Paper Group ANR 232
$μ$VulDeePecker: A Deep Learning-Based System for Multiclass Vulnerability Detection. A Spiking Neural Network Emulating the Structure of the Oculomotor System Requires No Learning to Control a Biomimetic Robotic Head. Efficient and Robust Algorithms for Adversarial Linear Contextual Bandits. Activism by the AI Community: Analysing Recent Achieveme …
$μ$VulDeePecker: A Deep Learning-Based System for Multiclass Vulnerability Detection
| Title | $μ$VulDeePecker: A Deep Learning-Based System for Multiclass Vulnerability Detection |
| Authors | Deqing Zou, Sujuan Wang, Shouhuai Xu, Zhen Li, Hai Jin |
| Abstract | Fine-grained software vulnerability detection is an important and challenging problem. Ideally, a detection system (or detector) not only should be able to detect whether or not a program contains vulnerabilities, but also should be able to pinpoint the type of a vulnerability in question. Existing vulnerability detection methods based on deep learning can detect the presence of vulnerabilities (i.e., addressing the binary classification or detection problem), but cannot pinpoint types of vulnerabilities (i.e., incapable of addressing multiclass classification). In this paper, we propose the first deep learning-based system for multiclass vulnerability detection, dubbed $\mu$VulDeePecker. The key insight underlying $\mu$VulDeePecker is the concept of code attention, which can capture information that can help pinpoint types of vulnerabilities, even when the samples are small. For this purpose, we create a dataset from scratch and use it to evaluate the effectiveness of $\mu$VulDeePecker. Experimental results show that $\mu$VulDeePecker is effective for multiclass vulnerability detection and that accommodating control-dependence (other than data-dependence) can lead to higher detection capabilities. |
| Tasks | Vulnerability Detection |
| Published | 2020-01-08 |
| URL | https://arxiv.org/abs/2001.02334v1 |
| https://arxiv.org/pdf/2001.02334v1.pdf | |
| PWC | https://paperswithcode.com/paper/vuldeepecker-a-deep-learning-based-system-for-1 |
| Repo | |
| Framework | |
A Spiking Neural Network Emulating the Structure of the Oculomotor System Requires No Learning to Control a Biomimetic Robotic Head
| Title | A Spiking Neural Network Emulating the Structure of the Oculomotor System Requires No Learning to Control a Biomimetic Robotic Head |
| Authors | Praveenram Balachandar, Konstantinos P. Michmizos |
| Abstract | Robotic vision introduces requirements for real-time processing of fast-varying, noisy information in a continuously changing environment. In a real-world environment, convenient assumptions, such as static camera systems and deep learning algorithms devouring high volumes of ideally slightly-varying data are hard to survive. Leveraging on recent studies on the neural connectome associated with eye movements, we designed a neuromorphic oculomotor controller and placed it at the heart of our in-house biomimetic robotic head prototype. The controller is unique in the sense that (1) all data are encoded and processed by a spiking neural network (SNN), and (2) by mimicking the associated brain areas’ connectivity, the SNN required no training to operate. A biologically-constrained Hebbian learning further improved the SNN performance in tracking a moving target. Here, we report the tracking performance of the robotic head and show that the robotic eye kinematics are similar to those reported in human eye studies. This work contributes to our ongoing effort to develop energy-efficient neuromorphic SNN and harness their emerging intelligence to control biomimetic robots with versatility and robustness. |
| Tasks | |
| Published | 2020-02-18 |
| URL | https://arxiv.org/abs/2002.07534v1 |
| https://arxiv.org/pdf/2002.07534v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-spiking-neural-network-emulating-the |
| Repo | |
| Framework | |
Efficient and Robust Algorithms for Adversarial Linear Contextual Bandits
| Title | Efficient and Robust Algorithms for Adversarial Linear Contextual Bandits |
| Authors | Gergely Neu, Julia Olkhovskaya |
| Abstract | We consider an adversarial variant of the classic $K$-armed linear contextual bandit problem where the sequence of loss functions associated with each arm are allowed to change without restriction over time. Under the assumption that the $d$-dimensional contexts are generated i.i.d.~at random from a known distributions, we develop computationally efficient algorithms based on the classic Exp3 algorithm. Our first algorithm, RealLinExp3, is shown to achieve a regret guarantee of $\widetilde{O}(\sqrt{KdT})$ over $T$ rounds, which matches the best available bound for this problem. Our second algorithm, RobustLinExp3, is shown to be robust to misspecification, in that it achieves a regret bound of $\widetilde{O}((Kd)^{1/3}T^{2/3}) + \varepsilon \sqrt{d} T$ if the true reward function is linear up to an additive nonlinear error uniformly bounded in absolute value by $\varepsilon$. To our knowledge, our performance guarantees constitute the very first results on this problem setting. |
