Paper Group ANR 296
Distortion and Faults in Machine Learning Software. Differential Privacy for Power Grid Obfuscation. Deep Learning Based Computed Tomography Whys and Wherefores. Limitations of routing-by-agreement based capsule networks. Feature-Based Q-Learning for Two-Player Stochastic Games. Image Reconstruction: From Sparsity to Data-adaptive Methods and Machi …
Distortion and Faults in Machine Learning Software
| Title | Distortion and Faults in Machine Learning Software |
| Authors | Shin Nakajima |
| Abstract | Machine learning software, deep neural networks (DNN) software in particular, discerns valuable information from a large dataset, a set of data. Outcomes of such DNN programs are dependent on the quality of both learning programs and datasets. Unfortunately, the quality of datasets is difficult to be defined, because they are just samples. The quality assurance of DNN software is difficult, because resultant trained machine learning models are unknown prior to its development, and the validation is conducted indirectly in terms of prediction performance. This paper introduces a hypothesis that faults in the learning programs manifest themselves as distortions in trained machine learning models. Relative distortion degrees measured with appropriate observer functions may indicate that there are some hidden faults. The proposal is demonstrated with example cases of the MNIST dataset. |
| Tasks | |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1911.11596v1 |
| https://arxiv.org/pdf/1911.11596v1.pdf | |
| PWC | https://paperswithcode.com/paper/distortion-and-faults-in-machine-learning |
| Repo | |
| Framework | |
Differential Privacy for Power Grid Obfuscation
| Title | Differential Privacy for Power Grid Obfuscation |
| Authors | Ferdinando Fioretto, Terrence W. K. Mak, Pascal Van Hentenryck |
| Abstract | The availability of high-fidelity energy networks brings significant value to academic and commercial research. However, such releases also raise fundamental concerns related to privacy and security as they can reveal sensitive commercial information and expose system vulnerabilities. This paper investigates how to release power networks where the parameters of transmission lines and transformers are obfuscated. It does so by using the framework of Differential Privacy (DP), that provides strong privacy guarantees and has attracted significant attention in recent years. Unfortunately, simple DP mechanisms often result in AC-infeasible networks. To address these concerns, this paper presents a novel differential privacy mechanism that guarantees AC-feasibility and largely preserves the fidelity of the obfuscated network. Experimental results also show that the obfuscation significantly reduces the potential damage of an attacker exploiting the release of the dataset. |
| Tasks | |
| Published | 2019-01-21 |
| URL | https://arxiv.org/abs/1901.06949v2 |
| https://arxiv.org/pdf/1901.06949v2.pdf | |
| PWC | https://paperswithcode.com/paper/differential-privacy-for-power-grid |
| Repo | |
| Framework | |
Deep Learning Based Computed Tomography Whys and Wherefores
| Title | Deep Learning Based Computed Tomography Whys and Wherefores |
| Authors | Shabab Bazrafkan, Vincent Van Nieuwenhove, Joris Soons, Jan De Beenhouwer, Jan Sijbers |
| Abstract | This is an article about the Computed Tomography (CT) and how Deep Learning influences CT reconstruction pipeline, especially in low dose scenarios. |
| Tasks | Computed Tomography (CT) |
| Published | 2019-04-08 |
| URL | http://arxiv.org/abs/1904.03908v1 |
| http://arxiv.org/pdf/1904.03908v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-based-computed-tomography-whys |
| Repo | |
| Framework | |
Limitations of routing-by-agreement based capsule networks
| Title | Limitations of routing-by-agreement based capsule networks |
| Authors | David Peer, Sebastian Stabinger, Antonio Rodriguez-Sanchez |
| Abstract | Classical neural networks add a bias term to the sum of all weighted inputs. For capsule networks, the routing-by-agreement algorithm, which is commonly used to route vectors from lower level capsules to upper level capsules, calculates activations without a bias term. In this paper we show that such a term is also necessary for routing-by-agreement. We will proof that for every input there exists a symmetric input that cannot be distinguished correctly by capsules without a bias term. We show that this limitation impacts the training of deeper capsule networks negatively and that adding a bias term allows for the training of deeper capsule networks. An alternative to a bias is also presented in this paper. This novel method does not introduce additional parameters and is directly encoded in the activation vector of capsules. |
