Paper Group ANR 36
Crowdsourced Classification with XOR Queries: Fundamental Limits and An Efficient Algorithm. Reliability Validation of Learning Enabled Vehicle Tracking. Effects of sparse rewards of different magnitudes in the speed of learning of model-based actor critic methods. Sentiment Analysis in Drug Reviews using Supervised Machine Learning Algorithms. Ada …
Crowdsourced Classification with XOR Queries: Fundamental Limits and An Efficient Algorithm
| Title | Crowdsourced Classification with XOR Queries: Fundamental Limits and An Efficient Algorithm |
| Authors | Daesung Kim, Hye Won Chung |
| Abstract | Crowdsourcing systems have emerged as an effective platform to label data and classify objects with relatively low cost by exploiting non-expert workers. To ensure reliable recovery of unknown labels with as few number of queries as possible, we consider an effective query type that asks “group attribute” of a chosen subset of objects. In particular, we consider the problem of classifying $m$ binary labels with XOR queries that ask whether the number of objects having a given attribute in the chosen subset of size $d$ is even or odd. The subset size $d$, which we call query degree, can be varying over queries. Since a worker needs to make more efforts to answer a query of a higher degree, we consider a noise model where the accuracy of worker’s answer changes depending both on the worker reliability and query degree $d$. For this general model, we characterize the information-theoretic limit on the optimal number of queries to reliably recover $m$ labels in terms of a given combination of degree-$d$ queries and noise parameters. Further, we propose an efficient inference algorithm that achieves this limit even when the noise parameters are unknown. |
| Tasks | |
| Published | 2020-01-31 |
| URL | https://arxiv.org/abs/2001.11775v1 |
| https://arxiv.org/pdf/2001.11775v1.pdf | |
| PWC | https://paperswithcode.com/paper/crowdsourced-classification-with-xor-queries |
| Repo | |
| Framework | |
Reliability Validation of Learning Enabled Vehicle Tracking
| Title | Reliability Validation of Learning Enabled Vehicle Tracking |
| Authors | Youcheng Sun, Yifan Zhou, Simon Maskell, James Sharp, Xiaowei Huang |
| Abstract | This paper studies the reliability of a real-world learning-enabled system, which conducts dynamic vehicle tracking based on a high-resolution wide-area motion imagery input. The system consists of multiple neural network components – to process the imagery inputs – and multiple symbolic (Kalman filter) components – to analyse the processed information for vehicle tracking. It is known that neural networks suffer from adversarial examples, which make them lack robustness. However, it is unclear if and how the adversarial examples over learning components can affect the overall system-level reliability. By integrating a coverage-guided neural network testing tool, DeepConcolic, with the vehicle tracking system, we found that (1) the overall system can be resilient to some adversarial examples thanks to the existence of other components, and (2) the overall system presents an extra level of uncertainty which cannot be determined by analysing the deep learning components only. This research suggests the need for novel verification and validation methods for learning-enabled systems. |
| Tasks | |
| Published | 2020-02-06 |
| URL | https://arxiv.org/abs/2002.02424v1 |
| https://arxiv.org/pdf/2002.02424v1.pdf | |
| PWC | https://paperswithcode.com/paper/reliability-validation-of-learning-enabled |
| Repo | |
| Framework | |
Effects of sparse rewards of different magnitudes in the speed of learning of model-based actor critic methods
| Title | Effects of sparse rewards of different magnitudes in the speed of learning of model-based actor critic methods |
| Authors | Juan Vargas, Lazar Andjelic, Amir Barati Farimani |
| Abstract | Actor critic methods with sparse rewards in model-based deep reinforcement learning typically require a deterministic binary reward function that reflects only two possible outcomes: if, for each step, the goal has been achieved or not. Our hypothesis is that we can influence an agent to learn faster by applying an external environmental pressure during training, which adversely impacts its ability to get higher rewards. As such, we deviate from the classical paradigm of sparse rewards and add a uniformly sampled reward value to the baseline reward to show that (1) sample efficiency of the training process can be correlated to the adversity experienced during training, (2) it is possible to achieve higher performance in less time and with less resources, (3) we can reduce the performance variability experienced seed over seed, (4) there is a maximum point after which more pressure will not generate better results, and (5) that random positive incentives have an adverse effect when using a negative reward strategy, making an agent under those conditions learn poorly and more slowly. These results have been shown to be valid for Deep Deterministic Policy Gradients using Hindsight Experience Replay in a well known Mujoco environment, but we argue that they could be generalized to other methods and environments as well. |
