Paper Group ANR 630
Redirection Controller Using Reinforcement Learning. Robust Learning-based Predictive Control for Constrained Nonlinear Systems. Polynomial-time Updates of Epistemic States in a Fragment of Probabilistic Epistemic Argumentation (Technical Report). Supervized Segmentation with Graph-Structured Deep Metric Learning. A Many Objective Optimization Appr …
Redirection Controller Using Reinforcement Learning
| Title | Redirection Controller Using Reinforcement Learning |
| Authors | Yuchen Chang, Keigo Matsumoto, Takuji Narumi, Tomohiro Tanikawa, Michitaka Hirose |
| Abstract | There is a growing demand for planning redirected walking techniques and applying them to physical environments with obstacles. Such techniques are mainly managed using three kinds of methods: direct scripting, generalized controller, and physical- or virtual-environment analysis to determine user redirection. The first approach is effective when a user’s path and both physical and virtual environments are fixed; however, it is difficult to handle irregular movements and reuse other environments. The second approach has the potential of reusing any environment but is less optimized. The last approach is highly anticipated and versatile, although it has not been sufficiently developed. In this study, we propose a novel redirection controller using reinforcement learning with advanced plannability/versatility. Our simulation experiments show that the proposed strategy can reduce the number of resets by 20.3% for physical-space conditions with multiple obstacles. |
| Tasks | |
| Published | 2019-09-20 |
| URL | https://arxiv.org/abs/1909.09505v2 |
| https://arxiv.org/pdf/1909.09505v2.pdf | |
| PWC | https://paperswithcode.com/paper/redirection-controller-using-reinforcement |
| Repo | |
| Framework | |
Robust Learning-based Predictive Control for Constrained Nonlinear Systems
| Title | Robust Learning-based Predictive Control for Constrained Nonlinear Systems |
| Authors | Xinglong Zhang, Jiahang Liu, Xin Xu, Hong Chen |
| Abstract | The integration of machine learning methods and Model Predictive Control (MPC) has received increasing attention in recent years. In general, learning-based predictive control (LPC) is promising to build data-driven models and solve the online optimization problem with lower computational costs. However, the robustness of LPC is difficult to be guaranteed since there will be uncertainties due to function approximation used in machine learning algorithms. In this paper, a novel robust learning-based predictive control (r-LPC) scheme is proposed for constrained nonlinear systems with unknown dynamics. In r-LPC, the Koopman operator is used to form a global linear representation of the unknown dynamics, and an incremental actor-critic algorithm is presented for receding horizon optimization. To realize the satisfaction of system constraints, soft logarithmic barrier functions are designed within the learning predictive framework. The recursive feasibility and stability of the closed-loop system are discussed under the convergence arguments of the approximation algorithms adopted. Also, the robustness property of r-LPC is analyzed theoretically by taking into consideration the existence of perturbations on the controller due to possible approximation errors. Simulation results with the proposed learning control approach for the data-driven regulation of a Van der Pol oscillator system have been reported, including the comparisons with a classic MPC and an infinite-horizon Dual Heuristic Programming (DHP) algorithm. The results show that the r-LPC significantly outperforms the DHP algorithm in terms of control performance and can be comparative to the MPC in terms of regulating control as well as energy consumption. Moreover, its average computational cost is much smaller than that with the MPC in the adopted environment. |
| Tasks | |
| Published | 2019-11-22 |
| URL | https://arxiv.org/abs/1911.09827v1 |
| https://arxiv.org/pdf/1911.09827v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-learning-based-predictive-control-for |
| Repo | |
| Framework | |
Polynomial-time Updates of Epistemic States in a Fragment of Probabilistic Epistemic Argumentation (Technical Report)
| Title | Polynomial-time Updates of Epistemic States in a Fragment of Probabilistic Epistemic Argumentation (Technical Report) |
| Authors | Nico Potyka, Sylwia Polberg, Anthony Hunter |
| Abstract | Probabilistic epistemic argumentation allows for reasoning about argumentation problems in a way that is well founded by probability theory. Epistemic states are represented by probability functions over possible worlds and can be adjusted to new beliefs using update operators. While the use of probability functions puts this approach on a solid foundational basis, it also causes computational challenges as the amount of data to process depends exponentially on the number of arguments. This leads to bottlenecks in applications such as modelling opponent’s beliefs for persuasion dialogues. We show how update operators over probability functions can be related to update operators over much more compact representations that allow polynomial-time updates. We discuss the cognitive and probabilistic-logical plausibility of this approach and demonstrate its applicability in computational persuasion. |
