January 30, 2020

3430 words 17 mins read

Paper Group ANR 459

Constrained Attractor Selection Using Deep Reinforcement Learning. Gait Recognition via Disentangled Representation Learning. Robustness of Neural Networks to Parameter Quantization. Support Vector Machines on Noisy Intermediate Scale Quantum Computers. An Innovative Word Encoding Method For Text Classification Using Convolutional Neural Network. E …

Constrained Attractor Selection Using Deep Reinforcement Learning


Title	Constrained Attractor Selection Using Deep Reinforcement Learning
Authors	Xue-She Wang, James D. Turner, Brian P. Mann
Abstract	This paper describes an approach for attractor selection in nonlinear dynamical systems with constrained actuation. Attractor selection is achieved using two different deep reinforcement learning methods: 1) the cross-entropy method (CEM) and 2) the deep deterministic policy gradient (DDPG) method. The framework and algorithms for applying these control methods are presented. Experiments were performed on a Duffing oscillator as it is a classic nonlinear dynamical system with multiple attractors. Both methods achieve attractor selection under various control constraints. While these methods have nearly identical success rates, the DDPG method has the advantages a high learning rate, low performance variance, and offers a smooth control approach. This experiment demonstrates the applicability of reinforcement learning to constrained attractor selection problems.
Tasks
Published	2019-09-23
URL	https://arxiv.org/abs/1909.10500v2
PDF	https://arxiv.org/pdf/1909.10500v2.pdf
PWC	https://paperswithcode.com/paper/constrained-attractor-selection-using-deep
Repo
Framework

Gait Recognition via Disentangled Representation Learning


Title	Gait Recognition via Disentangled Representation Learning
Authors	Ziyuan Zhang, Luan Tran, Xi Yin, Yousef Atoum, Xiaoming Liu, Jian Wan, Nanxin Wang
Abstract	Gait, the walking pattern of individuals, is one of the most important biometrics modalities. Most of the existing gait recognition methods take silhouettes or articulated body models as the gait features. These methods suffer from degraded recognition performance when handling confounding variables, such as clothing, carrying and view angle. To remedy this issue, we propose a novel AutoEncoder framework to explicitly disentangle pose and appearance features from RGB imagery and the LSTM-based integration of pose features over time produces the gait feature. In addition, we collect a Frontal-View Gait (FVG) dataset to focus on gait recognition from frontal-view walking, which is a challenging problem since it contains minimal gait cues compared to other views. FVG also includes other important variations, e.g., walking speed, carrying, and clothing. With extensive experiments on CASIA-B, USF and FVG datasets, our method demonstrates superior performance to the state of the arts quantitatively, the ability of feature disentanglement qualitatively, and promising computational efficiency.
Tasks	Gait Recognition, Representation Learning
Published	2019-04-09
URL	http://arxiv.org/abs/1904.04925v1
PDF	http://arxiv.org/pdf/1904.04925v1.pdf
PWC	https://paperswithcode.com/paper/gait-recognition-via-disentangled
Repo
Framework

Robustness of Neural Networks to Parameter Quantization


Title	Robustness of Neural Networks to Parameter Quantization
Authors	Abhishek Murthy, Himel Das, Md Ariful Islam
Abstract	Quantization, a commonly used technique to reduce the memory footprint of a neural network for edge computing, entails reducing the precision of the floating-point representation used for the parameters of the network. The impact of such rounding-off errors on the overall performance of the neural network is estimated using testing, which is not exhaustive and thus cannot be used to guarantee the safety of the model. We present a framework based on Satisfiability Modulo Theory (SMT) solvers to quantify the robustness of neural networks to parameter perturbation. To this end, we introduce notions of local and global robustness that capture the deviation in the confidence of class assignments due to parameter quantization. The robustness notions are then cast as instances of SMT problems and solved automatically using solvers, such as dReal. We demonstrate our framework on two simple Multi-Layer Perceptrons (MLP) that perform binary classification on a two-dimensional input. In addition to quantifying the robustness, we also show that Rectified Linear Unit activation results in higher robustness than linear activations for our MLPs.
Tasks	Quantization
Published	2019-03-26
URL	http://arxiv.org/abs/1903.10672v1
PDF	http://arxiv.org/pdf/1903.10672v1.pdf
PWC	https://paperswithcode.com/paper/robustness-of-neural-networks-to-parameter
Repo
Framework