| Tasks | Multi-Armed Bandits |
| Published | 2020-02-01 |
| URL | https://arxiv.org/abs/2002.00287v1 |
| https://arxiv.org/pdf/2002.00287v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-and-robust-algorithms-for |
| Repo | |
| Framework | |
Activism by the AI Community: Analysing Recent Achievements and Future Prospects
| Title | Activism by the AI Community: Analysing Recent Achievements and Future Prospects |
| Authors | Haydn Belfield |
| Abstract | The artificial intelligence community (AI) has recently engaged in activism in relation to their employers, other members of the community, and their governments in order to shape the societal and ethical implications of AI. It has achieved some notable successes, but prospects for further political organising and activism are uncertain. We survey activism by the AI community over the last six years; apply two analytical frameworks drawing upon the literature on epistemic communities, and worker organising and bargaining; and explore what they imply for the future prospects of the AI community. Success thus far has hinged on a coherent shared culture, and high bargaining power due to the high demand for a limited supply of AI talent. Both are crucial to the future of AI activism and worthy of sustained attention. |
| Tasks | |
| Published | 2020-01-17 |
| URL | https://arxiv.org/abs/2001.06528v1 |
| https://arxiv.org/pdf/2001.06528v1.pdf | |
| PWC | https://paperswithcode.com/paper/activism-by-the-ai-community-analysing-recent |
| Repo | |
| Framework | |
Multi-task U-Net for Music Source Separation
| Title | Multi-task U-Net for Music Source Separation |
| Authors | Venkatesh S. Kadandale, Juan F. Montesinos, Gloria Haro, Emilia Gómez |
| Abstract | A fairly straightforward approach for music source separation is to train independent models, wherein each model is dedicated for estimating only a specific source. Training a single model to estimate multiple sources generally does not perform as well as the independent dedicated models. However, Conditioned U-Net (C-U-Net) uses a control mechanism to train a single model for multi-source separation and attempts to achieve a performance comparable to that of the dedicated models. We propose a multi-task U-Net (M-U-Net) trained using a weighted multi-task loss as an alternative to the C-U-Net. We investigate two weighting strategies for our multi-task loss: 1) Dynamic Weighted Average (DWA), and 2) Energy Based Weighting (EBW). DWA determines the weights by tracking the rate of change of loss of each task during training. EBW aims to neutralize the effect of the training bias arising from the difference in energy levels of each of the sources in a mixture. Our methods provide two-fold advantages compared to the C-U-Net: 1) Fewer effective training iterations with no conditioning, and 2) Fewer trainable network parameters (no control parameters). Our methods achieve performance comparable to that of C-U-Net and the dedicated U-Nets at a much lower training cost. |
| Tasks | Music Source Separation |
| Published | 2020-03-23 |
| URL | https://arxiv.org/abs/2003.10414v1 |
| https://arxiv.org/pdf/2003.10414v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-task-u-net-for-music-source-separation |
| Repo | |
| Framework | |
Periodic Q-Learning
| Title | Periodic Q-Learning |
| Authors | Donghwan Lee, Niao He |
| Abstract | The use of target networks is a common practice in deep reinforcement learning for stabilizing the training; however, theoretical understanding of this technique is still limited. In this paper, we study the so-called periodic Q-learning algorithm (PQ-learning for short), which resembles the technique used in deep Q-learning for solving infinite-horizon discounted Markov decision processes (DMDP) in the tabular setting. PQ-learning maintains two separate Q-value estimates - the online estimate and target estimate. The online estimate follows the standard Q-learning update, while the target estimate is updated periodically. In contrast to the standard Q-learning, PQ-learning enjoys a simple finite time analysis and achieves better sample complexity for finding an epsilon-optimal policy. Our result provides a preliminary justification of the effectiveness of utilizing target estimates or networks in Q-learning algorithms. |
| Tasks | Q-Learning |
| Published | 2020-02-23 |
| URL | https://arxiv.org/abs/2002.09795v1 |
| https://arxiv.org/pdf/2002.09795v1.pdf | |
| PWC | https://paperswithcode.com/paper/periodic-q-learning |
| Repo | |
