| Tasks | |
| Published | 2017-07-05 |
| URL | http://arxiv.org/abs/1707.01294v1 |
| http://arxiv.org/pdf/1707.01294v1.pdf | |
| PWC | https://paperswithcode.com/paper/r-phoc-segmentation-free-word-spotting-using |
| Repo | |
| Framework | |
Maritime situational awareness using adaptive multi-sensor management under hazy conditions
| Title | Maritime situational awareness using adaptive multi-sensor management under hazy conditions |
| Authors | D. K. Prasad, C. K. Prasath, D. Rajan, L. Rachmawati, E. Rajabally, C. Quek |
| Abstract | This paper presents a multi-sensor architecture with an adaptive multi-sensor management system suitable for control and navigation of autonomous maritime vessels in hazy and poor-visibility conditions. This architecture resides in the autonomous maritime vessels. It augments the data from on-board imaging sensors and weather sensors with the AIS data and weather data from sensors on other vessels and the on-shore vessel traffic surveillance system. The combined data is analyzed using computational intelligence and data analytics to determine suitable course of action while utilizing historically learnt knowledge and performing live learning from the current situation. Such framework is expected to be useful in diverse weather conditions and shall be a useful architecture to provide autonomy to maritime vessels. |
| Tasks | |
| Published | 2017-02-02 |
| URL | http://arxiv.org/abs/1702.00754v1 |
| http://arxiv.org/pdf/1702.00754v1.pdf | |
| PWC | https://paperswithcode.com/paper/maritime-situational-awareness-using-adaptive |
| Repo | |
| Framework | |
Random Walk Sampling for Big Data over Networks
| Title | Random Walk Sampling for Big Data over Networks |
| Authors | Saeed Basirian, Alexander Jung |
| Abstract | It has been shown recently that graph signals with small total variation can be accurately recovered from only few samples if the sampling set satisfies a certain condition, referred to as the network nullspace property. Based on this recovery condition, we propose a sampling strategy for smooth graph signals based on random walks. Numerical experiments demonstrate the effectiveness of this approach for graph signals obtained from a synthetic random graph model as well as a real-world dataset. |
| Tasks | |
| Published | 2017-04-16 |
| URL | http://arxiv.org/abs/1704.04799v1 |
| http://arxiv.org/pdf/1704.04799v1.pdf | |
| PWC | https://paperswithcode.com/paper/random-walk-sampling-for-big-data-over |
| Repo | |
| Framework | |
Non-Convex Weighted Lp Minimization based Group Sparse Representation Framework for Image Denoising
| Title | Non-Convex Weighted Lp Minimization based Group Sparse Representation Framework for Image Denoising |
| Authors | Qiong Wang, Xinggan Zhang, Yu Wu, Lan Tang, Zhiyuan Zha |
| Abstract | Nonlocal image representation or group sparsity has attracted considerable interest in various low-level vision tasks and has led to several state-of-the-art image denoising techniques, such as BM3D, LSSC. In the past, convex optimization with sparsity-promoting convex regularization was usually regarded as a standard scheme for estimating sparse signals in noise. However, using convex regularization can not still obtain the correct sparsity solution under some practical problems including image inverse problems. In this paper we propose a non-convex weighted $\ell_p$ minimization based group sparse representation (GSR) framework for image denoising. To make the proposed scheme tractable and robust, the generalized soft-thresholding (GST) algorithm is adopted to solve the non-convex $\ell_p$ minimization problem. In addition, to improve the accuracy of the nonlocal similar patches selection, an adaptive patch search (APS) scheme is proposed. Experimental results have demonstrated that the proposed approach not only outperforms many state-of-the-art denoising methods such as BM3D and WNNM, but also results in a competitive speed. |
| Tasks | Denoising, Image Denoising |
| Published | 2017-04-05 |
| URL | http://arxiv.org/abs/1704.01429v3 |
| http://arxiv.org/pdf/1704.01429v3.pdf | |
| PWC | https://paperswithcode.com/paper/non-convex-weighted-lp-minimization-based |
| Repo | |
| Framework | |
Supervised Learning Based Algorithm Selection for Deep Neural Networks
| Title | Supervised Learning Based Algorithm Selection for Deep Neural Networks |
| Authors | Shaohuai Shi, Pengfei Xu, Xiaowen Chu |