Support Vector Machines on Noisy Intermediate Scale Quantum Computers


Title	Support Vector Machines on Noisy Intermediate Scale Quantum Computers
Authors	Jiaying Yang, Ahsan Javed Awan, Gemma Vall-Llosera
Abstract	Support vector machine algorithms are considered essential for the implementation of automation in a radio access network. Specifically, they are critical in the prediction of the quality of user experience for video streaming based on device and network-level metrics. Quantum SVM is the quantum analogue of the classical SVM algorithm, which utilizes the properties of quantum computers to speed up the algorithm exponentially. In this work, we derive an optimized preprocessing unit for a quantum SVM that allows classifying any two-dimensional datasets that are linearly separable. We further provide a result readout method of the kernel matrix generation circuit to avoid quantum tomography that, in turn, reduces the quantum circuit depth. We also derive a quantum SVM system based on an optimized HHL quantum circuit with reduced circuit depth.
Tasks
Published	2019-09-26
URL	https://arxiv.org/abs/1909.11988v1
PDF	https://arxiv.org/pdf/1909.11988v1.pdf
PWC	https://paperswithcode.com/paper/support-vector-machines-on-noisy-intermediate
Repo
Framework

An Innovative Word Encoding Method For Text Classification Using Convolutional Neural Network


Title	An Innovative Word Encoding Method For Text Classification Using Convolutional Neural Network
Authors	Amr Adel Helmy, Yasser M. K. Omar, Rania Hodhod
Abstract	Text classification plays a vital role today especially with the intensive use of social networking media. Recently, different architectures of convolutional neural networks have been used for text classification in which one-hot vector, and word embedding methods are commonly used. This paper presents a new language independent word encoding method for text classification. The proposed model converts raw text data to low-level feature dimension with minimal or no preprocessing steps by using a new approach called binary unique number of word “BUNOW”. BUNOW allows each unique word to have an integer ID in a dictionary that is represented as a k-dimensional vector of its binary equivalent. The output vector of this encoding is fed into a convolutional neural network (CNN) model for classification. Moreover, the proposed model reduces the neural network parameters, allows faster computation with few network layers, where a word is atomic representation the document as in word level, and decrease memory consumption for character level representation. The provided CNN model is able to work with other languages or multi-lingual text without the need for any changes in the encoding method. The model outperforms the character level and very deep character level CNNs models in terms of accuracy, network parameters, and memory consumption; the results show total classification accuracy 91.99% and error 8.01% using AG’s News dataset compared to the state of art methods that have total classification accuracy 91.45% and error 8.55%, in addition to the reduction in input feature vector and neural network parameters by 62% and 34%, respectively.
Tasks	Text Classification
Published	2019-03-11
URL	http://arxiv.org/abs/1903.04146v1
PDF	http://arxiv.org/pdf/1903.04146v1.pdf
PWC	https://paperswithcode.com/paper/an-innovative-word-encoding-method-for-text
Repo
Framework

Enabling Smartphone-based Estimation of Heart Rate


Title	Enabling Smartphone-based Estimation of Heart Rate
Authors	Nutta Homdee, Mehdi Boukhechba, Yixue W. Feng, Natalie Kramer, John Lach, Laura E. Barnes
Abstract	Continuous, ubiquitous monitoring through wearable sensors has the potential to collect useful information about users’ context. Heart rate is an important physiologic measure used in a wide variety of applications, such as fitness tracking and health monitoring. However, wearable sensors that monitor heart rate, such as smartwatches and electrocardiogram (ECG) patches, can have gaps in their data streams because of technical issues (e.g., bad wireless channels, battery depletion, etc.) or user-related reasons (e.g. motion artifacts, user compliance, etc.). The ability to use other available sensor data (e.g., smartphone data) to estimate missing heart rate readings is useful to cope with any such gaps, thus improving data quality and continuity. In this paper, we test the feasibility of estimating raw heart rate using smartphone sensor data. Using data generated by 12 participants in a one-week study period, we were able to build both personalized and generalized models using regression, SVM, and random forest algorithms. All three algorithms outperformed the baseline moving-average interpolation method for both personalized and generalized settings. Moreover, our findings suggest that personalized models outperformed the generalized models, which speaks to the importance of considering personal physiology, behavior, and life style in the estimation of heart rate. The promising results provide preliminary evidence of the feasibility of combining smartphone sensor data with wearable sensor data for continuous heart rate monitoring.
Tasks
Published	2019-12-18
URL	https://arxiv.org/abs/1912.08910v1
PDF	https://arxiv.org/pdf/1912.08910v1.pdf
PWC	https://paperswithcode.com/paper/enabling-smartphone-based-estimation-of-heart
Repo
Framework

