Paper Group ANR 1701
Federated Transfer Reinforcement Learning for Autonomous Driving. Visual Reaction: Learning to Play Catch with Your Drone. EvAn: Neuromorphic Event-based Anomaly Detection. Benefits of Overparameterization in Single-Layer Latent Variable Generative Models. Conjure Documentation, Release 2.3.0. Night Time Haze and Glow Removal using Deep Dilated Con …
Federated Transfer Reinforcement Learning for Autonomous Driving
| Title | Federated Transfer Reinforcement Learning for Autonomous Driving |
| Authors | Xinle Liang, Yang Liu, Tianjian Chen, Ming Liu, Qiang Yang |
| Abstract | Reinforcement learning (RL) is widely used in autonomous driving tasks and training RL models typically involves in a multi-step process: pre-training RL models on simulators, uploading the pre-trained model to real-life robots, and fine-tuning the weight parameters on robot vehicles. This sequential process is extremely time-consuming and more importantly, knowledge from the fine-tuned model stays local and can not be re-used or leveraged collaboratively. To tackle this problem, we present an online federated RL transfer process for real-time knowledge extraction where all the participant agents make corresponding actions with the knowledge learned by others, even when they are acting in very different environments. To validate the effectiveness of the proposed approach, we constructed a real-life collision avoidance system with Microsoft Airsim simulator and NVIDIA JetsonTX2 car agents, which cooperatively learn from scratch to avoid collisions in indoor environment with obstacle objects. We demonstrate that with the proposed framework, the simulator car agents can transfer knowledge to the RC cars in real-time, with 27% increase in the average distance with obstacles and 42% decrease in the collision counts. |
| Tasks | Autonomous Driving, Transfer Reinforcement Learning |
| Published | 2019-10-14 |
| URL | https://arxiv.org/abs/1910.06001v1 |
| https://arxiv.org/pdf/1910.06001v1.pdf | |
| PWC | https://paperswithcode.com/paper/federated-transfer-reinforcement-learning-for |
| Repo | |
| Framework | |
Visual Reaction: Learning to Play Catch with Your Drone
| Title | Visual Reaction: Learning to Play Catch with Your Drone |
| Authors | Kuo-Hao Zeng, Roozbeh Mottaghi, Luca Weihs, Ali Farhadi |
| Abstract | In this paper we address the problem of visual reaction: the task of interacting with dynamic environments where the changes in the environment are not necessarily caused by the agents itself. Visual reaction entails predicting the future changes in a visual environment and planning accordingly. We study the problem of visual reaction in the context of playing catch with a drone in visually rich synthetic environments. This is a challenging problem since the agent is required to learn (1) how objects with different physical properties and shapes move, (2) what sequence of actions should be taken according to the prediction, (3) how to adjust the actions based on the visual feedback from the dynamic environment (e.g., when objects bouncing off a wall), and (4) how to reason and act with an unexpected state change in a timely manner. We propose a new dataset for this task, which includes 30K throws of 20 types of objects in different directions with different forces. Our results show that our model that integrates a forecaster with a planner outperforms a set of strong baselines that are based on tracking as well as pure model-based and model-free RL baselines. |
| Tasks | |
| Published | 2019-12-04 |
| URL | https://arxiv.org/abs/1912.02155v1 |
| https://arxiv.org/pdf/1912.02155v1.pdf | |
| PWC | https://paperswithcode.com/paper/visual-reaction-learning-to-play-catch-with |
| Repo | |
| Framework | |
EvAn: Neuromorphic Event-based Anomaly Detection
| Title | EvAn: Neuromorphic Event-based Anomaly Detection |
| Authors | Lakshmi Annamalai, Anirban Chakraborty, Chetan Singh Thakur |
| Abstract | Event-based cameras are bio-inspired novel sensors that asynchronously record changes in illumination in the form of events, thus resulting in significant advantages over conventional cameras in terms of low power utilization, high dynamic range, and no motion blur. Moreover, such cameras, by design, encode only the relative motion between the scene and the sensor (and not the static background) to yield a very sparse data structure, which can be utilized for various motion analytics tasks. In this paper, for the first time in event data analytics community, we leverage these advantages of an event camera towards a critical vision application - video anomaly detection. We propose to model the motion dynamics in the event domain with dual discriminator conditional Generative adversarial Network (cGAN) built on state-of-the-art architectures. To adapt event data for using as input to cGAN, we also put forward a deep learning solution to learn a novel representation of event data, which retains the sparsity of the data as well as encode the temporal information readily available from these sensors. Since there is no existing dataset for anomaly detection in event domain, we also provide an anomaly detection event dataset with an exhaustive set of anomalies. Careful analysis reveals that the proposed method results in huge reduction in computational complexity as compared to previous state-of-the-art conventional anomaly detection networks. |