| Tasks | |
| Published | 2019-06-12 |
| URL | https://arxiv.org/abs/1906.05066v1 |
| https://arxiv.org/pdf/1906.05066v1.pdf | |
| PWC | https://paperswithcode.com/paper/polynomial-time-updates-of-epistemic-states |
| Repo | |
| Framework | |
Supervized Segmentation with Graph-Structured Deep Metric Learning
| Title | Supervized Segmentation with Graph-Structured Deep Metric Learning |
| Authors | Loic Landrieu, Mohamed Boussaha |
| Abstract | We present a fully-supervized method for learning to segment data structured by an adjacency graph. We introduce the graph-structured contrastive loss, a loss function structured by a ground truth segmentation. It promotes learning vertex embeddings which are homogeneous within desired segments, and have high contrast at their interface. Thus, computing a piecewise-constant approximation of such embeddings produces a graph-partition close to the objective segmentation. This loss is fully backpropagable, which allows us to learn vertex embeddings with deep learning algorithms. We evaluate our methods on a 3D point cloud oversegmentation task, defining a new state-of-the-art by a large margin. These results are based on the published work of Landrieu and Boussaha 2019. |
| Tasks | Metric Learning |
| Published | 2019-05-10 |
| URL | https://arxiv.org/abs/1905.04014v2 |
| https://arxiv.org/pdf/1905.04014v2.pdf | |
| PWC | https://paperswithcode.com/paper/supervized-segmentation-with-graph-structured |
| Repo | |
| Framework | |
A Many Objective Optimization Approach for Transfer Learning in EEG Classification
| Title | A Many Objective Optimization Approach for Transfer Learning in EEG Classification |
| Authors | Monalisa Pal, Sanghamitra Bandyopadhyay, Saugat Bhattacharyya |
| Abstract | In Brain-Computer Interfacing (BCI), due to inter-subject non-stationarities of electroencephalogram (EEG), classifiers are trained and tested using EEG from the same subject. When physical disabilities bottleneck the natural modality of performing a task, acquisition of ample training data is difficult which practically obstructs classifier training. Previous works have tackled this problem by generalizing the feature space amongst multiple subjects including the test subject. This work aims at knowledge transfer to classify EEG of the target subject using a classifier trained with the EEG of another unit source subject. A many-objective optimization framework is proposed where optimal weights are obtained for projecting features in another dimension such that single source-trained target EEG classification performance is maximized with the modified features. To validate the approach, motor imagery tasks from the BCI Competition III Dataset IVa are classified using power spectral density based features and linear support vector machine. Several performance metrics, improvement in accuracy, sensitivity to the dimension of the projected space, assess the efficacy of the proposed approach. Addressing single-source training promotes independent living of differently-abled individuals by reducing assistance from others. The proposed approach eliminates the requirement of EEG from multiple source subjects and is applicable to any existing feature extractors and classifiers. Source code is available at http://worksupplements.droppages.com/tlbci.html. |
| Tasks | EEG, Transfer Learning |
| Published | 2019-04-04 |
| URL | http://arxiv.org/abs/1904.04156v1 |
| http://arxiv.org/pdf/1904.04156v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-many-objective-optimization-approach-for |
| Repo | |
| Framework | |
Representative Task Self-selection for Flexible Clustered Lifelong Learning
| Title | Representative Task Self-selection for Flexible Clustered Lifelong Learning |
| Authors | Gan Sun, Yang Cong, Qianqian Wang, Bineng Zhong, Yun Fu |
| Abstract | Consider the lifelong machine learning paradigm whose objective is to learn a sequence of tasks depending on previous experiences, e.g., knowledge library or deep network weights. However, the knowledge libraries or deep networks for most recent lifelong learning models are with prescribed size, and can degenerate the performance for both learned tasks and coming ones when facing with a new task environment (cluster). To address this challenge, we propose a novel incremental clustered lifelong learning framework with two knowledge libraries: feature learning library and model knowledge library, called Flexible Clustered Lifelong Learning (FCL3). Specifically, the feature learning library modeled by an autoencoder architecture maintains a set of representation common across all the observed tasks, and the model knowledge library can be self-selected by identifying and adding new