Paper Group ANR 1593
An Unsupervised, Iterative N-Dimensional Point-Set Registration Algorithm. Neural Cross-Domain Collaborative Filtering with Shared Entities. Automatic Critical Mechanic Discovery in Video Games. Dynamic fairness - Breaking vicious cycles in automatic decision making. To Learn or Not to Learn: Analyzing the Role of Learning for Navigation in Virtual …
An Unsupervised, Iterative N-Dimensional Point-Set Registration Algorithm
| Title | An Unsupervised, Iterative N-Dimensional Point-Set Registration Algorithm |
| Authors | A. Pasha Hosseinbor, R. Zhdanov, A. Ushveridze |
| Abstract | An unsupervised, iterative point-set registration algorithm for an unlabeled (i.e. correspondence between points is unknown) N-dimensional Euclidean point-cloud is proposed. It is based on linear least squares, and considers all possible point pairings and iteratively aligns the two sets until the number of point pairs does not exceed the maximum number of allowable one-to-one pairings. |
| Tasks | |
| Published | 2019-08-06 |
| URL | https://arxiv.org/abs/1908.04384v1 |
| https://arxiv.org/pdf/1908.04384v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-unsupervised-iterative-n-dimensional-point |
| Repo | |
| Framework | |
Neural Cross-Domain Collaborative Filtering with Shared Entities
| Title | Neural Cross-Domain Collaborative Filtering with Shared Entities |
| Authors | Vijaikumar M, Shirish Shevade, M N Murty |
| Abstract | Cross-Domain Collaborative Filtering (CDCF) provides a way to alleviate data sparsity and cold-start problems present in recommendation systems by exploiting the knowledge from related domains. Existing CDCF models are either based on matrix factorization or deep neural networks. Either of the techniques in isolation may result in suboptimal performance for the prediction task. Also, most of the existing models face challenges particularly in handling diversity between domains and learning complex non-linear relationships that exist amongst entities (users/items) within and across domains. In this work, we propose an end-to-end neural network model – NeuCDCF, to address these challenges in a cross-domain setting. More importantly, NeuCDCF follows a wide and deep framework and it learns the representations combinedly from both matrix factorization and deep neural networks. We perform experiments on four real-world datasets and demonstrate that our model performs better than state-of-the-art CDCF models. |
| Tasks | Recommendation Systems |
| Published | 2019-07-19 |
| URL | https://arxiv.org/abs/1907.08440v1 |
| https://arxiv.org/pdf/1907.08440v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-cross-domain-collaborative-filtering |
| Repo | |
| Framework | |
Automatic Critical Mechanic Discovery in Video Games
| Title | Automatic Critical Mechanic Discovery in Video Games |
| Authors | Michael Cerny Green, Ahmed Khalifa, Gabriella A. B. Barros, Tiago Machado, Julian Togelius |
| Abstract | We present a new method of automatic critical mechanic discovery for video games using a combination of game description parsing and playtrace information. This method is applied to several games within the General Video Game Artificial Intelligence (GVG-AI) framework. In a user study, human-identified mechanics are compared against system-identified critical mechanics to verify alignment between humans and the system. The results of the study demonstrate that the new method is able to match humans with higher consistency than baseline. Our system is further validated by comparing MCTS agents augmented with critical mechanics and vanilla MCTS agents on 4 games from GVG-AI. Our new playtrace method shows a significant performance improvement over the baseline for all 4 tested games. The proposed method also shows either matched or improved performance over the old method, demonstrating that playtrace information is responsible for more complete critical mechanic discovery. |
| Tasks | |
| Published | 2019-09-06 |
| URL | https://arxiv.org/abs/1909.03094v2 |
| https://arxiv.org/pdf/1909.03094v2.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-critical-mechanic-discovery-in |
| Repo | |
| Framework | |
Dynamic fairness - Breaking vicious cycles in automatic decision making