| Tasks | Anomaly Detection |
| Published | 2019-11-21 |
| URL | https://arxiv.org/abs/1911.09722v2 |
| https://arxiv.org/pdf/1911.09722v2.pdf | |
| PWC | https://paperswithcode.com/paper/evan-neuromorphic-event-based-anomaly |
| Repo | |
| Framework | |
Benefits of Overparameterization in Single-Layer Latent Variable Generative Models
| Title | Benefits of Overparameterization in Single-Layer Latent Variable Generative Models |
| Authors | Rares-Darius Buhai, Andrej Risteski, Yoni Halpern, David Sontag |
| Abstract | One of the most surprising and exciting discoveries in supervising learning was the benefit of overparametrization (i.e. training a very large model) to improving the optimization landscape of a problem, with minimal effect on statistical performance (i.e. generalization). In contrast, unsupervised settings have been under-explored, despite the fact that it has been observed that overparameterization can be helpful as early as Dasgupta & Schulman (2007). In this paper, we perform an exhaustive study of different aspects of overparameterization in unsupervised learning via synthetic and semi-synthetic experiments. We discuss benefits to different metrics of success (held-out log-likelihood, recovering the parameters of the ground-truth model), sensitivity to variations of the training algorithm, and behavior as the amount of overparameterization increases. We find that, when learning using methods such as variational inference, larger models can significantly increase the number of ground truth latent variables recovered. |
| Tasks | |
| Published | 2019-06-28 |
| URL | https://arxiv.org/abs/1907.00030v1 |
| https://arxiv.org/pdf/1907.00030v1.pdf | |
| PWC | https://paperswithcode.com/paper/benefits-of-overparameterization-in-single |
| Repo | |
| Framework | |
Conjure Documentation, Release 2.3.0
| Title | Conjure Documentation, Release 2.3.0 |
| Authors | Özgür Akgün |
| Abstract | Welcome to the documentation of Conjure! Conjure is an automated modelling tool for Constraint Programming. In this documentation, you will find the following. - A brief introduction to Conjure, - installation instructions, - a description of how to use Conjure through its command line user interface, - a list of Conjure’s features, - a description of Conjure’s input language Essence, and - a collection of simple demonstrations of Conjure’s use. |
| Tasks | |
| Published | 2019-10-01 |
| URL | https://arxiv.org/abs/1910.00475v1 |
| https://arxiv.org/pdf/1910.00475v1.pdf | |
| PWC | https://paperswithcode.com/paper/conjure-documentation-release-230 |
| Repo | |
| Framework | |
Night Time Haze and Glow Removal using Deep Dilated Convolutional Network
| Title | Night Time Haze and Glow Removal using Deep Dilated Convolutional Network |
| Authors | Shiba Kuanar, K. R. Rao, Dwarikanath Mahapatra, Monalisa Bilas |
| Abstract | In this paper, we address the single image haze removal problem in a nighttime scene. The night haze removal is a severely ill-posed problem especially due to the presence of various visible light sources with varying colors and non-uniform illumination. These light sources are of different shapes and introduce noticeable glow in night scenes. To address these effects we introduce a deep learning based DeGlow-DeHaze iterative architecture which accounts for varying color illumination and glows. First, our convolution neural network (CNN) based DeGlow model is able to remove the glow effect significantly and on top of it a separate DeHaze network is included to remove the haze effect. For our recurrent network training, the hazy images and the corresponding transmission maps are synthesized from the NYU depth datasets and consequently restored a high-quality haze-free image. The experimental results demonstrate that our hybrid CNN model outperforms other state-of-the-art methods in terms of computation speed and image quality. We also show the effectiveness of our model on a number of real images and compare our results with the existing night haze heuristic models. |
| Tasks | Single Image Haze Removal |
| Published | 2019-02-03 |
| URL | http://arxiv.org/abs/1902.00855v1 |
| http://arxiv.org/pdf/1902.00855v1.pdf | |