representative models (clusters). When a new task arrives, our proposed FCL3model firstly transfers knowledge from these libraries to encode the new task, i.e.,effectively and selectively soft-assigning this new task to multiple representative models over feature learning library. Then, 1) the new task with a higher outlier probability will be judged as a new representative, and used to redefine both feature learning library and representative models over time; or 2) the new task with lower outlier probability will only refine the feature learning library. For model optimization, we cast this lifelong learning problem as an alternating direction minimization problem as a new task comes. Finally, we evaluate the proposed framework by analyzing several multi-task datasets, and the experimental results demonstrate that our FCL3 model can achieve better performance than most lifelong learning frameworks, even batch clustered multi-task learning models. |
| Tasks | Multi-Task Learning |
| Published | 2019-03-06 |
| URL | https://arxiv.org/abs/1903.02173v2 |
| https://arxiv.org/pdf/1903.02173v2.pdf | |
| PWC | https://paperswithcode.com/paper/representative-task-self-selection-for |
| Repo | |
| Framework | |
Deep Radar Detector
| Title | Deep Radar Detector |
| Authors | Daniel Brodeski, Igal Bilik, Raja Giryes |
| Abstract | While camera and LiDAR processing have been revolutionized since the introduction of deep learning, radar processing still relies on classical tools. In this paper, we introduce a deep learning approach for radar processing, working directly with the radar complex data. To overcome the lack of radar labeled data, we rely in training only on the radar calibration data and introduce new radar augmentation techniques. We evaluate our method on the radar 4D detection task and demonstrate superior performance compared to the classical approaches while keeping real-time performance. Applying deep learning on radar data has several advantages such as eliminating the need for an expensive radar calibration process each time and enabling classification of the detected objects with almost zero-overhead. |
| Tasks | Calibration |
| Published | 2019-06-26 |
| URL | https://arxiv.org/abs/1906.12187v1 |
| https://arxiv.org/pdf/1906.12187v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-radar-detector |
| Repo | |
| Framework | |
Sublinear quantum algorithms for training linear and kernel-based classifiers
| Title | Sublinear quantum algorithms for training linear and kernel-based classifiers |
| Authors | Tongyang Li, Shouvanik Chakrabarti, Xiaodi Wu |
| Abstract | We investigate quantum algorithms for classification, a fundamental problem in machine learning, with provable guarantees. Given $n$ $d$-dimensional data points, the state-of-the-art (and optimal) classical algorithm for training classifiers with constant margin runs in $\tilde{O}(n+d)$ time. We design sublinear quantum algorithms for the same task running in $\tilde{O}(\sqrt{n} +\sqrt{d})$ time, a quadratic improvement in both $n$ and $d$. Moreover, our algorithms use the standard quantization of the classical input and generate the same classical output, suggesting minimal overheads when used as subroutines for end-to-end applications. We also demonstrate a tight lower bound (up to poly-log factors) and discuss the possibility of implementation on near-term quantum machines. As a side result, we also give sublinear quantum algorithms for approximating the equilibria of $n$-dimensional matrix zero-sum games with optimal complexity $\tilde{\Theta}(\sqrt{n})$. |
| Tasks | Quantization |
| Published | 2019-04-04 |
| URL | http://arxiv.org/abs/1904.02276v1 |
| http://arxiv.org/pdf/1904.02276v1.pdf | |
| PWC | https://paperswithcode.com/paper/sublinear-quantum-algorithms-for-training |
| Repo | |
| Framework | |
Automated Detection and Type Classification of Central Venous Catheters in Chest X-Rays
| Title | Automated Detection and Type Classification of Central Venous Catheters in Chest X-Rays |
| Authors | Vaishnavi Subramanian, Hongzhi Wang, Joy T. Wu, Ken C. L. Wong, Arjun Sharma, Tanveer Syeda-Mahmood |
| Abstract | Central venous catheters (CVCs) are commonly used in critical care settings for monitoring body functions and administering medications. They are often described in radiology reports by referring to their presence, identity and placement. In this paper, we address the problem of automatic detection of their presence and identity through automated segmentation using deep learning networks and classification based on their intersection with previously learned shape priors from clinician annotations of CVCs. The results not only outperform existing methods of catheter detection achieving 85.2% accuracy at 91.6% precision, but also enable high precision (95.2%) classification of catheter types on a large dataset of over 10,000 chest X-rays, presenting a robust and practical solution to this problem. |
| Tasks | |
| Published | 2019-07-02 |
| URL | https://arxiv.org/abs/1907.01656v3 |