| Title | Dynamic fairness - Breaking vicious cycles in automatic decision making |
| Authors | Benjamin Paaßen, Astrid Bunge, Carolin Hainke, Leon Sindelar, Matthias Vogelsang |
| Abstract | In recent years, machine learning techniques have been increasingly applied in sensitive decision making processes, raising fairness concerns. Past research has shown that machine learning may reproduce and even exacerbate human bias due to biased training data or flawed model assumptions, and thus may lead to discriminatory actions. To counteract such biased models, researchers have proposed multiple mathematical definitions of fairness according to which classifiers can be optimized. However, it has also been shown that the outcomes generated by some fairness notions may be unsatisfactory. In this contribution, we add to this research by considering decision making processes in time. We establish a theoretic model in which even perfectly accurate classifiers which adhere to almost all common fairness definitions lead to stable long-term inequalities due to vicious cycles. Only demographic parity, which enforces equal rates of positive decisions across groups, avoids these effects and establishes a virtuous cycle, which leads to perfectly accurate and fair classification in the long term. |
| Tasks | Decision Making |
| Published | 2019-02-01 |
| URL | http://arxiv.org/abs/1902.00375v2 |
| http://arxiv.org/pdf/1902.00375v2.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-fairness-breaking-vicious-cycles-in |
| Repo | |
| Framework | |
To Learn or Not to Learn: Analyzing the Role of Learning for Navigation in Virtual Environments
| Title | To Learn or Not to Learn: Analyzing the Role of Learning for Navigation in Virtual Environments |
| Authors | Noriyuki Kojima, Jia Deng |
| Abstract | In this paper we compare learning-based methods and classical methods for navigation in virtual environments. We construct classical navigation agents and demonstrate that they outperform state-of-the-art learning-based agents on two standard benchmarks: MINOS and Stanford Large-Scale 3D Indoor Spaces. We perform detailed analysis to study the strengths and weaknesses of learned agents and classical agents, as well as how characteristics of the virtual environment impact navigation performance. Our results show that learned agents have inferior collision avoidance and memory management, but are superior in handling ambiguity and noise. These results can inform future design of navigation agents. |
| Tasks | |
| Published | 2019-07-26 |
| URL | https://arxiv.org/abs/1907.11770v1 |
| https://arxiv.org/pdf/1907.11770v1.pdf | |
| PWC | https://paperswithcode.com/paper/to-learn-or-not-to-learn-analyzing-the-role |
| Repo | |
| Framework | |
Weakly supervised training of pixel resolution segmentation models on whole slide images
| Title | Weakly supervised training of pixel resolution segmentation models on whole slide images |
| Authors | Nicolas Pinchaud |
| Abstract | We present a novel approach to train pixel resolution segmentation models on whole slide images in a weakly supervised setup. The model is trained to classify patches extracted from slides. This leads the training to be made under noisy labeled data. We solve the problem with two complementary strategies. First, the patches are sampled online using the model’s knowledge by focusing on regions where the model’s confidence is higher. Second, we propose an extension of the KL divergence that is robust to noisy labels. Our preliminary experiment on CAMELYON 16 data set show promising results. The model can successfully segment tumor areas with strong morphological consistency. |
| Tasks | |
| Published | 2019-05-30 |
| URL | https://arxiv.org/abs/1905.12931v2 |
| https://arxiv.org/pdf/1905.12931v2.pdf | |
| PWC | https://paperswithcode.com/paper/weakly-supervised-training-of-pixel |
| Repo | |
| Framework | |
Leveraging synthetic imagery for collision-at-sea avoidance
| Title | Leveraging synthetic imagery for collision-at-sea avoidance |
| Authors | Chris M. Ward, Josh Harguess, Alexander G. Corelli |