| PWC | https://paperswithcode.com/paper/night-time-haze-and-glow-removal-using-deep |
| Repo | |
| Framework | |
Interleaved Composite Quantization for High-Dimensional Similarity Search
| Title | Interleaved Composite Quantization for High-Dimensional Similarity Search |
| Authors | Soroosh Khoram, Stephen J Wright, Jing Li |
| Abstract | Similarity search retrieves the nearest neighbors of a query vector from a dataset of high-dimensional vectors. As the size of the dataset grows, the cost of performing the distance computations needed to implement a query can become prohibitive. A method often used to reduce this computational cost is quantization of the vector space and location-based encoding of the dataset vectors. These encodings can be used during query processing to find approximate nearest neighbors of the query point quickly. Search speed can be improved by using shorter codes, but shorter codes have higher quantization error, leading to degraded precision. In this work, we propose the Interleaved Composite Quantization (ICQ) which achieves fast similarity search without using shorter codes. In ICQ, a small subset of the code is used to approximate the distances, with complete codes being used only when necessary. Our method effectively reduces both code length and quantization error. Furthermore, ICQ is compatible with several recently proposed techniques for reducing quantization error and can be used in conjunction with these other techniques to improve results. We confirm these claims and show strong empirical performance of ICQ using several synthetic and real-word datasets. |
| Tasks | Quantization |
| Published | 2019-12-18 |
| URL | https://arxiv.org/abs/1912.08756v2 |
| https://arxiv.org/pdf/1912.08756v2.pdf | |
| PWC | https://paperswithcode.com/paper/interleaved-composite-quantization-for-high |
| Repo | |
| Framework | |
Hammering Mizar by Learning Clause Guidance
| Title | Hammering Mizar by Learning Clause Guidance |
| Authors | Jan Jakubův, Josef Urban |
| Abstract | We describe a very large improvement of existing hammer-style proof automation over large ITP libraries by combining learning and theorem proving. In particular, we have integrated state-of-the-art machine learners into the E automated theorem prover, and developed methods that allow learning and efficient internal guidance of E over the whole Mizar library. The resulting trained system improves the real-time performance of E on the Mizar library by 70% in a single-strategy setting. |
| Tasks | Automated Theorem Proving |
| Published | 2019-04-02 |
| URL | http://arxiv.org/abs/1904.01677v1 |
| http://arxiv.org/pdf/1904.01677v1.pdf | |
| PWC | https://paperswithcode.com/paper/hammering-mizar-by-learning-clause-guidance |
| Repo | |
| Framework | |
ENIGMA-NG: Efficient Neural and Gradient-Boosted Inference Guidance for E
| Title | ENIGMA-NG: Efficient Neural and Gradient-Boosted Inference Guidance for E |
| Authors | Karel Chvalovský, Jan Jakubův, Martin Suda, Josef Urban |
| Abstract | We describe an efficient implementation of clause guidance in saturation-based automated theorem provers extending the ENIGMA approach. Unlike in the first ENIGMA implementation where fast linear classifier is trained and used together with manually engineered features, we have started to experiment with more sophisticated state-of-the-art machine learning methods such as gradient boosted trees and recursive neural networks. In particular the latter approach poses challenges in terms of efficiency of clause evaluation, however, we show that deep integration of the neural evaluation with the ATP data-structures can largely amortize this cost and lead to competitive real-time results. Both methods are evaluated on a large dataset of theorem proving problems and compared with the previous approaches. The resulting methods improve on the manually designed clause guidance, providing the first practically convincing application of gradient-boosted and neural clause guidance in saturation-style automated theorem provers. |
| Tasks | Automated Theorem Proving |
| Published | 2019-03-07 |
| URL | http://arxiv.org/abs/1903.03182v1 |
| http://arxiv.org/pdf/1903.03182v1.pdf | |
| PWC | https://paperswithcode.com/paper/enigma-ng-efficient-neural-and-gradient |
| Repo | |
| Framework | |
Usage of multiple RTL features for Earthquake prediction
| Title | Usage of multiple RTL features for Earthquake prediction |
| Authors | P. Proskura, A. Zaytsev, I. Braslavsky, E. Egorov, E. Burnaev |