Parallel Distributed Logistic Regression for Vertical Federated Learning without Third-Party Coordinator


Title	Parallel Distributed Logistic Regression for Vertical Federated Learning without Third-Party Coordinator
Authors	Shengwen Yang, Bing Ren, Xuhui Zhou, Liping Liu
Abstract	Federated Learning is a new distributed learning mechanism which allows model training on a large corpus of decentralized data owned by different data providers, without sharing or leakage of raw data. According to the characteristics of data dis-tribution, it could be usually classified into three categories: horizontal federated learning, vertical federated learning, and federated transfer learning. In this paper we present a solution for parallel dis-tributed logistic regression for vertical federated learning. As compared with existing works, the role of third-party coordinator is removed in our proposed solution. The system is built on the pa-rameter server architecture and aims to speed up the model training via utilizing a cluster of servers in case of large volume of training data. We also evaluate the performance of the parallel distributed model training and the experimental results show the great scalability of the system.
Tasks	Transfer Learning
Published	2019-11-22
URL	https://arxiv.org/abs/1911.09824v1
PDF	https://arxiv.org/pdf/1911.09824v1.pdf
PWC	https://paperswithcode.com/paper/parallel-distributed-logistic-regression-for
Repo
Framework

Using Deep Neural Networks for Estimating Loop Unrolling Factor


Title	Using Deep Neural Networks for Estimating Loop Unrolling Factor
Authors	Asma Balamane, Zina Taklit
Abstract	Optimizing programs requires deep expertise. On one hand, it is a tedious task, because it requires a lot of tests to find out the best combination of optimizations to apply with their best factors. On the other hand, this task is critical, because it may degrade the performance of programs instead of improving it. The automatization of this task can deal with this problem and permit to obtain good results. Optimizing loops that take the most significant part of the program execution time plays a crucial role to achieve best performance. In this paper, we address Loop unrolling optimization, by proposing a deep Neural Network model to predict the optimal unrolling factor for programs written for TIRAMISU. TIRAMISU is a polyhedral framework designed to generate high performance code for multiple platforms including multicores, GPUs, and distributed machines. TIRAMISU introduces a scheduling language with novel commands to explicitly manage the complexities that arise when targeting these systems.
Tasks
Published	2019-11-10
URL	https://arxiv.org/abs/1911.03991v1
PDF	https://arxiv.org/pdf/1911.03991v1.pdf
PWC	https://paperswithcode.com/paper/using-deep-neural-networks-for-estimating
Repo
Framework

Quantum process tomography with unknown single-preparation input states


Title	Quantum process tomography with unknown single-preparation input states
Authors	Yannick Deville, Alain Deville
Abstract	Quantum Process Tomography (QPT) methods aim at identifying, i.e. estimating, a given quantum process. QPT is a major quantum information processing tool, since it especially allows one to characterize the actual behavior of quantum gates, which are the building blocks of quantum computers. However, usual QPT procedures are complicated, since they set several constraints on the quantum states used as inputs of the process to be characterized. In this paper, we extend QPT so as to avoid two such constraints. On the one hand, usual QPT methods requires one to know, hence to precisely control (i.e. prepare), the specific quantum states used as inputs of the considered quantum process, which is cumbersome. We therefore propose a Blind, or unsupervised, extension of QPT (i.e. BQPT), which means that this approach uses input quantum states whose values are unknown and arbitrary, except that they are requested to meet some general known properties (and this approach exploits the output states of the considered quantum process). On the other hand, usual QPT methods require one to be able to prepare many copies of the same (known) input state, which is constraining. On the contrary, we propose “single-preparation methods”, i.e. methods which can operate with only one instance of each considered input state. These two new concepts are here illustrated with practical BQPT methods which are numerically validated, in the case when: i) random pure states are used as inputs and their required properties are especially related to the statistical independence of the random variables that define them, ii) the considered quantum process is based on cylindrical-symmetry Heisenberg spin coupling. These concepts may be extended to a much wider class of processes and to BQPT methods based on other input quantum state properties.
Tasks
Published	2019-09-18
URL	https://arxiv.org/abs/1909.08401v1
PDF	https://arxiv.org/pdf/1909.08401v1.pdf
PWC	https://paperswithcode.com/paper/quantum-process-tomography-with-unknown
Repo
Framework