| Tasks | |
| Published | 2019-05-21 |
| URL | https://arxiv.org/abs/1905.08744v1 |
| https://arxiv.org/pdf/1905.08744v1.pdf | |
| PWC | https://paperswithcode.com/paper/limitations-of-routing-by-agreement-based |
| Repo | |
| Framework | |
Feature-Based Q-Learning for Two-Player Stochastic Games
| Title | Feature-Based Q-Learning for Two-Player Stochastic Games |
| Authors | Zeyu Jia, Lin F. Yang, Mengdi Wang |
| Abstract | Consider a two-player zero-sum stochastic game where the transition function can be embedded in a given feature space. We propose a two-player Q-learning algorithm for approximating the Nash equilibrium strategy via sampling. The algorithm is shown to find an $\epsilon$-optimal strategy using sample size linear to the number of features. To further improve its sample efficiency, we develop an accelerated algorithm by adopting techniques such as variance reduction, monotonicity preservation and two-sided strategy approximation. We prove that the algorithm is guaranteed to find an $\epsilon$-optimal strategy using no more than $\tilde{\mathcal{O}}(K/(\epsilon^{2}(1-\gamma)^{4}))$ samples with high probability, where $K$ is the number of features and $\gamma$ is a discount factor. The sample, time and space complexities of the algorithm are independent of original dimensions of the game. |
| Tasks | Q-Learning |
| Published | 2019-06-02 |
| URL | https://arxiv.org/abs/1906.00423v1 |
| https://arxiv.org/pdf/1906.00423v1.pdf | |
| PWC | https://paperswithcode.com/paper/190600423 |
| Repo | |
| Framework | |
Image Reconstruction: From Sparsity to Data-adaptive Methods and Machine Learning
| Title | Image Reconstruction: From Sparsity to Data-adaptive Methods and Machine Learning |
| Authors | Saiprasad Ravishankar, Jong Chul Ye, Jeffrey A. Fessler |
| Abstract | The field of medical image reconstruction has seen roughly four types of methods. The first type tended to be analytical methods, such as filtered back-projection (FBP) for X-ray computed tomography (CT) and the inverse Fourier transform for magnetic resonance imaging (MRI), based on simple mathematical models for the imaging systems. These methods are typically fast, but have suboptimal properties such as poor resolution-noise trade-off for CT. A second type is iterative reconstruction methods based on more complete models for the imaging system physics and, where appropriate, models for the sensor statistics. These iterative methods improved image quality by reducing noise and artifacts. The FDA-approved methods among these have been based on relatively simple regularization models. A third type of methods has been designed to accommodate modified data acquisition methods, such as reduced sampling in MRI and CT to reduce scan time or radiation dose. These methods typically involve mathematical image models involving assumptions such as sparsity or low-rank. A fourth type of methods replaces mathematically designed models of signals and systems with data-driven or adaptive models inspired by the field of machine learning. This paper focuses on the two most recent trends in medical image reconstruction: methods based on sparsity or low-rank models, and data-driven methods based on machine learning techniques. |
| Tasks | Computed Tomography (CT), Image Reconstruction |
| Published | 2019-04-04 |
| URL | https://arxiv.org/abs/1904.02816v3 |
| https://arxiv.org/pdf/1904.02816v3.pdf | |
| PWC | https://paperswithcode.com/paper/image-reconstruction-from-sparsity-to-data |
| Repo | |
| Framework | |
Explaining Reinforcement Learning to Mere Mortals: An Empirical Study
| Title | Explaining Reinforcement Learning to Mere Mortals: An Empirical Study |
| Authors | Andrew Anderson, Jonathan Dodge, Amrita Sadarangani, Zoe Juozapaitis, Evan Newman, Jed Irvine, Souti Chattopadhyay, Alan Fern, Margaret Burnett |