| Abstract | We construct a classification model that predicts if an earthquake with the magnitude above a threshold will take place at a given location in a time range 30-180 days from a given moment of time. A common approach is to use expert forecasts based on features like Region-Time-Length (RTL) characteristics. The proposed approach uses machine learning on top of multiple RTL features to take into account effects at various scales and to improve prediction accuracy. For historical data about Japan earthquakes 1992-2005 and predictions at locations given in this database the best model has precision up to ~ 0.95 and recall up to ~ 0.98. |
| Tasks | |
| Published | 2019-05-26 |
| URL | https://arxiv.org/abs/1905.10805v1 |
| https://arxiv.org/pdf/1905.10805v1.pdf | |
| PWC | https://paperswithcode.com/paper/usage-of-multiple-rtl-features-for-earthquake |
| Repo | |
| Framework | |
“How do I fool you?": Manipulating User Trust via Misleading Black Box Explanations
| Title | “How do I fool you?": Manipulating User Trust via Misleading Black Box Explanations |
| Authors | Himabindu Lakkaraju, Osbert Bastani |
| Abstract | As machine learning black boxes are increasingly being deployed in critical domains such as healthcare and criminal justice, there has been a growing emphasis on developing techniques for explaining these black boxes in a human interpretable manner. It has recently become apparent that a high-fidelity explanation of a black box ML model may not accurately reflect the biases in the black box. As a consequence, explanations have the potential to mislead human users into trusting a problematic black box. In this work, we rigorously explore the notion of misleading explanations and how they influence user trust in black-box models. More specifically, we propose a novel theoretical framework for understanding and generating misleading explanations, and carry out a user study with domain experts to demonstrate how these explanations can be used to mislead users. Our work is the first to empirically establish how user trust in black box models can be manipulated via misleading explanations. |
| Tasks | |
| Published | 2019-11-15 |
| URL | https://arxiv.org/abs/1911.06473v1 |
| https://arxiv.org/pdf/1911.06473v1.pdf | |
| PWC | https://paperswithcode.com/paper/how-do-i-fool-you-manipulating-user-trust-via |
| Repo | |
| Framework | |
On Accurate and Reliable Anomaly Detection for Gas Turbine Combustors: A Deep Learning Approach
| Title | On Accurate and Reliable Anomaly Detection for Gas Turbine Combustors: A Deep Learning Approach |
| Authors | Weizhong Yan, Lijie Yu |
| Abstract | Monitoring gas turbine combustors health, in particular, early detecting abnormal behaviors and incipient faults, is critical in ensuring gas turbines operating efficiently and in preventing costly unplanned maintenance. One popular means of detecting combustor abnormalities is through continuously monitoring exhaust gas temperature profiles. Over the years many anomaly detection technologies have been explored for detecting combustor faults, however, the performance (detection rate) of anomaly detection solutions fielded is still inadequate. Advanced technologies that can improve detection performance are in great need. Aiming for improving anomaly detection performance, in this paper we introduce recently-developed deep learning (DL) in machine learning into the combustors anomaly detection application. Specifically, we use deep learning to hierarchically learn features from the sensor measurements of exhaust gas temperatures. And we then use the learned features as the input to a neural network classifier for performing combustor anomaly detection. Since such deep learned features potentially better capture complex relations among all sensor measurements and the underlying combustor behavior than handcrafted features do, we expect the learned features can lead to a more accurate and robust anomaly detection. Using the data collected from a real-world gas turbine combustion system, we demonstrated that the proposed deep learning based anomaly detection significantly indeed improved combustor anomaly detection performance. |
| Tasks | Anomaly Detection |
| Published | 2019-08-25 |
| URL | https://arxiv.org/abs/1908.09238v1 |
| https://arxiv.org/pdf/1908.09238v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-accurate-and-reliable-anomaly-detection |
| Repo | |
| Framework | |
Efficient Error-Tolerant Quantized Neural Network Accelerators
| Title | Efficient Error-Tolerant Quantized Neural Network Accelerators |
| Authors | Giulio Gambardella, Johannes Kappauf, Michaela Blott, Christoph Doehring, Martin Kumm, Peter Zipf, Kees Vissers |
