Paper Group ANR 617
Gray-box Adversarial Training. Swarm robotics in wireless distributed protocol design for coordinating robots involved in cooperative tasks. Speaker Clustering With Neural Networks And Audio Processing. Deep learning algorithm for data-driven simulation of noisy dynamical system. The core consistency of a compressed tensor. Semi-Supervised Learning …
Gray-box Adversarial Training
| Title | Gray-box Adversarial Training |
| Authors | Vivek B. S., Konda Reddy Mopuri, R. Venkatesh Babu |
| Abstract | Adversarial samples are perturbed inputs crafted to mislead the machine learning systems. A training mechanism, called adversarial training, which presents adversarial samples along with clean samples has been introduced to learn robust models. In order to scale adversarial training for large datasets, these perturbations can only be crafted using fast and simple methods (e.g., gradient ascent). However, it is shown that adversarial training converges to a degenerate minimum, where the model appears to be robust by generating weaker adversaries. As a result, the models are vulnerable to simple black-box attacks. In this paper we, (i) demonstrate the shortcomings of existing evaluation policy, (ii) introduce novel variants of white-box and black-box attacks, dubbed gray-box adversarial attacks” based on which we propose novel evaluation method to assess the robustness of the learned models, and (iii) propose a novel variant of adversarial training, named Graybox Adversarial Training” that uses intermediate versions of the models to seed the adversaries. Experimental evaluation demonstrates that the models trained using our method exhibit better robustness compared to both undefended and adversarially trained model |
| Tasks | |
| Published | 2018-08-06 |
| URL | http://arxiv.org/abs/1808.01753v1 |
| http://arxiv.org/pdf/1808.01753v1.pdf | |
| PWC | https://paperswithcode.com/paper/gray-box-adversarial-training |
| Repo | |
| Framework | |
Swarm robotics in wireless distributed protocol design for coordinating robots involved in cooperative tasks
| Title | Swarm robotics in wireless distributed protocol design for coordinating robots involved in cooperative tasks |
| Authors | F. De Rango, N. Palmieri, X. S. Yang, S. Marano |
| Abstract | The mine detection in an unexplored area is an optimization problem where multiple mines, randomly distributed throughout an area, need to be discovered and disarmed in a minimum amount of time. We propose a strategy to explore an unknown area, using a stigmergy approach based on ants behavior, and a novel swarm based protocol to recruit and coordinate robots for disarming the mines cooperatively. Simulation tests are presented to show the effectiveness of our proposed Ant-based Task Robot Coordination (ATRC) with only the exploration task and with both exploration and recruiting strategies. Multiple minimization objectives have been considered: the robots’ recruiting time and the overall area exploration time. We discuss, through simulation, different cases under different network and field conditions, performed by the robots. The results have shown that the proposed decentralized approaches enable the swarm of robots to perform cooperative tasks intelligently without any central control. |
| Tasks | |
| Published | 2018-04-22 |
| URL | http://arxiv.org/abs/1804.08096v1 |
| http://arxiv.org/pdf/1804.08096v1.pdf | |
| PWC | https://paperswithcode.com/paper/swarm-robotics-in-wireless-distributed |
| Repo | |
| Framework | |
Speaker Clustering With Neural Networks And Audio Processing
| Title | Speaker Clustering With Neural Networks And Audio Processing |
| Authors | Maxime Jumelle, Taqiyeddine Sakmeche |
| Abstract | Speaker clustering is the task of differentiating speakers in a recording. In a way, the aim is to answer “who spoke when” in audio recordings. A common method used in industry is feature extraction directly from the recording thanks to MFCC features, and by using well-known techniques such as Gaussian Mixture Models (GMM) and Hidden Markov Models (HMM). In this paper, we studied neural networks (especially CNN) followed by clustering and audio processing in the quest to reach similar accuracy to state-of-the-art methods. |
| Tasks | |
| Published | 2018-03-22 |
| URL | http://arxiv.org/abs/1803.08276v1 |
| http://arxiv.org/pdf/1803.08276v1.pdf | |
| PWC | https://paperswithcode.com/paper/speaker-clustering-with-neural-networks-and |
| Repo | |
| Framework | |
Deep learning algorithm for data-driven simulation of noisy dynamical system