| Framework | |
Voice and accompaniment separation in music using self-attention convolutional neural network
| Title | Voice and accompaniment separation in music using self-attention convolutional neural network |
| Authors | Yuzhou Liu, Balaji Thoshkahna, Ali Milani, Trausti Kristjansson |
| Abstract | Music source separation has been a popular topic in signal processing for decades, not only because of its technical difficulty, but also due to its importance to many commercial applications, such as automatic karoake and remixing. In this work, we propose a novel self-attention network to separate voice and accompaniment in music. First, a convolutional neural network (CNN) with densely-connected CNN blocks is built as our base network. We then insert self-attention subnets at different levels of the base CNN to make use of the long-term intra-dependency of music, i.e., repetition. Within self-attention subnets, repetitions of the same musical patterns inform reconstruction of other repetitions, for better source separation performance. Results show the proposed method leads to 19.5% relative improvement in vocals separation in terms of SDR. We compare our methods with state-of-the-art systems i.e. MMDenseNet and MMDenseLSTM. |
| Tasks | Music Source Separation |
| Published | 2020-03-19 |
| URL | https://arxiv.org/abs/2003.08954v1 |
| https://arxiv.org/pdf/2003.08954v1.pdf | |
| PWC | https://paperswithcode.com/paper/voice-and-accompaniment-separation-in-music |
| Repo | |
| Framework | |
Efficient 2D neuron boundary segmentation with local topological constraints
| Title | Efficient 2D neuron boundary segmentation with local topological constraints |
| Authors | Thanuja D. Ambegoda, Matthew Cook |
| Abstract | We present a method for segmenting neuron membranes in 2D electron microscopy imagery. This segmentation task has been a bottleneck to reconstruction efforts of the brain’s synaptic circuits. One common problem is the misclassification of blurry membrane fragments as cell interior, which leads to merging of two adjacent neuron sections into one via the blurry membrane region. Human annotators can easily avoid such errors by implicitly performing gap completion, taking into account the continuity of membranes. Drawing inspiration from these human strategies, we formulate the segmentation task as an edge labeling problem on a graph with local topological constraints. We derive an integer linear program (ILP) that enforces membrane continuity, i.e. the absence of gaps. The cost function of the ILP is the pixel-wise deviation of the segmentation from a priori membrane probabilities derived from the data. Based on membrane probability maps obtained using random forest classifiers and convolutional neural networks, our method improves the neuron boundary segmentation accuracy compared to a variety of standard segmentation approaches. Our method successfully performs gap completion and leads to fewer topological errors. The method could potentially also be incorporated into other image segmentation pipelines with known topological constraints. |
| Tasks | Semantic Segmentation |
| Published | 2020-02-03 |
| URL | https://arxiv.org/abs/2002.01036v1 |
| https://arxiv.org/pdf/2002.01036v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-2d-neuron-boundary-segmentation |
| Repo | |
| Framework | |
Event-based Asynchronous Sparse Convolutional Networks
| Title | Event-based Asynchronous Sparse Convolutional Networks |
| Authors | Nico Messikommer, Daniel Gehrig, Antonio Loquercio, Davide Scaramuzza |
| Abstract | Event cameras are bio-inspired sensors that respond to per-pixel brightness changes in the form of asynchronous and sparse “events”. Recently, pattern recognition algorithms, such as learning-based methods, have made significant progress with event cameras by converting events into synchronous dense, image-like representations and applying traditional machine learning methods developed for standard cameras. However, these approaches discard the spatial and temporal sparsity inherent in event data at the cost of higher computational complexity and latency. In this work, we present a general framework for converting models trained on synchronous image-like event representations into asynchronous models with identical output, thus directly leveraging the intrinsic asynchronous and sparse nature of the event data. We show both theoretically and experimentally that this drastically reduces the computational complexity and latency of high-capacity, synchronous neural networks without sacrificing accuracy. In addition, our framework has several desirable characteristics: (i) it exploits spatio-temporal sparsity of events explicitly, (ii) it is agnostic to the event representation, network architecture, and task, and (iii) it does not require any train-time change, since it is compatible with the standard neural networks’ training process. We thoroughly validate the proposed framework on two computer vision tasks: object detection and object recognition. In these tasks, we reduce the computational complexity up to 20 times with respect to high-latency neural networks. At the same time, we outperform state-of-the-art asynchronous approaches up to 24% in prediction accuracy. |