| Abstract | Many recent deep learning platforms rely on third-party libraries (such as cuBLAS) to utilize the computing power of modern hardware accelerators (such as GPUs). However, we observe that they may achieve suboptimal performance because the library functions are not used appropriately. In this paper, we target at optimizing the operations of multiplying a matrix with the transpose of another matrix (referred to as NT operation hereafter), which contribute about half of the training time of fully connected deep neural networks. Rather than directly calling the library function, we propose a supervised learning based algorithm selection approach named MTNN, which uses a gradient boosted decision tree to select one from two alternative NT implementations intelligently: (1) calling the cuBLAS library function; (2) calling our proposed algorithm TNN that uses an efficient out-of-place matrix transpose. We evaluate the performance of MTNN on two modern GPUs: NVIDIA GTX 1080 and NVIDIA Titan X Pascal. MTNN can achieve 96% of prediction accuracy with very low computational overhead, which results in an average of 54% performance improvement on a range of NT operations. To further evaluate the impact of MTNN on the training process of deep neural networks, we have integrated MTNN into a popular deep learning platform Caffe. Our experimental results show that the revised Caffe can outperform the original one by an average of 28%. Both MTNN and the revised Caffe are open-source. |
| Tasks | |
| Published | 2017-02-10 |
| URL | http://arxiv.org/abs/1702.03192v2 |
| http://arxiv.org/pdf/1702.03192v2.pdf | |
| PWC | https://paperswithcode.com/paper/supervised-learning-based-algorithm-selection |
| Repo | |
| Framework | |
Multi-task memory networks for category-specific aspect and opinion terms co-extraction
| Title | Multi-task memory networks for category-specific aspect and opinion terms co-extraction |
| Authors | Wenya Wang, Sinno Jialin Pan, Daniel Dahlmeier |
| Abstract | In aspect-based sentiment analysis, most existing methods either focus on aspect/opinion terms extraction or aspect terms categorization. However, each task by itself only provides partial information to end users. To generate more detailed and structured opinion analysis, we propose a finer-grained problem, which we call category-specific aspect and opinion terms extraction. This problem involves the identification of aspect and opinion terms within each sentence, as well as the categorization of the identified terms. To this end, we propose an end-to-end multi-task attention model, where each task corresponds to aspect/opinion terms extraction for a specific category. Our model benefits from exploring the commonalities and relationships among different tasks to address the data sparsity issue. We demonstrate its state-of-the-art performance on three benchmark datasets. |
| Tasks | Aspect-Based Sentiment Analysis, Sentiment Analysis |
| Published | 2017-02-06 |
| URL | http://arxiv.org/abs/1702.01776v2 |
| http://arxiv.org/pdf/1702.01776v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-task-memory-networks-for-category |
| Repo | |
| Framework | |
Structure Learning in Motor Control:A Deep Reinforcement Learning Model
| Title | Structure Learning in Motor Control:A Deep Reinforcement Learning Model |
| Authors | Ari Weinstein, Matthew M. Botvinick |
| Abstract | Motor adaptation displays a structure-learning effect: adaptation to a new perturbation occurs more quickly when the subject has prior exposure to perturbations with related structure. Although this `learning-to-learn’ effect is well documented, its underlying computational mechanisms are poorly understood. We present a new model of motor structure learning, approaching it from the point of view of deep reinforcement learning. Previous work outside of motor control has shown how recurrent neural networks can account for learning-to-learn effects. We leverage this insight to address motor learning, by importing it into the setting of model-based reinforcement learning. We apply the resulting processing architecture to empirical findings from a landmark study of structure learning in target-directed reaching (Braun et al., 2009), and discuss its implications for a wider range of learning-to-learn phenomena. | |
| Tasks | |
| Published | 2017-06-21 |
| URL | http://arxiv.org/abs/1706.06827v2 |
| http://arxiv.org/pdf/1706.06827v2.pdf | |
| PWC | https://paperswithcode.com/paper/structure-learning-in-motor-controla-deep |
| Repo | |
| Framework | |
J-MOD$^{2}$: Joint Monocular Obstacle Detection and Depth Estimation
| Title | J-MOD$^{2}$: Joint Monocular Obstacle Detection and Depth Estimation |
| Authors | Michele Mancini, Gabriele Costante, Paolo Valigi, Thomas A. Ciarfuglia |
| Abstract | In this work, we propose an end-to-end deep architecture that jointly learns to detect obstacles and estimate their depth for MAV flight applications. Most of the existing approaches either rely on Visual SLAM systems or on depth estimation models to build 3D maps and detect obstacles. However, for the task of avoiding obstacles this level of complexity is not required. Recent works have proposed multi task architectures to both perform scene understanding and depth estimation. We follow their track and propose a specific architecture to jointly estimate depth and obstacles, without the need to compute a global map, but maintaining compatibility with a global SLAM system if needed. The network architecture is devised to exploit the joint information of the obstacle detection task, that produces more reliable bounding boxes, with the depth estimation one, increasing the robustness of both to scenario changes. We call this architecture J-MOD$^{2}$. We test the effectiveness of our approach with experiments on sequences with different appearance and focal lengths and compare it to SotA multi task methods that jointly perform semantic segmentation and depth estimation. In addition, we show the integration in a full system using a set of simulated navigation experiments where a MAV explores an unknown scenario and plans safe trajectories by using our detection model. |