| Tasks | |
| Published | 2020-01-18 |
| URL | https://arxiv.org/abs/2001.06725v1 |
| https://arxiv.org/pdf/2001.06725v1.pdf | |
| PWC | https://paperswithcode.com/paper/effects-of-sparse-rewards-of-different |
| Repo | |
| Framework | |
Sentiment Analysis in Drug Reviews using Supervised Machine Learning Algorithms
| Title | Sentiment Analysis in Drug Reviews using Supervised Machine Learning Algorithms |
| Authors | Sairamvinay Vijayaraghavan, Debraj Basu |
| Abstract | Sentiment Analysis is an important algorithm in Natural Language Processing which is used to detect sentiment within some text. In our project, we had chosen to work on analyzing reviews of various drugs which have been reviewed in form of texts and have also been given a rating on a scale from 1-10. We had obtained this data set from the UCI machine learning repository which had 2 data sets: train and test (split as 75-25%). We had split the number rating for the drug into three classes in general: positive (7-10), negative (1-4) or neutral(4-7). There are multiple reviews for the drugs that belong to a similar condition and we decided to investigate how the reviews for different conditions use different words impact the ratings of the drugs. Our intention was mainly to implement supervised machine learning classification algorithms that predict the class of the rating using the textual review. We had primarily implemented different embeddings such as Term Frequency Inverse Document Frequency (TFIDF) and the Count Vectors (CV). We had trained models on the most popular conditions such as “Birth Control”, “Depression” and “Pain” within the data set and obtained good results while predicting the test data sets. |
| Tasks | Sentiment Analysis |
| Published | 2020-03-21 |
| URL | https://arxiv.org/abs/2003.11643v1 |
| https://arxiv.org/pdf/2003.11643v1.pdf | |
| PWC | https://paperswithcode.com/paper/sentiment-analysis-in-drug-reviews-using |
| Repo | |
| Framework | |
Adaptive Estimator Selection for Off-Policy Evaluation
| Title | Adaptive Estimator Selection for Off-Policy Evaluation |
| Authors | Yi Su, Pavithra Srinath, Akshay Krishnamurthy |
| Abstract | We develop a generic data-driven method for estimator selection in off-policy policy evaluation settings. We establish a strong performance guarantee for the method, showing that it is competitive with the oracle estimator, up to a constant factor. Via in-depth case studies in contextual bandits and reinforcement learning, we demonstrate the generality and applicability of the method. We also perform comprehensive experiments, demonstrating the empirical efficacy of our approach and comparing with related approaches. In both case studies, our method compares favorably with existing methods. |
| Tasks | Multi-Armed Bandits |
| Published | 2020-02-18 |
| URL | https://arxiv.org/abs/2002.07729v1 |
| https://arxiv.org/pdf/2002.07729v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-estimator-selection-for-off-policy |
| Repo | |
| Framework | |
A light neural network for modulation detection under impairments
| Title | A light neural network for modulation detection under impairments |
| Authors | Thomas Courtat, Hélion du Mas des Bourboux |
| Abstract | We present a neural network architecture able to efficiently detect modulation techniques in a portion of I/Q signals. This network is lighter by up to two orders of magnitude than other architectures working on the same or similar tasks. Moreover, the number of parameters does not depend on the signal duration, which allows processing stream of data, and results in a signal-length invariant network. In addition, we develop a custom simulator able to model the different impairments the propagation channel and the demodulator can bring to the recorded I/Q signal: random phase shifts, delays, roll-off, sampling rates, and frequency offsets. We benefit from this data set to train our neural network to be invariant to impairments and quantify its accuracy at disentangling between modulations under realistic real-life conditions. |
| Tasks | |
| Published | 2020-03-27 |
| URL | https://arxiv.org/abs/2003.12260v1 |
| https://arxiv.org/pdf/2003.12260v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-light-neural-network-for-modulation |
| Repo | |
| Framework | |
Are Gabor Kernels Optimal for Iris Recognition?