| Tasks | Object Detection, Object Recognition |
| Published | 2020-03-20 |
| URL | https://arxiv.org/abs/2003.09148v1 |
| https://arxiv.org/pdf/2003.09148v1.pdf | |
| PWC | https://paperswithcode.com/paper/event-based-asynchronous-sparse-convolutional |
| Repo | |
| Framework | |
A Double Q-Learning Approach for Navigation of Aerial Vehicles with Connectivity Constraint
| Title | A Double Q-Learning Approach for Navigation of Aerial Vehicles with Connectivity Constraint |
| Authors | Behzad Khamidehi, Elvino S. Sousa |
| Abstract | This paper studies the trajectory optimization problem for an aerial vehicle with the mission of flying between a pair of given initial and final locations. The objective is to minimize the travel time of the aerial vehicle ensuring that the communication connectivity constraint required for the safe operation of the aerial vehicle is satisfied. We consider two different criteria for the connectivity constraint of the aerial vehicle which leads to two different scenarios. In the first scenario, we assume that the maximum continuous time duration that the aerial vehicle is out of the coverage of the ground base stations (GBSs) is limited to a given threshold. In the second scenario, however, we assume that the total time periods that the aerial vehicle is not covered by the GBSs is restricted. Based on these two constraints, we formulate two trajectory optimization problems. To solve these non-convex problems, we use an approach based on the double Q-learning method which is a model-free reinforcement learning technique and unlike the existing algorithms does not need perfect knowledge of the environment. Moreover, in contrast to the well-known Q-learning technique, our double Q-learning algorithm does not suffer from the over-estimation issue. Simulation results show that although our algorithm does not require prior information of the environment, it works well and shows near optimal performance. |
| Tasks | Q-Learning |
| Published | 2020-02-24 |
| URL | https://arxiv.org/abs/2002.10563v1 |
| https://arxiv.org/pdf/2002.10563v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-double-q-learning-approach-for-navigation |
| Repo | |
| Framework | |
The Elliptical Processes: a New Family of Flexible Stochastic Processes
| Title | The Elliptical Processes: a New Family of Flexible Stochastic Processes |
| Authors | Maria Bånkestad, Jens Sjölund, Jalil Taghia, Thomas Schön |
| Abstract | We present the elliptical processes-a new family of stochastic processes that subsumes the Gaussian process and the Student-t process. This generalization retains computational tractability while substantially increasing the range of tail behaviors that can be modeled. We base the elliptical processes on a representation of elliptical distributions as mixtures of Gaussian distributions and derive closed-form expressions for the marginal and conditional distributions. We perform an in-depth study of a particular elliptical process, where the mixture distribution is piecewise constant, and show some of its advantages over the Gaussian process through a number of experiments on robust regression. Looking forward, we believe there are several settings, e.g. when the likelihood is not Gaussian or when accurate tail modeling is critical, where the elliptical processes could become the stochastic processes of choice. |
| Tasks | |
| Published | 2020-03-13 |
| URL | https://arxiv.org/abs/2003.07201v1 |
| https://arxiv.org/pdf/2003.07201v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-elliptical-processes-a-new-family-of |
| Repo | |
| Framework | |
Correction of Chromatic Aberration from a Single Image Using Keypoints
| Title | Correction of Chromatic Aberration from a Single Image Using Keypoints |
| Authors | Benjamin T. Cecchetto |
| Abstract | In this paper, we propose a method to correct for chromatic aberration in a single photograph. Our method replicates what a user would do in a photo editing program to account for this defect. We find matching keypoints in each colour channel then align them as a user would. |
| Tasks | |
| Published | 2020-02-08 |
| URL | https://arxiv.org/abs/2002.03196v1 |
| https://arxiv.org/pdf/2002.03196v1.pdf | |
| PWC | https://paperswithcode.com/paper/correction-of-chromatic-aberration-from-a |
| Repo | |
| Framework | |
Traduction des Grammaires Catégorielles de Lambek dans les Grammaires Catégorielles Abstraites