| Abstract | We present a user study to investigate the impact of explanations on non-experts’ understanding of reinforcement learning (RL) agents. We investigate both a common RL visualization, saliency maps (the focus of attention), and a more recent explanation type, reward-decomposition bars (predictions of future types of rewards). We designed a 124 participant, four-treatment experiment to compare participants’ mental models of an RL agent in a simple Real-Time Strategy (RTS) game. Our results show that the combination of both saliency and reward bars were needed to achieve a statistically significant improvement in mental model score over the control. In addition, our qualitative analysis of the data reveals a number of effects for further study. |
| Tasks | |
| Published | 2019-03-22 |
| URL | https://arxiv.org/abs/1903.09708v2 |
| https://arxiv.org/pdf/1903.09708v2.pdf | |
| PWC | https://paperswithcode.com/paper/explaining-reinforcement-learning-to-mere |
| Repo | |
| Framework | |
Adaptive Stress Testing with Reward Augmentation for Autonomous Vehicle Validation
| Title | Adaptive Stress Testing with Reward Augmentation for Autonomous Vehicle Validation |
| Authors | Anthony Corso, Peter Du, Katherine Driggs-Campbell, Mykel J. Kochenderfer |
| Abstract | Determining possible failure scenarios is a critical step in the evaluation of autonomous vehicle systems. Real-world vehicle testing is commonly employed for autonomous vehicle validation, but the costs and time requirements are high. Consequently, simulation-driven methods such as Adaptive Stress Testing (AST) have been proposed to aid in validation. AST formulates the problem of finding the most likely failure scenarios as a Markov decision process, which can be solved using reinforcement learning. In practice, AST tends to find scenarios where failure is unavoidable and tends to repeatedly discover the same types of failures of a system. This work addresses these issues by encoding domain relevant information into the search procedure. With this modification, the AST method discovers a larger and more expressive subset of the failure space when compared to the original AST formulation. We show that our approach is able to identify useful failure scenarios of an autonomous vehicle policy. |
| Tasks | |
| Published | 2019-08-02 |
| URL | https://arxiv.org/abs/1908.01046v2 |
| https://arxiv.org/pdf/1908.01046v2.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-stress-testing-with-reward |
| Repo | |
| Framework | |
Multi-modal Deep Guided Filtering for Comprehensible Medical Image Processing
| Title | Multi-modal Deep Guided Filtering for Comprehensible Medical Image Processing |
| Authors | Bernhard Stimpel, Christopher Syben, Franziska Schirrmacher, Philipp Hoelter, Arnd Dörfler, Andreas Maier |
| Abstract | Deep learning-based image processing is capable of creating highly appealing results. However, it is still widely considered as a “blackbox” transformation. In medical imaging, this lack of comprehensibility of the results is a sensitive issue. The integration of known operators into the deep learning environment has proven to be advantageous for the comprehensibility and reliability of the computations. Consequently, we propose the use of the locally linear guided filter in combination with a learned guidance map for general purpose medical image processing. The output images are only processed by the guided filter while the guidance map can be trained to be task-optimal in an end-to-end fashion. We investigate the performance based on two popular tasks: image super resolution and denoising. The evaluation is conducted based on pairs of multi-modal magnetic resonance imaging and cross-modal computed tomography and magnetic resonance imaging datasets. For both tasks, the proposed approach is on par with state-of-the-art approaches. Additionally, we can show that the input image’s content is almost unchanged after the processing which is not the case for conventional deep learning approaches. On top, the proposed pipeline offers increased robustness against degraded input as well as adversarial attacks. |
| Tasks | Denoising, Image Super-Resolution, Super-Resolution |
| Published | 2019-11-18 |
| URL | https://arxiv.org/abs/1911.07731v1 |
| https://arxiv.org/pdf/1911.07731v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-modal-deep-guided-filtering-for |
| Repo | |
| Framework | |
Neural Network Processing Neural Networks: An efficient way to learn higher order functions
| Title | Neural Network Processing Neural Networks: An efficient way to learn higher order functions |
| Authors | Firat Tuna |
