Paper Group ANR 1600
Plant-wide fault and disturbance screening using combined transfer entropy and eigenvector centrality analysis. Self-supervised Deformation Modeling for Facial Expression Editing. Evaluating Empathy in Artificial Agents. Iterative Update and Unified Representation for Multi-Agent Reinforcement Learning. Meta-learning Pseudo-differential Operators w …
Plant-wide fault and disturbance screening using combined transfer entropy and eigenvector centrality analysis
| Title | Plant-wide fault and disturbance screening using combined transfer entropy and eigenvector centrality analysis |
| Authors | Simon Streicher, Carl Sandrock |
| Abstract | Finding the source of a disturbance or fault in complex systems such as industrial chemical processing plants can be a difficult task and consume a significant number of engineering hours. In many cases, a systematic elimination procedure is considered to be the only feasible approach but can cause undesired process upsets. Practitioners desire robust alternative approaches. This paper presents an unsupervised, data-driven method for ranking process elements according to the magnitude and novelty of their influence. Partial bivariate transfer entropy estimation is used to infer a weighted directed graph of process elements. Eigenvector centrality is applied to rank network nodes according to their overall effect. As the ranking of process elements rely on emerging properties that depend on the aggregate of many connections, the results are robust to errors in the estimation of individual edge properties and the inclusion of indirect connections that do not represent the true causal structure of the process. A monitoring chart of continuously calculated process element importance scores over multiple overlapping time regions can assist with incipient fault detection. Ranking results combined with visual inspection of information transfer networks is also useful for root cause analysis of known faults and disturbances. A software implementation of the proposed method is available. |
| Tasks | Fault Detection |
| Published | 2019-04-08 |
| URL | http://arxiv.org/abs/1904.04035v1 |
| http://arxiv.org/pdf/1904.04035v1.pdf | |
| PWC | https://paperswithcode.com/paper/plant-wide-fault-and-disturbance-screening |
| Repo | |
| Framework | |
Self-supervised Deformation Modeling for Facial Expression Editing
| Title | Self-supervised Deformation Modeling for Facial Expression Editing |
| Authors | ShahRukh Athar, Zhixin Shu, Dimitris Samaras |
| Abstract | Recent advances in deep generative models have demonstrated impressive results in photo-realistic facial image synthesis and editing. Facial expressions are inherently the result of muscle movement. However, existing neural network-based approaches usually only rely on texture generation to edit expressions and largely neglect the motion information. In this work, we propose a novel end-to-end network that disentangles the task of facial editing into two steps: a " “motion-editing” step and a “texture-editing” step. In the “motion-editing” step, we explicitly model facial movement through image deformation, warping the image into the desired expression. In the “texture-editing” step, we generate necessary textures, such as teeth and shading effects, for a photo-realistic result. Our physically-based task-disentanglement system design allows each step to learn a focused task, removing the need of generating texture to hallucinate motion. Our system is trained in a self-supervised manner, requiring no ground truth deformation annotation. Using Action Units [8] as the representation for facial expression, our method improves the state-of-the-art facial expression editing performance in both qualitative and quantitative evaluations. |
| Tasks | Image Generation, Texture Synthesis |
| Published | 2019-11-02 |
| URL | https://arxiv.org/abs/1911.00735v2 |
| https://arxiv.org/pdf/1911.00735v2.pdf | |
| PWC | https://paperswithcode.com/paper/self-supervised-deformation-modeling-for |
| Repo | |
| Framework | |
Evaluating Empathy in Artificial Agents
| Title | Evaluating Empathy in Artificial Agents |
| Authors | Özge Nilay Yalçın |
| Abstract | The novel research area of computational empathy is in its infancy and moving towards developing methods and standards. One major problem is the lack of agreement on the evaluation of empathy in artificial interactive systems. Even though the existence of well-established methods from psychology, psychiatry and neuroscience, the translation between these methods and computational empathy is not straightforward. It requires a collective effort to develop metrics that are more suitable for interactive artificial agents. This paper is aimed as an attempt to initiate the dialogue on this important problem. We examine the evaluation methods for empathy in humans and provide suggestions for the development of better metrics to evaluate empathy in artificial agents. We acknowledge the difficulty of arriving at a single solution in a vast variety of interactive systems and propose a set of systematic approaches that can be used with a variety of applications and systems. |