| Abstract | Maritime collisions involving multiple ships are considered rare, but in 2017 several United States Navy vessels were involved in fatal at-sea collisions that resulted in the death of seventeen American Servicemembers. The experimentation introduced in this paper is a direct response to these incidents. We propose a shipboard Collision-At-Sea avoidance system, based on video image processing, that will help ensure the safe stationing and navigation of maritime vessels. Our system leverages a convolutional neural network trained on synthetic maritime imagery in order to detect nearby vessels within a scene, perform heading analysis of detected vessels, and provide an alert in the presence of an inbound vessel. Additionally, we present the Navigational Hazards - Synthetic (NAVHAZ-Synthetic) dataset. This dataset, is comprised of one million annotated images of ten vessel classes observed from virtual vessel-mounted cameras, as well as a human “Topside Lookout” perspective. NAVHAZ-Synthetic includes imagery displaying varying sea-states, lighting conditions, and optical degradations such as fog, sea-spray, and salt-accumulation. We present our results on the use of synthetic imagery in a computer vision based collision-at-sea warning system with promising performance. |
| Tasks | |
| Published | 2019-05-13 |
| URL | https://arxiv.org/abs/1905.04828v1 |
| https://arxiv.org/pdf/1905.04828v1.pdf | |
| PWC | https://paperswithcode.com/paper/leveraging-synthetic-imagery-for-collision-at |
| Repo | |
| Framework | |
Classical Policy Gradient: Preserving Bellman’s Principle of Optimality
| Title | Classical Policy Gradient: Preserving Bellman’s Principle of Optimality |
| Authors | Philip S. Thomas, Scott M. Jordan, Yash Chandak, Chris Nota, James Kostas |
| Abstract | We propose a new objective function for finite-horizon episodic Markov decision processes that better captures Bellman’s principle of optimality, and provide an expression for the gradient of the objective. |
| Tasks | |
| Published | 2019-06-06 |
| URL | https://arxiv.org/abs/1906.03063v1 |
| https://arxiv.org/pdf/1906.03063v1.pdf | |
| PWC | https://paperswithcode.com/paper/classical-policy-gradient-preserving-bellmans |
| Repo | |
| Framework | |
Randomized Riemannian Preconditioning for Quadratically Constrained Problems
| Title | Randomized Riemannian Preconditioning for Quadratically Constrained Problems |
| Authors | Boris Shustin, Haim Avron |
| Abstract | Optimization problem with quadratic equality constraints are prevalent in machine learning. Indeed, two important examples are Canonical Correlation Analysis (CCA) and Linear Discriminant Analysis (LDA). Unfortunately, methods for solving such problems typically involve computing matrix inverses and decomposition. For the aforementioned problems, these matrices are actually Gram matrices of input data matrices, and as such the computations are too expensive for large scale datasets. In this paper, we propose a sketching based approach for solving CCA and LDA that reduces the cost dependence on the input size. The proposed algorithms feature randomized preconditioning combined with Riemannian optimization. |
| Tasks | |
| Published | 2019-02-05 |
| URL | http://arxiv.org/abs/1902.01635v1 |
| http://arxiv.org/pdf/1902.01635v1.pdf | |
| PWC | https://paperswithcode.com/paper/randomized-riemannian-preconditioning-for |
| Repo | |
| Framework | |
SVRG for Policy Evaluation with Fewer Gradient Evaluations
| Title | SVRG for Policy Evaluation with Fewer Gradient Evaluations |
| Authors | Zilun Peng, Ahmed Touati, Pascal Vincent, Doina Precup |
| Abstract | Stochastic variance-reduced gradient (SVRG) is an optimization method originally designed for tackling machine learning problems with a finite sum structure. SVRG was later shown to work for policy evaluation, a problem in reinforcement learning in which one aims to estimate the value function of a given policy. SVRG makes use of gradient estimates at two scales. At the slower scale, SVRG computes a full gradient over the whole dataset, which could lead to prohibitive computation costs. In this work, we show that two variants of SVRG for policy evaluation could significantly diminish the number of gradient calculations while preserving a linear convergence speed. More importantly, our theoretical result implies that one does not need to use the entire dataset in every epoch of SVRG when it is applied to policy evaluation with linear function approximation. Our experiments demonstrate large computational savings provided by the proposed methods. |