| Title | Deep learning algorithm for data-driven simulation of noisy dynamical system |
| Authors | Kyongmin Yeo, Igor Melnyk |
| Abstract | We present a deep learning model, DE-LSTM, for the simulation of a stochastic process with an underlying nonlinear dynamics. The deep learning model aims to approximate the probability density function of a stochastic process via numerical discretization and the underlying nonlinear dynamics is modeled by the Long Short-Term Memory (LSTM) network. It is shown that, when the numerical discretization is used, the function estimation problem can be solved by a multi-label classification problem. A penalized maximum log likelihood method is proposed to impose a smoothness condition in the prediction of the probability distribution. We show that the time evolution of the probability distribution can be computed by a high-dimensional integration of the transition probability of the LSTM internal states. A Monte Carlo algorithm to approximate the high-dimensional integration is outlined. The behavior of DE-LSTM is thoroughly investigated by using the Ornstein-Uhlenbeck process and noisy observations of nonlinear dynamical systems; Mackey-Glass time series and forced Van der Pol oscillator. It is shown that DE-LSTM makes a good prediction of the probability distribution without assuming any distributional properties of the stochastic process. For a multiple-step forecast of the Mackey-Glass time series, the prediction uncertainty, denoted by the 95% confidence interval, first grows, then dynamically adjusts following the evolution of the system, while in the simulation of the forced Van der Pol oscillator, the prediction uncertainty does not grow in time even for a 3,000-step forecast. |
| Tasks | Multi-Label Classification, Time Series |
| Published | 2018-02-22 |
| URL | http://arxiv.org/abs/1802.08323v2 |
| http://arxiv.org/pdf/1802.08323v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-algorithm-for-data-driven |
| Repo | |
| Framework | |
The core consistency of a compressed tensor
| Title | The core consistency of a compressed tensor |
| Authors | Georgios Tsitsikas, Evangelos E. Papalexakis |
| Abstract | Tensor decomposition on big data has attracted significant attention recently. Among the most popular methods is a class of algorithms that leverages compression in order to reduce the size of the tensor and potentially parallelize computations. A fundamental requirement for such methods to work properly is that the low-rank tensor structure is retained upon compression. In lieu of efficient and realistic means of computing and studying the effects of compression on the low rank of a tensor, we study the effects of compression on the core consistency; a widely used heuristic that has been used as a proxy for estimating that low rank. We provide theoretical analysis, where we identify sufficient conditions for the compression such that the core consistency is preserved, and we conduct extensive experiments that validate our analysis. Further, we explore popular compression schemes and how they affect the core consistency. |
| Tasks | |
| Published | 2018-11-18 |
| URL | http://arxiv.org/abs/1811.07428v1 |
| http://arxiv.org/pdf/1811.07428v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-core-consistency-of-a-compressed-tensor |
| Repo | |
| Framework | |
Semi-Supervised Learning via Compact Latent Space Clustering
| Title | Semi-Supervised Learning via Compact Latent Space Clustering |
| Authors | Konstantinos Kamnitsas, Daniel C. Castro, Loic Le Folgoc, Ian Walker, Ryutaro Tanno, Daniel Rueckert, Ben Glocker, Antonio Criminisi, Aditya Nori |
| Abstract | We present a novel cost function for semi-supervised learning of neural networks that encourages compact clustering of the latent space to facilitate separation. The key idea is to dynamically create a graph over embeddings of labeled and unlabeled samples of a training batch to capture underlying structure in feature space, and use label propagation to estimate its high and low density regions. We then devise a cost function based on Markov chains on the graph that regularizes the latent space to form a single compact cluster per class, while avoiding to disturb existing clusters during optimization. We evaluate our approach on three benchmarks and compare to state-of-the art with promising results. Our approach combines the benefits of graph-based regularization with efficient, inductive inference, does not require modifications to a network architecture, and can thus be easily applied to existing networks to enable an effective use of unlabeled data. |