| Tasks | |
| Published | 2019-08-14 |
| URL | https://arxiv.org/abs/1908.05341v1 |
| https://arxiv.org/pdf/1908.05341v1.pdf | |
| PWC | https://paperswithcode.com/paper/evaluating-empathy-in-artificial-agents |
| Repo | |
| Framework | |
Iterative Update and Unified Representation for Multi-Agent Reinforcement Learning
| Title | Iterative Update and Unified Representation for Multi-Agent Reinforcement Learning |
| Authors | Jiancheng Long, Hongming Zhang, Tianyang Yu, Bo Xu |
| Abstract | Multi-agent systems have a wide range of applications in cooperative and competitive tasks. As the number of agents increases, nonstationarity gets more serious in multi-agent reinforcement learning (MARL), which brings great difficulties to the learning process. Besides, current mainstream algorithms configure each agent an independent network,so that the memory usage increases linearly with the number of agents which greatly slows down the interaction with the environment. Inspired by Generative Adversarial Networks (GAN), this paper proposes an iterative update method (IU) to stabilize the nonstationary environment. Further, we add first-person perspective and represent all agents by only one network which can change agents’ policies from sequential compute to batch compute. Similar to continual lifelong learning, we realize the iterative update method in this unified representative network (IUUR). In this method, iterative update can greatly alleviate the nonstationarity of the environment, unified representation can speed up the interaction with environment and avoid the linear growth of memory usage. Besides, this method does not bother decentralized execution and distributed deployment. Experiments show that compared with MADDPG, our algorithm achieves state-of-the-art performance and saves wall-clock time by a large margin especially with more agents. |
| Tasks | Multi-agent Reinforcement Learning |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.06758v1 |
| https://arxiv.org/pdf/1908.06758v1.pdf | |
| PWC | https://paperswithcode.com/paper/iterative-update-and-unified-representation |
| Repo | |
| Framework | |
Meta-learning Pseudo-differential Operators with Deep Neural Networks
| Title | Meta-learning Pseudo-differential Operators with Deep Neural Networks |
| Authors | Jordi Feliu-Faba, Yuwei Fan, Lexing Ying |
| Abstract | This paper introduces a meta-learning approach for parameterized pseudo-differential operators with deep neural networks. With the help of the nonstandard wavelet form, the pseudo-differential operators can be approximated in a compressed form with a collection of vectors. The nonlinear map from the parameter to this collection of vectors and the wavelet transform are learned together from a small number of matrix-vector multiplications of the pseudo-differential operator. Numerical results for Green’s functions of elliptic partial differential equations and the radiative transfer equations demonstrate the efficiency and accuracy of the proposed approach. |
| Tasks | Meta-Learning |
| Published | 2019-06-16 |
| URL | https://arxiv.org/abs/1906.06782v2 |
| https://arxiv.org/pdf/1906.06782v2.pdf | |
| PWC | https://paperswithcode.com/paper/meta-learning-pseudo-differential-operators |
| Repo | |
| Framework | |
Autonomous Identification and Goal-Directed Invocation of Event-Predictive Behavioral Primitives
| Title | Autonomous Identification and Goal-Directed Invocation of Event-Predictive Behavioral Primitives |
| Authors | Christian Gumbsch, Martin V. Butz, Georg Martius |
| Abstract | Voluntary behavior of humans appears to be composed of small, elementary building blocks or behavioral primitives. While this modular organization seems crucial for the learning of complex motor skills and the flexible adaption of behavior to new circumstances, the problem of learning meaningful, compositional abstractions from sensorimotor experiences remains an open challenge. Here, we introduce a computational learning architecture, termed surprise-based behavioral modularization into event-predictive structures (SUBMODES), that explores behavior and identifies the underlying behavioral units completely from scratch. The SUBMODES architecture bootstraps sensorimotor exploration using a self-organizing neural controller. While exploring the behavioral capabilities of its own body, the system learns modular structures that predict the sensorimotor dynamics and generate the associated behavior. In line with recent theories of event perception, the system uses unexpected prediction error signals, i.e., surprise, to detect transitions between successive behavioral primitives. We show that, when applied to two robotic systems with completely different body kinematics, the system manages to learn a variety of complex and realistic behavioral primitives. Moreover, after initial self-exploration the system can use its learned predictive models progressively more effectively for invoking model predictive planning and goal-directed control in different tasks and environments. |