| https://arxiv.org/pdf/1907.01656v3.pdf | |
| PWC | https://paperswithcode.com/paper/automated-detection-and-type-classification |
| Repo | |
| Framework | |
Compressing deep quaternion neural networks with targeted regularization
| Title | Compressing deep quaternion neural networks with targeted regularization |
| Authors | Riccardo Vecchi, Simone Scardapane, Danilo Comminiello, Aurelio Uncini |
| Abstract | In recent years, hyper-complex deep networks (e.g., quaternion-based) have received increasing interest with applications ranging from image reconstruction to 3D audio processing. Similarly to their real-valued counterparts, quaternion neural networks might require custom regularization strategies to avoid overfitting. In addition, for many real-world applications and embedded implementations there is the need of designing sufficiently compact networks, with as few weights and units as possible. However, the problem of how to regularize and/or sparsify quaternion-valued networks has not been properly addressed in the literature as of now. In this paper we show how to address both problems by designing targeted regularization strategies, able to minimize the number of connections and neurons of the network during training. To this end, we investigate two extensions of $\ell_1$ and structured regularization to the quaternion domain. In our experimental evaluation, we show that these tailored strategies significantly outperform classical (real-valued) regularization strategies, resulting in small networks especially suitable for low-power and real-time applications. |
| Tasks | Image Reconstruction |
| Published | 2019-07-26 |
| URL | https://arxiv.org/abs/1907.11546v2 |
| https://arxiv.org/pdf/1907.11546v2.pdf | |
| PWC | https://paperswithcode.com/paper/compressing-deep-quaternion-neural-networks |
| Repo | |
| Framework | |
BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning
| Title | BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning |
| Authors | Xinyue Chen, Zijian Zhou, Zheng Wang, Che Wang, Yanqiu Wu, Keith Ross |
| Abstract | The field of Deep Reinforcement Learning (DRL) has recently seen a surge in research in batch reinforcement learning, which aims for sample-efficient learning from a given data set without additional interactions with the environment. In the batch DRL setting, commonly employed off-policy DRL algorithms can perform poorly and sometimes even fail to learn altogether. In this paper, we propose a new algorithm, Best-Action Imitation Learning (BAIL), which unlike many off-policy DRL algorithms does not involve maximizing Q functions over the action space. Striving for simplicity as well as performance, BAIL first selects from the batch the actions it believes to be high-performing actions for their corresponding states; it then uses those state-action pairs to train a policy network using imitation learning. Although BAIL is simple, we demonstrate that BAIL achieves state of the art performance on the Mujoco benchmark. |
| Tasks | Imitation Learning |
| Published | 2019-10-27 |
| URL | https://arxiv.org/abs/1910.12179v2 |
| https://arxiv.org/pdf/1910.12179v2.pdf | |
| PWC | https://paperswithcode.com/paper/bail-best-action-imitation-learning-for-batch-1 |
| Repo | |
| Framework | |
Automated Text Summarization for the Enhancement of Public Services
| Title | Automated Text Summarization for the Enhancement of Public Services |
| Authors | Xingbang Liu, Janyl Jumadinova |
| Abstract | Natural language processing and machine learning algorithms have been shown to be effective in a variety of applications. In this work, we contribute to the area of AI adoption in the public sector. We present an automated system that was used to process textual information, generate important keywords, and automatically summarize key elements of the Meadville community statements. We also describe the process of collaboration with My Meadville administrators during the development of our system. My Meadville, a community initiative, supported by the city of Meadville conducted a large number of interviews with the residents of Meadville during the community events and transcribed these interviews into textual data files. Their goal was to uncover the issues of importance to the Meadville residents in an attempt to enhance public services. Our AI system cleans and pre-processes the interview data, then using machine learning algorithms it finds important keywords and key excerpts from each interview. It also provides searching functionality to find excerpts from relevant interviews based on specific keywords. Our automated system allowed the city to save over 300 hours of human labor that would have taken to read all interviews and highlight important points. Our findings are being used by My Meadville initiative to locate important information from the collected data set for ongoing community enhancement projects, to highlight relevant community assets, and to assist in identifying the steps to be taken based on the concerns and areas of improvement identified by the community members. |