| Abstract | Functions are rich in meaning and can be interpreted in a variety of ways. Neural networks were proven to be capable of approximating a large class of functions[1]. In this paper, we propose a new class of neural networks called “Neural Network Processing Neural Networks” (NNPNNs), which inputs neural networks and numerical values, instead of just numerical values. Thus enabling neural networks to represent and process rich structures. |
| Tasks | |
| Published | 2019-11-06 |
| URL | https://arxiv.org/abs/1911.05640v2 |
| https://arxiv.org/pdf/1911.05640v2.pdf | |
| PWC | https://paperswithcode.com/paper/neural-network-processing-neural-networks-an |
| Repo | |
| Framework | |
Playing Go without Game Tree Search Using Convolutional Neural Networks
| Title | Playing Go without Game Tree Search Using Convolutional Neural Networks |
| Authors | Jeffrey Barratt, Chuanbo Pan |
| Abstract | The game of Go has a long history in East Asian countries, but the field of Computer Go has yet to catch up to humans until the past couple of years. While the rules of Go are simple, the strategy and combinatorics of the game are immensely complex. Even within the past couple of years, new programs that rely on neural networks to evaluate board positions still explore many orders of magnitude more board positions per second than a professional can. We attempt to mimic human intuition in the game by creating a convolutional neural policy network which, without any sort of tree search, should play the game at or above the level of most humans. We introduce three structures and training methods that aim to create a strong Go player: non-rectangular convolutions, which will better learn the shapes on the board, supervised learning, training on a data set of 53,000 professional games, and reinforcement learning, training on games played between different versions of the network. Our network has already surpassed the skill level of intermediate amateurs simply using supervised learning. Further training and implementation of non-rectangular convolutions and reinforcement learning will likely increase this skill level much further. |
| Tasks | Game of Go |
| Published | 2019-07-02 |
| URL | https://arxiv.org/abs/1907.04658v1 |
| https://arxiv.org/pdf/1907.04658v1.pdf | |
| PWC | https://paperswithcode.com/paper/playing-go-without-game-tree-search-using |
| Repo | |
| Framework | |
A Novel Hyperparameter-free Approach to Decision Tree Construction that Avoids Overfitting by Design
| Title | A Novel Hyperparameter-free Approach to Decision Tree Construction that Avoids Overfitting by Design |
| Authors | Rafael Garcia Leiva, Antonio Fernandez Anta, Vincenzo Mancuso, Paolo Casari |
| Abstract | Decision trees are an extremely popular machine learning technique. Unfortunately, overfitting in decision trees still remains an open issue that sometimes prevents achieving good performance. In this work, we present a novel approach for the construction of decision trees that avoids the overfitting by design, without losing accuracy. A distinctive feature of our algorithm is that it requires neither the optimization of any hyperparameters, nor the use of regularization techniques, thus significantly reducing the decision tree training time. Moreover, our algorithm produces much smaller and shallower trees than traditional algorithms, facilitating the interpretability of the resulting models. |
| Tasks | |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01246v1 |
| https://arxiv.org/pdf/1906.01246v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-hyperparameter-free-approach-to |
| Repo | |
| Framework | |
From Active Contours to Minimal Geodesic Paths: New Solutions to Active Contours Problems by Eikonal Equations
| Title | From Active Contours to Minimal Geodesic Paths: New Solutions to Active Contours Problems by Eikonal Equations |
| Authors | Da Chen, Laurent D. Cohen |
| Abstract | In this chapter, we give an overview of part of our previous work based on the minimal path framework and the Eikonal partial differential equation (PDE). We show that by designing adequate Riemannian and Randers geodesic metrics the minimal paths can be utilized to search for solutions to almost all of the active contour problems and to the Euler-Mumford elastica problem, which allows to blend the advantages from minimal geodesic paths and those original approaches, i.e. the active contours and elastica curves. The proposed minimal path-based models can be applied to deal with a broad variety of image analysis tasks such as boundary detection, image segmentation and tubular structure extraction. The numerical implementations for the computation of minimal paths are known to be quite efficient thanks to the Eikonal solvers such as the Finsler variant of the fast marching method. |