| Tasks | Depth Estimation, Scene Understanding, Semantic Segmentation |
| Published | 2017-09-25 |
| URL | http://arxiv.org/abs/1709.08480v2 |
| http://arxiv.org/pdf/1709.08480v2.pdf | |
| PWC | https://paperswithcode.com/paper/j-mod2-joint-monocular-obstacle-detection-and |
| Repo | |
| Framework | |
Deriving a Representative Vector for Ontology Classes with Instance Word Vector Embeddings
| Title | Deriving a Representative Vector for Ontology Classes with Instance Word Vector Embeddings |
| Authors | Vindula Jayawardana, Dimuthu Lakmal, Nisansa de Silva, Amal Shehan Perera, Keet Sugathadasa, Buddhi Ayesha |
| Abstract | Selecting a representative vector for a set of vectors is a very common requirement in many algorithmic tasks. Traditionally, the mean or median vector is selected. Ontology classes are sets of homogeneous instance objects that can be converted to a vector space by word vector embeddings. This study proposes a methodology to derive a representative vector for ontology classes whose instances were converted to the vector space. We start by deriving five candidate vectors which are then used to train a machine learning model that would calculate a representative vector for the class. We show that our methodology out-performs the traditional mean and median vector representations. |
| Tasks | |
| Published | 2017-06-08 |
| URL | http://arxiv.org/abs/1706.02909v1 |
| http://arxiv.org/pdf/1706.02909v1.pdf | |
| PWC | https://paperswithcode.com/paper/deriving-a-representative-vector-for-ontology |
| Repo | |
| Framework | |
Demixing Structured Superposition Signals from Periodic and Aperiodic Nonlinear Observations
| Title | Demixing Structured Superposition Signals from Periodic and Aperiodic Nonlinear Observations |
| Authors | Mohammadreza Soltani, Chinmay Hegde |
| Abstract | We consider the demixing problem of two (or more) structured high-dimensional vectors from a limited number of nonlinear observations where this nonlinearity is due to either a periodic or an aperiodic function. We study certain families of structured superposition models, and propose a method which provably recovers the components given (nearly) $m = \mathcal{O}(s)$ samples where $s$ denotes the sparsity level of the underlying components. This strictly improves upon previous nonlinear demixing techniques and asymptotically matches the best possible sample complexity. We also provide a range of simulations to illustrate the performance of the proposed algorithms. |
| Tasks | |
| Published | 2017-08-08 |
| URL | http://arxiv.org/abs/1708.02999v1 |
| http://arxiv.org/pdf/1708.02999v1.pdf | |
| PWC | https://paperswithcode.com/paper/demixing-structured-superposition-signals |
| Repo | |
| Framework | |
Population Seeding Techniques for Rolling Horizon Evolution in General Video Game Playing
| Title | Population Seeding Techniques for Rolling Horizon Evolution in General Video Game Playing |
| Authors | Rauca D. Gaina, Simon M. Lucas, Diego Perez-Liebana |
| Abstract | While Monte Carlo Tree Search and closely related methods have dominated General Video Game Playing, recent research has demonstrated the promise of Rolling Horizon Evolutionary Algorithms as an interesting alternative. However, there is little attention paid to population initialization techniques in the setting of general real-time video games. Therefore, this paper proposes the use of population seeding to improve the performance of Rolling Horizon Evolution and presents the results of two methods, One Step Look Ahead and Monte Carlo Tree Search, tested on 20 games of the General Video Game AI corpus with multiple evolution parameter values (population size and individual length). An in-depth analysis is carried out between the results of the seeding methods and the vanilla Rolling Horizon Evolution. In addition, the paper presents a comparison to a Monte Carlo Tree Search algorithm. The results are promising, with seeding able to boost performance significantly over baseline evolution and even match the high level of play obtained by the Monte Carlo Tree Search. |
| Tasks | |
| Published | 2017-04-23 |
| URL | http://arxiv.org/abs/1704.06942v1 |
| http://arxiv.org/pdf/1704.06942v1.pdf | |
| PWC | https://paperswithcode.com/paper/population-seeding-techniques-for-rolling |
| Repo | |
| Framework | |