| Tasks | |
| Published | 2018-06-07 |
| URL | http://arxiv.org/abs/1806.02679v2 |
| http://arxiv.org/pdf/1806.02679v2.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-learning-via-compact-latent |
| Repo | |
| Framework | |
Semantic segmentation of trajectories with agent models
| Title | Semantic segmentation of trajectories with agent models |
| Authors | Daisuke Ogawa, Toru Tamaki, Bisser Raytchev, Kazufumi Kaneda |
| Abstract | In many cases, such as trajectories clustering and classification, we often divide a trajectory into segments as preprocessing. In this paper, we propose a trajectory semantic segmentation method based on learned behavior models. In the proposed method, we learn some behavior models from video sequences. Next, using learned behavior models and a hidden Markov model, we segment a trajectory into semantic segments. Comparing with the Ramer-Douglas-Peucker algorithm, we show the effectiveness of the proposed method. |
| Tasks | Semantic Segmentation |
| Published | 2018-02-27 |
| URL | http://arxiv.org/abs/1802.09659v1 |
| http://arxiv.org/pdf/1802.09659v1.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-segmentation-of-trajectories-with |
| Repo | |
| Framework | |
Robust Model Predictive Control of Irrigation Systems with Active Uncertainty Learning and Data Analytics
| Title | Robust Model Predictive Control of Irrigation Systems with Active Uncertainty Learning and Data Analytics |
| Authors | Chao Shang, Wei-Han Chen, Abraham Duncan Stroock, Fengqi You |
| Abstract | We develop a novel data-driven robust model predictive control (DDRMPC) approach for automatic control of irrigation systems. The fundamental idea is to integrate both mechanistic models, which describe dynamics in soil moisture variations, and data-driven models, which characterize uncertainty in forecast errors of evapotranspiration and precipitation, into a holistic systems control framework. To better capture the support of uncertainty distribution, we take a new learning-based approach by constructing uncertainty sets from historical data. For evapotranspiration forecast error, the support vector clustering-based uncertainty set is adopted, which can be conveniently built from historical data. As for precipitation forecast errors, we analyze the dependence of their distribution on forecast values, and further design a tailored uncertainty set based on the properties of this type of uncertainty. In this way, the overall uncertainty distribution can be elaborately described, which finally contributes to rational and efficient control decisions. To assure the quality of data-driven uncertainty sets, a training-calibration scheme is used to provide theoretical performance guarantees. A generalized affine decision rule is adopted to obtain tractable approximations of optimal control problems, thereby ensuring the practicability of DDRMPC. Case studies using real data show that, DDRMPC can reliably maintain soil moisture above the safety level and avoid crop devastation. The proposed DDRMPC approach leads to a 40% reduction of total water consumption compared to the fine-tuned open-loop control strategy. In comparison with the carefully tuned rule-based control and certainty equivalent model predictive control, the proposed DDRMPC approach can significantly reduce the total water consumption and improve the control performance. |
| Tasks | Calibration |
| Published | 2018-10-14 |
| URL | https://arxiv.org/abs/1810.05947v3 |
| https://arxiv.org/pdf/1810.05947v3.pdf | |
| PWC | https://paperswithcode.com/paper/robust-model-predictive-control-of-irrigation |
| Repo | |
| Framework | |
Self-adaptive Privacy Concern Detection for User-generated Content
| Title | Self-adaptive Privacy Concern Detection for User-generated Content |
| Authors | Xuan-Son Vu, Lili Jiang |
| Abstract | To protect user privacy in data analysis, a state-of-the-art strategy is differential privacy in which scientific noise is injected into the real analysis output. The noise masks individual’s sensitive information contained in the dataset. However, determining the amount of noise is a key challenge, since too much noise will destroy data utility while too little noise will increase privacy risk. Though previous research works have designed some mechanisms to protect data privacy in different scenarios, most of the existing studies assume uniform privacy concerns for all individuals. Consequently, putting an equal amount of noise to all individuals leads to insufficient privacy protection for some users, while over-protecting others. To address this issue, we propose a self-adaptive approach for privacy concern detection based on user personality. Our experimental studies demonstrate the effectiveness to address a suitable personalized privacy protection for cold-start users (i.e., without their privacy-concern information in training data). |