| Tasks | |
| Published | 2019-06-09 |
| URL | https://arxiv.org/abs/1906.03704v1 |
| https://arxiv.org/pdf/1906.03704v1.pdf | |
| PWC | https://paperswithcode.com/paper/svrg-for-policy-evaluation-with-fewer |
| Repo | |
| Framework | |
W-Net: A CNN-based Architecture for White Blood Cells Image Classification
| Title | W-Net: A CNN-based Architecture for White Blood Cells Image Classification |
| Authors | Changhun Jung, Mohammed Abuhamad, Jumabek Alikhanov, Aziz Mohaisen, Kyungja Han, DaeHun Nyang |
| Abstract | Computer-aided methods for analyzing white blood cells (WBC) have become widely popular due to the complexity of the manual process. Recent works have shown highly accurate segmentation and detection of white blood cells from microscopic blood images. However, the classification of the observed cells is still a challenge and highly demanded as the distribution of the five types reflects on the condition of the immune system. This work proposes W-Net, a CNN-based method for WBC classification. We evaluate W-Net on a real-world large-scale dataset, obtained from The Catholic University of Korea, that includes 6,562 real images of the five WBC types. W-Net achieves an average accuracy of 97%. |
| Tasks | Image Classification |
| Published | 2019-10-02 |
| URL | https://arxiv.org/abs/1910.01091v1 |
| https://arxiv.org/pdf/1910.01091v1.pdf | |
| PWC | https://paperswithcode.com/paper/w-net-a-cnn-based-architecture-for-white |
| Repo | |
| Framework | |
KINN: Incorporating Expert Knowledge in Neural Networks
| Title | KINN: Incorporating Expert Knowledge in Neural Networks |
| Authors | Muhammad Ali Chattha, Shoaib Ahmed Siddiqui, Muhammad Imran Malik, Ludger van Elst, Andreas Dengel, Sheraz Ahmed |
| Abstract | The promise of ANNs to automatically discover and extract useful features/patterns from data without dwelling on domain expertise although seems highly promising but comes at the cost of high reliance on large amount of accurately labeled data, which is often hard to acquire and formulate especially in time-series domains like anomaly detection, natural disaster management, predictive maintenance and healthcare. As these networks completely rely on data and ignore a very important modality i.e. expert, they are unable to harvest any benefit from the expert knowledge, which in many cases is very useful. In this paper, we try to bridge the gap between these data driven and expert knowledge based systems by introducing a novel framework for incorporating expert knowledge into the network (KINN). Integrating expert knowledge into the network has three key advantages: (a) Reduction in the amount of data needed to train the model, (b) provision of a lower bound on the performance of the resulting classifier by obtaining the best of both worlds, and (c) improved convergence of model parameters (model converges in smaller number of epochs). Although experts are extremely good in solving different tasks, there are some trends and patterns, which are usually hidden only in the data. Therefore, KINN employs a novel residual knowledge incorporation scheme, which can automatically determine the quality of the predictions made by the expert and rectify it accordingly by learning the trends/patterns from data. Specifically, the method tries to use information contained in one modality to complement information missed by the other. We evaluated KINN on a real world traffic flow prediction problem. KINN significantly superseded performance of both the expert and as well as the base network (LSTM in this case) when evaluated in isolation, highlighting its superiority for the task. |
| Tasks | Anomaly Detection, Time Series |
| Published | 2019-02-15 |
| URL | http://arxiv.org/abs/1902.05653v1 |
| http://arxiv.org/pdf/1902.05653v1.pdf | |
| PWC | https://paperswithcode.com/paper/kinn-incorporating-expert-knowledge-in-neural |
| Repo | |
| Framework | |
Knowledge Induced Deep Q-Network for a Slide-to-Wall Object Grasping
| Title | Knowledge Induced Deep Q-Network for a Slide-to-Wall Object Grasping |
| Authors | Hengyue Liang, Xibai Lou, Changhyun Choi |