| Title | Are Gabor Kernels Optimal for Iris Recognition? |
| Authors | Aidan Boyd, Adam Czajka, Kevin Bowyer |
| Abstract | Gabor kernels are widely accepted as dominant filters for iris recognition. In this work we investigate, given the current interest in neural networks, if Gabor kernels are the only family of functions performing best in iris recognition, or if better filters can be learned directly from iris data. We use (on purpose) a single-layer convolutional neural network as it mimics an iris code-based algorithm. We learn two sets of data-driven kernels; one starting from randomly initialized weights and the other from open-source set of Gabor kernels. Through experimentation, we show that the network does not converge on Gabor kernels, instead converging on a mix of edge detectors, blob detectors and simple waves. In our experiments carried out with three subject-disjoint datasets we found that the performance of these learned kernels is comparable to the open-source Gabor kernels. These lead us to two conclusions: (a) a family of functions offering optimal performance in iris recognition is wider than Gabor kernels, and (b) we probably hit the maximum performance for an iris coding algorithm that uses a single convolutional layer, yet with multiple filters. Released with this work is a framework to learn data-driven kernels that can be easily transplanted into open-source iris recognition software (for instance, OSIRIS – Open Source IRIS). |
| Tasks | Iris Recognition |
| Published | 2020-02-20 |
| URL | https://arxiv.org/abs/2002.08959v1 |
| https://arxiv.org/pdf/2002.08959v1.pdf | |
| PWC | https://paperswithcode.com/paper/are-gabor-kernels-optimal-for-iris |
| Repo | |
| Framework | |
Coordination without communication: optimal regret in two players multi-armed bandits
| Title | Coordination without communication: optimal regret in two players multi-armed bandits |
| Authors | Sébastien Bubeck, Thomas Budzinski |
| Abstract | We consider two agents playing simultaneously the same stochastic three-armed bandit problem. The two agents are cooperating but they cannot communicate. We propose a strategy with no collisions at all between the players (with very high probability), and with near-optimal regret $O(\sqrt{T \log(T)})$. We also provide evidence that the extra logarithmic term $\sqrt{\log(T)}$ is necessary, with a lower bound for a variant of the problem. |
| Tasks | Multi-Armed Bandits |
| Published | 2020-02-14 |
| URL | https://arxiv.org/abs/2002.07596v1 |
| https://arxiv.org/pdf/2002.07596v1.pdf | |
| PWC | https://paperswithcode.com/paper/coordination-without-communication-optimal |
| Repo | |
| Framework | |
Adversarial Attacks on Linear Contextual Bandits
| Title | Adversarial Attacks on Linear Contextual Bandits |
| Authors | Evrard Garcelon, Baptiste Roziere, Laurent Meunier, Jean Tarbouriech, Olivier Teytaud, Alessandro Lazaric, Matteo Pirotta |
| Abstract | Contextual bandit algorithms are applied in a wide range of domains, from advertising to recommender systems, from clinical trials to education. In many of these domains, malicious agents may have incentives to attack the bandit algorithm to induce it to perform a desired behavior. For instance, an unscrupulous ad publisher may try to increase their own revenue at the expense of the advertisers; a seller may want to increase the exposure of their products, or thwart a competitor’s advertising campaign. In this paper, we study several attack scenarios and show that a malicious agent can force a linear contextual bandit algorithm to pull any desired arm $T - o(T)$ times over a horizon of $T$ steps, while applying adversarial modifications to either rewards or contexts that only grow logarithmically as $O(\log T)$. We also investigate the case when a malicious agent is interested in affecting the behavior of the bandit algorithm in a single context (e.g., a specific user). We first provide sufficient conditions for the feasibility of the attack and we then propose an efficient algorithm to perform the attack. We validate our theoretical results on experiments performed on both synthetic and real-world datasets. |
| Tasks | Multi-Armed Bandits, Recommendation Systems |
| Published | 2020-02-10 |
| URL | https://arxiv.org/abs/2002.03839v2 |
| https://arxiv.org/pdf/2002.03839v2.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-attacks-on-linear-contextual |
| Repo | |
| Framework | |
Assessing Human Translations from French to Bambara for Machine Learning: a Pilot Study