| Tasks | Boundary Detection, Semantic Segmentation |
| Published | 2019-07-23 |
| URL | https://arxiv.org/abs/1907.09828v2 |
| https://arxiv.org/pdf/1907.09828v2.pdf | |
| PWC | https://paperswithcode.com/paper/from-active-contours-to-minimal-geodesic |
| Repo | |
| Framework | |
Prediction of Missing Semantic Relations in Lexical-Semantic Network using Random Forest Classifier
| Title | Prediction of Missing Semantic Relations in Lexical-Semantic Network using Random Forest Classifier |
| Authors | Kévin Cousot, Mehdi Mirzapour, Waleed Ragheb |
| Abstract | This study focuses on the prediction of missing six semantic relations (such as is_a and has_part) between two given nodes in RezoJDM a French lexical-semantic network. The output of this prediction is a set of pairs in which the first entries are semantic relations and the second entries are the probabilities of existence of such relations. Due to the statement of the problem we choose the random forest (RF) predictor classifier approach to tackle this problem. We take for granted the existing semantic relations, for training/test dataset, gathered and validated by crowdsourcing. We describe how all of the mentioned ideas can be followed after using the node2vec approach in the feature extraction phase. We show how this approach can lead to acceptable results. |
| Tasks | |
| Published | 2019-11-12 |
| URL | https://arxiv.org/abs/1911.04759v1 |
| https://arxiv.org/pdf/1911.04759v1.pdf | |
| PWC | https://paperswithcode.com/paper/prediction-of-missing-semantic-relations-in |
| Repo | |
| Framework | |
Perception-oriented Single Image Super-Resolution via Dual Relativistic Average Generative Adversarial Networks
| Title | Perception-oriented Single Image Super-Resolution via Dual Relativistic Average Generative Adversarial Networks |
| Authors | Yuan Ma, Kewen Liu, Hongxia Xiong, Panpan Fang, Xiaojun Li, Yalei Chen, Chaoyang Liu |
| Abstract | The presence of residual and dense neural networks which greatly promotes the development of image Super-Resolution(SR) have witnessed a lot of impressive results. Depending on our observation, although more layers and connections could always improve performance, the increase of model parameters is not conducive to launch application of SR algorithms. Furthermore, algorithms supervised by L1/L2 loss can achieve considerable performance on traditional metrics such as PSNR and SSIM, yet resulting in blurry and over-smoothed outputs without sufficient high-frequency details, namely low perceptual index(PI). Regarding the issues, this paper develops a perception-oriented single image SR algorithm via dual relativistic average generative adversarial networks. In the generator part, a novel residual channel attention block is proposed to recalibrate significance of specific channels, further increasing feature expression capabilities. Parameters of convolutional layers within each block are shared to expand receptive fields while maintain the amount of tunable parameters unchanged. The feature maps are subsampled using sub-pixel convolution to obtain reconstructed high-resolution images. The discriminator part consists of two relativistic average discriminators that work in pixel domain and feature domain, respectively, fully exploiting the prior that half of data in a mini-batch are fake. Different weighted combinations of perceptual loss and adversarial loss are utilized to supervise the generator to equilibrate perceptual quality and objective results. Experimental results and ablation studies show that our proposed algorithm can rival state-of-the-art SR algorithms, both perceptually(PI-minimization) and objectively(PSNR-maximization) with fewer parameters. |
| Tasks | Image Super-Resolution, Super-Resolution |
| Published | 2019-11-08 |
| URL | https://arxiv.org/abs/1911.03464v3 |
| https://arxiv.org/pdf/1911.03464v3.pdf | |
| PWC | https://paperswithcode.com/paper/image-super-resolution-via-residual-blended |
| Repo | |
| Framework | |