| Tasks | Text Summarization |
| Published | 2019-10-16 |
| URL | https://arxiv.org/abs/1910.10490v1 |
| https://arxiv.org/pdf/1910.10490v1.pdf | |
| PWC | https://paperswithcode.com/paper/automated-text-summarization-for-the |
| Repo | |
| Framework | |
Action Prediction in Humans and Robots
| Title | Action Prediction in Humans and Robots |
| Authors | Florentin Wörgötter, Fatemeh Ziaeetabar, Stefan Pfeiffer, Osman Kaya, Tomas Kulvicius, Minija Tamosiunaite |
| Abstract | Efficient action prediction is of central importance for the fluent workflow between humans and equally so for human-robot interaction. To achieve prediction, actions can be encoded by a series of events, where every event corresponds to a change in a (static or dynamic) relation between some of the objects in a scene. Manipulation actions and others can be uniquely encoded this way and only, on average, less than 60% of the time series has to pass until an action can be predicted. Using a virtual reality setup and testing ten different manipulation actions, here we show that in most cases humans predict actions at the same event as the algorithm. In addition, we perform an in-depth analysis about the temporal gain resulting from such predictions when chaining actions and show in some robotic experiments that the percentage gain for humans and robots is approximately equal. Thus, if robots use this algorithm then their prediction-moments will be compatible to those of their human interaction partners, which should much benefit natural human-robot collaboration. |
| Tasks | Time Series |
| Published | 2019-07-03 |
| URL | https://arxiv.org/abs/1907.01932v1 |
| https://arxiv.org/pdf/1907.01932v1.pdf | |
| PWC | https://paperswithcode.com/paper/action-prediction-in-humans-and-robots |
| Repo | |
| Framework | |
Array Languages Make Neural Networks Fast
| Title | Array Languages Make Neural Networks Fast |
| Authors | Artjoms Šinkarovs, Hans-Nikolai Vießmann, Sven-Bodo Scholz |
| Abstract | Modern machine learning frameworks are complex: they are typically organised in multiple layers each of which is written in a different language and they depend on a number of external libraries, but at their core they mainly consist of tensor operations. As array-oriented languages provide perfect abstractions to implement tensor operations, we consider a minimalistic machine learning framework that is shallowly embedded in an array-oriented language and we study its productivity and performance. We do this by implementing a state of the art Convolutional Neural Network (CNN) and compare it against implementations in TensorFlow and PyTorch — two state of the art industrial-strength frameworks. It turns out that our implementation is 2 and 3 times faster, even after fine-tuning the TensorFlow and PyTorch to our hardware — a 64-core GPU-accelerated machine. The size of all three CNN specifications is the same, about 150 lines of code. Our mini framework is 150 lines of highly reusable hardware-agnostic code that does not depend on external libraries. The compiler for a host array language automatically generates parallel code for a chosen architecture. The key to such a balance between performance and portability lies in the design of the array language; in particular, the ability to express rank-polymorphic operations concisely, yet being able to do optimisations across them. This design builds on very few assumptions, and it is readily transferable to other contexts offering a clean approach to high-performance machine learning. |
| Tasks | |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/1912.05234v1 |
| https://arxiv.org/pdf/1912.05234v1.pdf | |
| PWC | https://paperswithcode.com/paper/array-languages-make-neural-networks-fast |
| Repo | |
| Framework | |
The Impact of Feature Causality on Normal Behaviour Models for SCADA-based Wind Turbine Fault Detection
| Title | The Impact of Feature Causality on Normal Behaviour Models for SCADA-based Wind Turbine Fault Detection |
| Authors | Telmo Felgueira, Silvio Rodrigues, Christian S. Perone, Rui Castro |
| Abstract | The cost of wind energy can be reduced by using SCADA data to detect faults in wind turbine components. Normal behavior models are one of the main fault detection approaches, but there is a lack of consensus in how different input features affect the results. In this work, a new taxonomy based on the causal relations between the input features and the target is presented. Based on this taxonomy, the impact of different input feature configurations on the modelling and fault detection performance is evaluated. To this end, a framework that formulates the detection of faults as a classification problem is also presented. |
| Tasks | Fault Detection |
| Published | 2019-06-28 |
| URL | https://arxiv.org/abs/1906.12329v1 |
| https://arxiv.org/pdf/1906.12329v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-impact-of-feature-causality-on-normal |
| Repo | |
| Framework | |