| Title | Assessing Human Translations from French to Bambara for Machine Learning: a Pilot Study |
| Authors | Michael Leventhal, Allahsera Tapo, Sarah Luger, Marcos Zampieri, Christopher M. Homan |
| Abstract | We present novel methods for assessing the quality of human-translated aligned texts for learning machine translation models of under-resourced languages. Malian university students translated French texts, producing either written or oral translations to Bambara. Our results suggest that similar quality can be obtained from either written or spoken translations for certain kinds of texts. They also suggest specific instructions that human translators should be given in order to improve the quality of their work. |
| Tasks | Machine Translation |
| Published | 2020-03-31 |
| URL | https://arxiv.org/abs/2004.00068v1 |
| https://arxiv.org/pdf/2004.00068v1.pdf | |
| PWC | https://paperswithcode.com/paper/assessing-human-translations-from-french-to |
| Repo | |
| Framework | |
Randomized Primal-Dual Algorithms for Composite Convex Minimization with Faster Convergence Rates
| Title | Randomized Primal-Dual Algorithms for Composite Convex Minimization with Faster Convergence Rates |
| Authors | Quoc Tran-Dinh, Deyi Liu |
| Abstract | We develop two novel randomized primal-dual algorithms to solve nonsmooth composite convex optimization problems. The first algorithm is fully randomized, i.e., it has randomized updates on both primal and dual variables, while the second one is a semi-randomized scheme which only has one randomized update on the primal (or dual) variable while using the full update for the other. Both algorithms achieve the best-known $\mathcal{O}(1/k)$ or $\mathcal{O}(1/k^2)$ convergence rates in expectation under either only convexity or strong convexity, respectively, where $k$ is the iteration counter. Interestingly, with new parameter update rules, our algorithms can achieve $o(1/k)$ or $o(1/k^2)$ best-iterate convergence rate in expectation under either convexity or strong convexity, respectively. These rates can be obtained for both the primal and dual problems. To the best of our knowledge, this is the first time such faster convergence rates are shown for randomized primal-dual methods. Finally, we verify our theoretical results via two numerical examples and compare them with the state-of-the-art. |
| Tasks | |
| Published | 2020-03-03 |
| URL | https://arxiv.org/abs/2003.01322v1 |
| https://arxiv.org/pdf/2003.01322v1.pdf | |
| PWC | https://paperswithcode.com/paper/randomized-primal-dual-algorithms-for |
| Repo | |
| Framework | |
Interpreting Cloud Computer Vision Pain-Points: A Mining Study of Stack Overflow
| Title | Interpreting Cloud Computer Vision Pain-Points: A Mining Study of Stack Overflow |
| Authors | Alex Cummaudo, Rajesh Vasa, Scott Barnett, John Grundy, Mohamed Abdelrazek |
| Abstract | Intelligent services are becoming increasingly more pervasive; application developers want to leverage the latest advances in areas such as computer vision to provide new services and products to users, and large technology firms enable this via RESTful APIs. While such APIs promise an easy-to-integrate on-demand machine intelligence, their current design, documentation and developer interface hides much of the underlying machine learning techniques that power them. Such APIs look and feel like conventional APIs but abstract away data-driven probabilistic behaviour - the implications of a developer treating these APIs in the same way as other, traditional cloud services, such as cloud storage, is of concern. The objective of this study is to determine the various pain-points developers face when implementing systems that rely on the most mature of these intelligent services, specifically those that provide computer vision. We use Stack Overflow to mine indications of the frustrations that developers appear to face when using computer vision services, classifying their questions against two recent classification taxonomies (documentation-related and general questions). We find that, unlike mature fields like mobile development, there is a contrast in the types of questions asked by developers. These indicate a shallow understanding of the underlying technology that empower such systems. We discuss several implications of these findings via the lens of learning taxonomies to suggest how the software engineering community can improve these services and comment on the nature by which developers use them. |
| Tasks | |
| Published | 2020-01-28 |
| URL | https://arxiv.org/abs/2001.10130v1 |