| Abstract | Neural Networks are currently one of the most widely deployed machine learning algorithms. In particular, Convolutional Neural Networks (CNNs), are gaining popularity and are evaluated for deployment in safety critical applications such as self driving vehicles. Modern CNNs feature enormous memory bandwidth and high computational needs, challenging existing hardware platforms to meet throughput, latency and power requirements. Functional safety and error tolerance need to be considered as additional requirement in safety critical systems. In general, fault tolerant operation can be achieved by adding redundancy to the system, which is further exacerbating the computational demands. Furthermore, the question arises whether pruning and quantization methods for performance scaling turn out to be counterproductive with regards to fail safety requirements. In this work we present a methodology to evaluate the impact of permanent faults affecting Quantized Neural Networks (QNNs) and how to effectively decrease their effects in hardware accelerators. We use FPGA-based hardware accelerated error injection, in order to enable the fast evaluation. A detailed analysis is presented showing that QNNs containing convolutional layers are by far not as robust to faults as commonly believed and can lead to accuracy drops of up to 10%. To circumvent that, we propose two different methods to increase their robustness: 1) selective channel replication which adds significantly less redundancy than used by the common triple modular redundancy and 2) a fault-aware scheduling of processing elements for folded implementations |
| Tasks | Quantization |
| Published | 2019-12-16 |
| URL | https://arxiv.org/abs/1912.07394v1 |
| https://arxiv.org/pdf/1912.07394v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-error-tolerant-quantized-neural |
| Repo | |
| Framework | |
Improving singing voice separation with the Wave-U-Net using Minimum Hyperspherical Energy
| Title | Improving singing voice separation with the Wave-U-Net using Minimum Hyperspherical Energy |
| Authors | Joaquin Perez-Lapillo, Oleksandr Galkin, Tillman Weyde |
| Abstract | In recent years, deep learning has surpassed traditional approaches to the problem of singing voice separation. The Wave-U-Net is a recent deep network architecture that operates directly on the time domain. The standard Wave-U-Net is trained with data augmentation and early stopping to prevent overfitting. Minimum hyperspherical energy (MHE) regularization has recently proven to increase generalization in image classification problems by encouraging a diversified filter configuration. In this work, we apply MHE regularization to the 1D filters of the Wave-U-Net. We evaluated this approach for separating the vocal part from mixed music audio recordings on the MUSDB18 dataset. We found that adding MHE regularization to the loss function consistently improves singing voice separation, as measured in the Signal to Distortion Ratio on test recordings, leading to the current best time-domain system for singing voice extraction. |
| Tasks | Data Augmentation, Image Classification |
| Published | 2019-10-22 |
| URL | https://arxiv.org/abs/1910.10071v1 |
| https://arxiv.org/pdf/1910.10071v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-singing-voice-separation-with-the |
| Repo | |
| Framework | |
On Empirical Comparisons of Optimizers for Deep Learning
| Title | On Empirical Comparisons of Optimizers for Deep Learning |
| Authors | Dami Choi, Christopher J. Shallue, Zachary Nado, Jaehoon Lee, Chris J. Maddison, George E. Dahl |
| Abstract | Selecting an optimizer is a central step in the contemporary deep learning pipeline. In this paper, we demonstrate the sensitivity of optimizer comparisons to the hyperparameter tuning protocol. Our findings suggest that the hyperparameter search space may be the single most important factor explaining the rankings obtained by recent empirical comparisons in the literature. In fact, we show that these results can be contradicted when hyperparameter search spaces are changed. As tuning effort grows without bound, more general optimizers should never underperform the ones they can approximate (i.e., Adam should never perform worse than momentum), but recent attempts to compare optimizers either assume these inclusion relationships are not practically relevant or restrict the hyperparameters in ways that break the inclusions. In our experiments, we find that inclusion relationships between optimizers matter in practice and always predict optimizer comparisons. In particular, we find that the popular adaptive gradient methods never underperform momentum or gradient descent. We also report practical tips around tuning often ignored hyperparameters of adaptive gradient methods and raise concerns about fairly benchmarking optimizers for neural network training. |
| Tasks | |
| Published | 2019-10-11 |
| URL | https://arxiv.org/abs/1910.05446v2 |
| https://arxiv.org/pdf/1910.05446v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-empirical-comparisons-of-optimizers-for |
| Repo | |
| Framework | |