| Tasks | |
| Published | 2019-02-26 |
| URL | https://arxiv.org/abs/1902.09948v2 |
| https://arxiv.org/pdf/1902.09948v2.pdf | |
| PWC | https://paperswithcode.com/paper/autonomous-identification-and-goal-directed |
| Repo | |
| Framework | |
Label-Consistent Backdoor Attacks
| Title | Label-Consistent Backdoor Attacks |
| Authors | Alexander Turner, Dimitris Tsipras, Aleksander Madry |
| Abstract | Deep neural networks have been demonstrated to be vulnerable to backdoor attacks. Specifically, by injecting a small number of maliciously constructed inputs into the training set, an adversary is able to plant a backdoor into the trained model. This backdoor can then be activated during inference by a backdoor trigger to fully control the model’s behavior. While such attacks are very effective, they crucially rely on the adversary injecting arbitrary inputs that are—often blatantly—mislabeled. Such samples would raise suspicion upon human inspection, potentially revealing the attack. Thus, for backdoor attacks to remain undetected, it is crucial that they maintain label-consistency—the condition that injected inputs are consistent with their labels. In this work, we leverage adversarial perturbations and generative models to execute efficient, yet label-consistent, backdoor attacks. Our approach is based on injecting inputs that appear plausible, yet are hard to classify, hence causing the model to rely on the (easier-to-learn) backdoor trigger. |
| Tasks | |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02771v2 |
| https://arxiv.org/pdf/1912.02771v2.pdf | |
| PWC | https://paperswithcode.com/paper/label-consistent-backdoor-attacks |
| Repo | |
| Framework | |
A discriminative condition-aware backend for speaker verification
| Title | A discriminative condition-aware backend for speaker verification |
| Authors | Luciana Ferrer, Mitchell McLaren |
| Abstract | We present a scoring approach for speaker verification that mimics the standard PLDA-based backend process used in most current speaker verification systems. However, unlike the standard backends, all parameters of the model are jointly trained to optimize the binary cross-entropy for the speaker verification task. We further integrate the calibration stage inside the model, making the parameters of this stage depend on metadata vectors that represent the conditions of the signals. We show that the proposed backend has excellent out-of-the-box calibration performance on most of our test sets, making it an ideal approach for cases in which the test conditions are not known and development data is not available for training a domain-specific calibration model. |
| Tasks | Calibration, Speaker Verification |
| Published | 2019-11-26 |
| URL | https://arxiv.org/abs/1911.11622v1 |
| https://arxiv.org/pdf/1911.11622v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-discriminative-condition-aware-backend-for |
| Repo | |
| Framework | |
ReStoCNet: Residual Stochastic Binary Convolutional Spiking Neural Network for Memory-Efficient Neuromorphic Computing
| Title | ReStoCNet: Residual Stochastic Binary Convolutional Spiking Neural Network for Memory-Efficient Neuromorphic Computing |
| Authors | Gopalakrishnan Srinivasan, Kaushik Roy |
| Abstract | In this work, we propose ReStoCNet, a residual stochastic multilayer convolutional Spiking Neural Network (SNN) composed of binary kernels, to reduce the synaptic memory footprint and enhance the computational efficiency of SNNs for complex pattern recognition tasks. ReStoCNet consists of an input layer followed by stacked convolutional layers for hierarchical input feature extraction, pooling layers for dimensionality reduction, and fully-connected layer for inference. In addition, we introduce residual connections between the stacked convolutional layers to improve the hierarchical feature learning capability of deep SNNs. We propose Spike Timing Dependent Plasticity (STDP) based probabilistic learning algorithm, referred to as Hybrid-STDP (HB-STDP), incorporating Hebbian and anti-Hebbian learning mechanisms, to train the binary kernels forming ReStoCNet in a layer-wise unsupervised manner. We demonstrate the efficacy of ReStoCNet and the presented HB-STDP based unsupervised training methodology on the MNIST and CIFAR-10 datasets. We show that residual connections enable the deeper convolutional layers to self-learn useful high-level input features and mitigate the accuracy loss observed in deep SNNs devoid of residual connections. The proposed ReStoCNet offers >20x kernel memory compression compared to full-precision (32-bit) SNN while yielding high enough classification accuracy on the chosen pattern recognition tasks. |