| Abstract | In robotic grasping tasks, robots usually avoid any collisions with the environment and exclusively interact with the target objects. However, the environment can facilitate grasping rather than being obstacles. Indeed, interacting with the environment sometimes provides an alternative strategy when it is not possible to grasp from the top. One example of such tasks is the Slide-to-Wall grasping, where the target object needs to be pushed towards a wall before a feasible grasp can be applied. In this paper, we propose an approach that actively exploits the environment to grasp objects. We formulate the Slide-to-Wall grasping problem as a Markov Decision Process and propose a reinforcement learning approach. Though a standard Deep Q-Network (DQN) method is capable of solving MDP problems, it does not effectively generalize to unseen environment settings that are different from training. To tackle the generalization challenge, we propose a Knowledge Induced DQN (KI-DQN) that not only trains more effectively, but also outperforms the standard DQN significantly in testing cases with unseen walls, and can be directly tested on real robots without fine-tuning while DQN cannot. |
| Tasks | Robotic Grasping |
| Published | 2019-10-09 |
| URL | https://arxiv.org/abs/1910.03781v1 |
| https://arxiv.org/pdf/1910.03781v1.pdf | |
| PWC | https://paperswithcode.com/paper/knowledge-induced-deep-q-network-for-a-slide |
| Repo | |
| Framework | |
Deep Node Ranking: Structural Network Embedding and End-to-End Node Classification
| Title | Deep Node Ranking: Structural Network Embedding and End-to-End Node Classification |
| Authors | Blaž Škrlj, Jan Kralj, Janez Konc, Marko Robnik-Šikonja, Nada Lavrač |
| Abstract | Complex networks are used as an abstraction for systems modeling in physics, biology, sociology, and other areas. We propose an algorithm, named Deep Node Ranking (DNR), based on fast personalized node ranking and raw approximation power of deep learning for learning supervised and unsupervised network embeddings as well as for classifying network nodes directly. The experiments demonstrate that the DNR algorithm is competitive with strong baselines on nine node classification benchmarks from the domains of molecular biology, finance, social media and language processing in terms of speed, as well as predictive accuracy. Embeddings, obtained by the proposed algorithm, are also a viable option for network visualization. |
| Tasks | Network Embedding, Node Classification |
| Published | 2019-02-11 |
| URL | http://arxiv.org/abs/1902.03964v4 |
| http://arxiv.org/pdf/1902.03964v4.pdf | |
| PWC | https://paperswithcode.com/paper/deep-node-ranking-an-algorithm-for-structural |
| Repo | |
| Framework | |
Combining Deep Learning and Verification for Precise Object Instance Detection
| Title | Combining Deep Learning and Verification for Precise Object Instance Detection |
| Authors | Siddharth Ancha, Junyu Nan, David Held |
| Abstract | Deep learning object detectors often return false positives with very high confidence. Although they optimize generic detection performance, such as mean average precision (mAP), they are not designed for reliability. For a reliable detection system, if a high confidence detection is made, we would want high certainty that the object has indeed been detected. To achieve this, we have developed a set of verification tests which a proposed detection must pass to be accepted. We develop a theoretical framework which proves that, under certain assumptions, our verification tests will not accept any false positives. Based on an approximation to this framework, we present a practical detection system that can verify, with high precision, whether each detection of a machine-learning based object detector is correct. We show that these tests can improve the overall accuracy of a base detector and that accepted examples are highly likely to be correct. This allows the detector to operate in a high precision regime and can thus be used for robotic perception systems as a reliable instance detection method. |
| Tasks | |
| Published | 2019-12-27 |
| URL | https://arxiv.org/abs/1912.12270v1 |
| https://arxiv.org/pdf/1912.12270v1.pdf | |
| PWC | https://paperswithcode.com/paper/combining-deep-learning-and-verification-for |
| Repo | |
| Framework | |