| https://arxiv.org/pdf/2001.10130v1.pdf | |
| PWC | https://paperswithcode.com/paper/interpreting-cloud-computer-vision-pain |
| Repo | |
| Framework | |
RSnet: An improvement for Darknet
| Title | RSnet: An improvement for Darknet |
| Authors | Shengquan Wang, Ang Li, Jiying Chen, Baoyu Zheng, Jiaxin Ji, Li Xianglong |
| Abstract | Recently, when we used this method to identify aircraft targets in remote sensing images, we found that there are some defects in our own YOLOv2 and Darknet-19 network. Characteristic in the images we identified are not very clear, thats why we couldn’t get some much more good results. Then we replaced the maxpooling in the yolov3 network as the global maxpooling. Under the same test conditions, we got a higher. It achieves 76.9 AP50 in 100 ms on a GTX1050TI, compared to 80.5 AP50 in 627 ms by our net. Map.86% of Map was obtained by the improved network, higher than the former. |
| Tasks | |
| Published | 2020-01-16 |
| URL | https://arxiv.org/abs/2002.03729v1 |
| https://arxiv.org/pdf/2002.03729v1.pdf | |
| PWC | https://paperswithcode.com/paper/rsnet-an-improvement-for-darknet |
| Repo | |
| Framework | |
Co-evolution of language and agents in referential games
| Title | Co-evolution of language and agents in referential games |
| Authors | Gautier Dagan, Dieuwke Hupkes, Elia Bruni |
| Abstract | Referential games offer a grounded learning environment for neural agents, that accounts for the functional aspects of language. However, they fail to account for another fundamental aspect of human language: Because languages are transmitted from generation to generation, they have to be learnable by new language users, which makes them subject to cultural evolution. Recent work has shown that incorporating cultural evolution in referential game results in considerable improvements in the properties of the languages that emerge in the game. In this work, we first substantiate this claim with a different data set and a wider array of evaluation metrics. Then, drawing inspiration from linguistic theories of human language evolution, we consider a scenario in which not only cultural but also genetic evolution is integrated. As our core contribution, we introduce the Language Transmission Engine, in which cultural evolution of the language is combined with genetic evolution of the agents’ architecture. We show that this co-evolution scenario leads to across-the-board improvements on all considered metrics. These results stress that cultural evolution is important for language emergence studies, but also the suitability of the architecture itself should be considered. |
| Tasks | |
| Published | 2020-01-10 |
| URL | https://arxiv.org/abs/2001.03361v1 |
| https://arxiv.org/pdf/2001.03361v1.pdf | |
| PWC | https://paperswithcode.com/paper/co-evolution-of-language-and-agents-in |
| Repo | |
| Framework | |
Coronary Artery Segmentation from Intravascular Optical Coherence Tomography Using Deep Capsules
| Title | Coronary Artery Segmentation from Intravascular Optical Coherence Tomography Using Deep Capsules |
| Authors | Arjun Balaji, Lachlan Kelsey, Kamran Majeed, Carl Schultz, Barry Doyle |
| Abstract | The segmentation and analysis of coronary arteries from intravascular optical coherence tomography (IVOCT) is an important aspect of diagnosing and managing coronary artery disease. However, automated, robust IVOCT image analysis tools are lacking. Current image processing methods are hindered by the time needed to generate these expert-labelled datasets and also the potential for bias during the analysis. Here we present a new deep learning method based on capsules to automatically produce lumen segmentations, built using a large IVOCT dataset of 12,011 images with ground-truth segmentations. This dataset contains images with both blood and light artefacts (22.8%), as well as noise from metallic (23.1%) and bioresorbable stents (2.5%). We trained our model on a dataset containing 9,608 images. We rigorously investigate design variations with respect to upsampling regimes and input selection and validate our deep learning model using 2,403 images. We show that our fully trained and optimized model achieves a mean Soft Dice Score of 97.11% (median of 98.2%), segments 200 IVOCT images in an acceptable timeframe of 12 seconds and outperforms current algorithms. |
| Tasks | |
| Published | 2020-03-13 |
| URL | https://arxiv.org/abs/2003.06080v1 |
| https://arxiv.org/pdf/2003.06080v1.pdf | |
| PWC | https://paperswithcode.com/paper/coronary-artery-segmentation-from |
| Repo | |
| Framework | |