| Tasks | |
| Published | 2018-06-19 |
| URL | http://arxiv.org/abs/1806.07221v1 |
| http://arxiv.org/pdf/1806.07221v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-adaptive-privacy-concern-detection-for |
| Repo | |
| Framework | |
Mugeetion: Musical Interface Using Facial Gesture and Emotion
| Title | Mugeetion: Musical Interface Using Facial Gesture and Emotion |
| Authors | Eunjeong Stella Koh, Shahrokh Yadegari |
| Abstract | People feel emotions when listening to music. However, emotions are not tangible objects that can be exploited in the music composition process as they are difficult to capture and quantify in algorithms. We present a novel musical interface, Mugeetion, designed to capture occurring instances of emotional states from users’ facial gestures and relay that data to associated musical features. Mugeetion can translate qualitative data of emotional states into quantitative data, which can be utilized in the sound generation process. We also presented and tested this work in the exhibition of sound installation, Hearing Seascape, using the audiences’ facial expressions. Audiences heard changes in the background sound based on their emotional state. The process contributes multiple research areas, such as gesture tracking systems, emotion-sound modeling, and the connection between sound and facial gesture. |
| Tasks | |
| Published | 2018-09-14 |
| URL | http://arxiv.org/abs/1809.05502v2 |
| http://arxiv.org/pdf/1809.05502v2.pdf | |
| PWC | https://paperswithcode.com/paper/mugeetion-musical-interface-using-facial |
| Repo | |
| Framework | |
Classifying movie genres by analyzing text reviews
| Title | Classifying movie genres by analyzing text reviews |
| Authors | Adam Nyberg |
| Abstract | This paper proposes a method for classifying movie genres by only looking at text reviews. The data used are from Large Movie Review Dataset v1.0 and IMDb. This paper compared a K-nearest neighbors (KNN) model and a multilayer perceptron (MLP) that uses tf-idf as input features. The paper also discusses different evaluation metrics used when doing multi-label classification. For the data used in this research, the KNN model performed the best with an accuracy of 55.4% and a Hamming loss of 0.047. |
| Tasks | Multi-Label Classification |
| Published | 2018-02-14 |
| URL | http://arxiv.org/abs/1802.05322v1 |
| http://arxiv.org/pdf/1802.05322v1.pdf | |
| PWC | https://paperswithcode.com/paper/classifying-movie-genres-by-analyzing-text |
| Repo | |
| Framework | |
An Improved LPTC Neural Model for Background Motion Direction Estimation
| Title | An Improved LPTC Neural Model for Background Motion Direction Estimation |
| Authors | Hongxin Wang, Jigen Peng, Shigang Yue |
| Abstract | A class of specialized neurons, called lobula plate tangential cells (LPTCs) has been shown to respond strongly to wide-field motion. The classic model, elementary motion detector (EMD) and its improved model, two-quadrant detector (TQD) have been proposed to simulate LPTCs. Although EMD and TQD can percept background motion, their outputs are so cluttered that it is difficult to discriminate actual motion direction of the background. In this paper, we propose a max operation mechanism to model a newly-found transmedullary neuron Tm9 whose physiological properties do not map onto EMD and TQD. This proposed max operation mechanism is able to improve the detection performance of TQD in cluttered background by filtering out irrelevant motion signals. We will demonstrate the functionality of this proposed mechanism in wide-field motion perception. |
| Tasks | |
| Published | 2018-01-22 |
| URL | http://arxiv.org/abs/1801.06976v1 |
| http://arxiv.org/pdf/1801.06976v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-improved-lptc-neural-model-for-background |
| Repo | |
| Framework | |
In-Edge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learning
| Title | In-Edge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learning |
| Authors | Xiaofei Wang, Yiwen Han, Chenyang Wang, Qiyang Zhao, Xu Chen, Min Chen |