| Tasks | Dimensionality Reduction |
| Published | 2019-02-11 |
| URL | http://arxiv.org/abs/1902.04161v1 |
| http://arxiv.org/pdf/1902.04161v1.pdf | |
| PWC | https://paperswithcode.com/paper/restocnet-residual-stochastic-binary |
| Repo | |
| Framework | |
Cross-Lingual Relevance Transfer for Document Retrieval
| Title | Cross-Lingual Relevance Transfer for Document Retrieval |
| Authors | Peng Shi, Jimmy Lin |
| Abstract | Recent work has shown the surprising ability of multi-lingual BERT to serve as a zero-shot cross-lingual transfer model for a number of language processing tasks. We combine this finding with a similarly-recently proposal on sentence-level relevance modeling for document retrieval to demonstrate the ability of multi-lingual BERT to transfer models of relevance across languages. Experiments on test collections in five different languages from diverse language families (Chinese, Arabic, French, Hindi, and Bengali) show that models trained with English data improve ranking quality, without any special processing, both for (non-English) mono-lingual retrieval as well as cross-lingual retrieval. |
| Tasks | Cross-Lingual Transfer |
| Published | 2019-11-08 |
| URL | https://arxiv.org/abs/1911.02989v1 |
| https://arxiv.org/pdf/1911.02989v1.pdf | |
| PWC | https://paperswithcode.com/paper/cross-lingual-relevance-transfer-for-document |
| Repo | |
| Framework | |
Dynamic Multi Objective Particle Swarm Optimization based on a New Environment Change Detection Strategy
| Title | Dynamic Multi Objective Particle Swarm Optimization based on a New Environment Change Detection Strategy |
| Authors | Ahlem Aboud, Raja Fdhila, Adel M. Alimi |
| Abstract | The dynamic of real-world optimization problems raises new challenges to the traditional particle swarm optimization (PSO). Responding to these challenges, the dynamic optimization has received considerable attention over the past decade. This paper introduces a new dynamic multi-objective optimization based particle swarm optimization (Dynamic-MOPSO).The main idea of this paper is to solve such dynamic problem based on a new environment change detection strategy using the advantage of the particle swarm optimization. In this way, our approach has been developed not just to obtain the optimal solution, but also to have a capability to detect the environment changes. Thereby, DynamicMOPSO ensures the balance between the exploration and the exploitation in dynamic research space. Our approach is tested through the most popularized dynamic benchmark’s functions to evaluate its performance as a good method. |
| Tasks | |
| Published | 2019-03-25 |
| URL | http://arxiv.org/abs/1903.10681v1 |
| http://arxiv.org/pdf/1903.10681v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-multi-objective-particle-swarm |
| Repo | |
| Framework | |
Understanding Video Content: Efficient Hero Detection and Recognition for the Game “Honor of Kings”
| Title | Understanding Video Content: Efficient Hero Detection and Recognition for the Game “Honor of Kings” |
| Authors | Wentao Yao, Zixun Sun, Xiao Chen |
| Abstract | In order to understand content and automatically extract labels for videos of the game “Honor of Kings”, it is necessary to detect and recognize characters (called “hero”) together with their camps in the game video. In this paper, we propose an efficient two-stage algorithm to detect and recognize heros in game videos. First, we detect all heros in a video frame based on blood bar template-matching method, and classify them according to their camps (self/ friend/ enemy). Then we recognize the name of each hero using one or more deep convolution neural networks. Our method needs almost no work for labelling training and testing samples in the recognition stage. Experiments show its efficiency and accuracy in the task of hero detection and recognition in game videos. |
| Tasks | |
| Published | 2019-07-18 |
| URL | https://arxiv.org/abs/1907.07854v1 |
| https://arxiv.org/pdf/1907.07854v1.pdf | |
| PWC | https://paperswithcode.com/paper/understanding-video-content-efficient-hero |
| Repo | |
| Framework | |
A Bayesian Approach for the Robust Optimisation of Expensive-To-Evaluate Functions
| Title | A Bayesian Approach for the Robust Optimisation of Expensive-To-Evaluate Functions |
| Authors | Nicholas D. Sanders, Richard M. Everson, Jonathan E. Fieldsend, Alma A. M. Rahat |