| Title | Traduction des Grammaires Catégorielles de Lambek dans les Grammaires Catégorielles Abstraites |
| Authors | Valentin D. Richard |
| Abstract | Lambek Grammars (LG) are a computational modelling of natural language, based on non-commutative compositional types. It has been widely studied, especially for languages where the syntax plays a major role (like English). The goal of this internship report is to demonstrate that every Lambek Grammar can be, not entirely but efficiently, expressed in Abstract Categorial Grammars (ACG). The latter is a novel modelling based on higher-order signature homomorphisms (using $\lambda$-calculus), aiming at uniting the currently used models. The main idea is to transform the type rewriting system of LGs into that of Context-Free Grammars (CFG) by erasing introduction and elimination rules and generating enough axioms so that the cut rule suffices. This iterative approach preserves the derivations and enables us to stop the possible infinite generative process at any step. Although the underlying algorithm was not fully implemented, this proof provides another argument in favour of the relevance of ACGs in Natural Language Processing. |
| Tasks | |
| Published | 2020-01-23 |
| URL | https://arxiv.org/abs/2002.00725v1 |
| https://arxiv.org/pdf/2002.00725v1.pdf | |
| PWC | https://paperswithcode.com/paper/traduction-des-grammaires-categorielles-de |
| Repo | |
| Framework | |
Multilingual acoustic word embedding models for processing zero-resource languages
| Title | Multilingual acoustic word embedding models for processing zero-resource languages |
| Authors | Herman Kamper, Yevgen Matusevych, Sharon Goldwater |
| Abstract | Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available resource, such embeddings can be used in “zero-resource” speech search, indexing and discovery systems. Here we propose to train a single supervised embedding model on labelled data from multiple well-resourced languages and then apply it to unseen zero-resource languages. For this transfer learning approach, we consider two multilingual recurrent neural network models: a discriminative classifier trained on the joint vocabularies of all training languages, and a correspondence autoencoder trained to reconstruct word pairs. We test these using a word discrimination task on six target zero-resource languages. When trained on seven well-resourced languages, both models perform similarly and outperform unsupervised models trained on the zero-resource languages. With just a single training language, the second model works better, but performance depends more on the particular training–testing language pair. |
| Tasks | Transfer Learning, Word Embeddings |
| Published | 2020-02-06 |
| URL | https://arxiv.org/abs/2002.02109v2 |
| https://arxiv.org/pdf/2002.02109v2.pdf | |
| PWC | https://paperswithcode.com/paper/multilingual-acoustic-word-embedding-models |
| Repo | |
| Framework | |
Normalized and Geometry-Aware Self-Attention Network for Image Captioning
| Title | Normalized and Geometry-Aware Self-Attention Network for Image Captioning |
| Authors | Longteng Guo, Jing Liu, Xinxin Zhu, Peng Yao, Shichen Lu, Hanqing Lu |
| Abstract | Self-attention (SA) network has shown profound value in image captioning. In this paper, we improve SA from two aspects to promote the performance of image captioning. First, we propose Normalized Self-Attention (NSA), a reparameterization of SA that brings the benefits of normalization inside SA. While normalization is previously only applied outside SA, we introduce a novel normalization method and demonstrate that it is both possible and beneficial to perform it on the hidden activations inside SA. Second, to compensate for the major limit of Transformer that it fails to model the geometry structure of the input objects, we propose a class of Geometry-aware Self-Attention (GSA) that extends SA to explicitly and efficiently consider the relative geometry relations between the objects in the image. To construct our image captioning model, we combine the two modules and apply it to the vanilla self-attention network. We extensively evaluate our proposals on MS-COCO image captioning dataset and superior results are achieved when comparing to state-of-the-art approaches. Further experiments on three challenging tasks, i.e. video captioning, machine translation, and visual question answering, show the generality of our methods. |
| Tasks | Image Captioning, Machine Translation, Question Answering, Video Captioning, Visual Question Answering |
| Published | 2020-03-19 |
| URL | https://arxiv.org/abs/2003.08897v1 |
| https://arxiv.org/pdf/2003.08897v1.pdf | |
| PWC | https://paperswithcode.com/paper/normalized-and-geometry-aware-self-attention |
| Repo | |
| Framework | |