| Abstract | Recently, along with the rapid development of mobile communication technology, edge computing theory and techniques have been attracting more and more attentions from global researchers and engineers, which can significantly bridge the capacity of cloud and requirement of devices by the network edges, and thus can accelerate the content deliveries and improve the quality of mobile services. In order to bring more intelligence to the edge systems, compared to traditional optimization methodology, and driven by the current deep learning techniques, we propose to integrate the Deep Reinforcement Learning techniques and Federated Learning framework with the mobile edge systems, for optimizing the mobile edge computing, caching and communication. And thus, we design the “In-Edge AI” framework in order to intelligently utilize the collaboration among devices and edge nodes to exchange the learning parameters for a better training and inference of the models, and thus to carry out dynamic system-level optimization and application-level enhancement while reducing the unnecessary system communication load. “In-Edge AI” is evaluated and proved to have near-optimal performance but relatively low overhead of learning, while the system is cognitive and adaptive to the mobile communication systems. Finally, we discuss several related challenges and opportunities for unveiling a promising upcoming future of “In-Edge AI”. |
| Tasks | |
| Published | 2018-09-19 |
| URL | https://arxiv.org/abs/1809.07857v2 |
| https://arxiv.org/pdf/1809.07857v2.pdf | |
| PWC | https://paperswithcode.com/paper/in-edge-ai-intelligentizing-mobile-edge |
| Repo | |
| Framework | |
On the Flip Side: Identifying Counterexamples in Visual Question Answering
| Title | On the Flip Side: Identifying Counterexamples in Visual Question Answering |
| Authors | Gabriel Grand, Aron Szanto, Yoon Kim, Alexander Rush |
| Abstract | Visual question answering (VQA) models respond to open-ended natural language questions about images. While VQA is an increasingly popular area of research, it is unclear to what extent current VQA architectures learn key semantic distinctions between visually-similar images. To investigate this question, we explore a reformulation of the VQA task that challenges models to identify counterexamples: images that result in a different answer to the original question. We introduce two methods for evaluating existing VQA models against a supervised counterexample prediction task, VQA-CX. While our models surpass existing benchmarks on VQA-CX, we find that the multimodal representations learned by an existing state-of-the-art VQA model do not meaningfully contribute to performance on this task. These results call into question the assumption that successful performance on the VQA benchmark is indicative of general visual-semantic reasoning abilities. |
| Tasks | Question Answering, Visual Question Answering |
| Published | 2018-06-03 |
| URL | http://arxiv.org/abs/1806.00857v3 |
| http://arxiv.org/pdf/1806.00857v3.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-flip-side-identifying-counterexamples |
| Repo | |
| Framework | |
A Model for Auto-Programming for General Purposes
| Title | A Model for Auto-Programming for General Purposes |
| Authors | Juyang Weng |
| Abstract | The Universal Turing Machine (TM) is a model for VonNeumann computers — general-purpose computers. A human brain can inside-skull-automatically learn a universal TM so that he acts as a general-purpose computer and writes a computer program for any practical purposes. It is unknown whether a machine can accomplish the same. This theoretical work shows how the Developmental Network (DN) can accomplish this. Unlike a traditional TM, the TM learned by DN is a super TM — Grounded, Emergent, Natural, Incremental, Skulled, Attentive, Motivated, and Abstractive (GENISAMA). A DN is free of any central controller (e.g., Master Map, convolution, or error back-propagation). Its learning from a teacher TM is one transition observation at a time, immediate, and error-free until all its neurons have been initialized by early observed teacher transitions. From that point on, the DN is no longer error-free but is always optimal at every time instance in the sense of maximal likelihood, conditioned on its limited computational resources and the learning experience. This letter also extends the Church-Turing thesis to automatic programming for general purposes and sketchily proved it. |
| Tasks | |
| Published | 2018-10-12 |
| URL | http://arxiv.org/abs/1810.05764v1 |
| http://arxiv.org/pdf/1810.05764v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-model-for-auto-programming-for-general |
| Repo | |
| Framework | |