| Abstract | Many expensive black-box optimisation problems are sensitive to their inputs. In these problems it makes more sense to locate a region of good designs, than a single, possible fragile, optimal design. Expensive black-box functions can be optimised effectively with Bayesian optimisation, where a Gaussian process is a popular choice as a prior over the expensive function. We propose a method for robust optimisation using Bayesian optimisation to find a region of design space in which the expensive function’s performance is insensitive to the inputs whilst retaining a good quality. This is achieved by sampling realisations from a Gaussian process modelling the expensive function and evaluating the improvement for each realisation. The expectation of these improvements can be optimised cheaply with an evolutionary algorithm to determine the next location at which to evaluate the expensive function. We describe an efficient process to locate the optimum expected improvement. We show empirically that evaluating the expensive function at the location in the candidate sweet spot about which the model is most uncertain or at random yield the best convergence in contrast to exploitative schemes. We illustrate our method on six test functions in two, five, and ten dimensions, and demonstrate that it is able to outperform a state-of-the-art approach from the literature. |
| Tasks | Bayesian Optimisation |
| Published | 2019-04-25 |
| URL | https://arxiv.org/abs/1904.11416v2 |
| https://arxiv.org/pdf/1904.11416v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-bayesian-approach-for-the-robust |
| Repo | |
| Framework | |
Reading Protocol: Understanding what has been Read in Interactive Information Retrieval Tasks
| Title | Reading Protocol: Understanding what has been Read in Interactive Information Retrieval Tasks |
| Authors | Daniel Hienert, Dagmar Kern, Matthew Mitsui, Chirag Shah, Nicholas J. Belkin |
| Abstract | In Interactive Information Retrieval (IIR) experiments the user’s gaze motion on web pages is often recorded with eye tracking. The data is used to analyze gaze behavior or to identify Areas of Interest (AOI) the user has looked at. So far, tools for analyzing eye tracking data have certain limitations in supporting the analysis of gaze behavior in IIR experiments. Experiments often consist of a huge number of different visited web pages. In existing analysis tools the data can only be analyzed in videos or images and AOIs for every single web page have to be specified by hand, in a very time consuming process. In this work, we propose the reading protocol software which breaks eye tracking data down to the textual level by considering the HTML structure of the web pages. This has a lot of advantages for the analyst. First and foremost, it can easily be identified on a large scale what has actually been viewed and read on the stimuli pages by the subjects. Second, the web page structure can be used to filter to AOIs. Third, gaze data of multiple users can be presented on the same page, and fourth, fixation times on text can be exported and further processed in other tools. We present the software, its validation, and example use cases with data from three existing IIR experiments. |
| Tasks | Eye Tracking, Information Retrieval |
| Published | 2019-02-12 |
| URL | http://arxiv.org/abs/1902.04262v1 |
| http://arxiv.org/pdf/1902.04262v1.pdf | |
| PWC | https://paperswithcode.com/paper/reading-protocol-understanding-what-has-been |
| Repo | |
| Framework | |
Stable Bayesian Optimisation via Direct Stability Quantification
| Title | Stable Bayesian Optimisation via Direct Stability Quantification |
| Authors | Alistair Shilton, Sunil Gupta, Santu Rana, Svetha Venkatesh, Majid Abdolshah, Dang Nguyen |
| Abstract | In this paper we consider the problem of finding stable maxima of expensive (to evaluate) functions. We are motivated by the optimisation of physical and industrial processes where, for some input ranges, small and unavoidable variations in inputs lead to unacceptably large variation in outputs. Our approach uses multiple gradient Gaussian Process models to estimate the probability that worst-case output variation for specified input perturbation exceeded the desired maxima, and these probabilities are then used to (a) guide the optimisation process toward solutions satisfying our stability criteria and (b) post-filter results to find the best stable solution. We exhibit our algorithm on synthetic and real-world problems and demonstrate that it is able to effectively find stable maxima. |
| Tasks | Bayesian Optimisation |
| Published | 2019-02-21 |
| URL | http://arxiv.org/abs/1902.07846v1 |
| http://arxiv.org/pdf/1902.07846v1.pdf | |
| PWC | https://paperswithcode.com/paper/stable-bayesian-optimisation-via-direct |
| Repo | |
| Framework | |