Convergence Analysis of Machine Learning Algorithms for the Numerical Solution of Mean Field Control and Games: II – The Finite Horizon Case


Title	Convergence Analysis of Machine Learning Algorithms for the Numerical Solution of Mean Field Control and Games: II – The Finite Horizon Case
Authors	René Carmona, Mathieu Laurière
Abstract	We propose two numerical methods for the optimal control of McKean-Vlasov dynamics in finite time horizon. Both methods are based on the introduction of a suitable loss function defined over the parameters of a neural network. This allows the use of machine learning tools, and efficient implementations of stochastic gradient descent in order to perform the optimization. In the first method, the loss function stems directly from the optimal control problem. We analyze the approximation and the estimation errors. The second method tackles a generic forward-backward stochastic differential equation system (FBSDE) of McKean-Vlasov type, and relies on suitable reformulation as a mean field control problem. To provide a guarantee on how our numerical schemes approximate the solution of the original mean field control problem, we introduce a new optimization problem, directly amenable to numerical computation, and for which we rigorously provide an error rate. Several numerical examples are provided. Both methods can easily be applied to problems with common noise, which is not the case with the existing technology. Furthermore, although the first approach is designed for mean field control problems, the second is more general and can also be applied to the FBSDE arising in the theory of mean field games.
Tasks
Published	2019-08-05
URL	https://arxiv.org/abs/1908.01613v1
PDF	https://arxiv.org/pdf/1908.01613v1.pdf
PWC	https://paperswithcode.com/paper/convergence-analysis-of-machine-learning-1
Repo
Framework

Stabilising priors for robust Bayesian deep learning


Title	Stabilising priors for robust Bayesian deep learning
Authors	Felix McGregor, Arnu Pretorius, Johan du Preez, Steve Kroon
Abstract	Bayesian neural networks (BNNs) have developed into useful tools for probabilistic modelling due to recent advances in variational inference enabling large scale BNNs. However, BNNs remain brittle and hard to train, especially: (1) when using deep architectures consisting of many hidden layers and (2) in situations with large weight variances. We use signal propagation theory to quantify these challenges and propose self-stabilising priors. This is achieved by a reformulation of the ELBO to allow the prior to influence network signal propagation. Then, we develop a stabilising prior, where the distributional parameters of the prior are adjusted before each forward pass to ensure stability of the propagating signal. This stabilised signal propagation leads to improved convergence and robustness making it possible to train deeper networks and in more noisy settings.
Tasks
Published	2019-10-23
URL	https://arxiv.org/abs/1910.10386v1
PDF	https://arxiv.org/pdf/1910.10386v1.pdf
PWC	https://paperswithcode.com/paper/stabilising-priors-for-robust-bayesian-deep
Repo
Framework

Deep Learning for Spatio-Temporal Data Mining: A Survey


Title	Deep Learning for Spatio-Temporal Data Mining: A Survey
Authors	Senzhang Wang, Jiannong Cao, Philip S. Yu
Abstract	With the fast development of various positioning techniques such as Global Position System (GPS), mobile devices and remote sensing, spatio-temporal data has become increasingly available nowadays. Mining valuable knowledge from spatio-temporal data is critically important to many real world applications including human mobility understanding, smart transportation, urban planning, public safety, health care and environmental management. As the number, volume and resolution of spatio-temporal datasets increase rapidly, traditional data mining methods, especially statistics based methods for dealing with such data are becoming overwhelmed. Recently, with the advances of deep learning techniques, deep leaning models such as convolutional neural network (CNN) and recurrent neural network (RNN) have enjoyed considerable success in various machine learning tasks due to their powerful hierarchical feature learning ability in both spatial and temporal domains, and have been widely applied in various spatio-temporal data mining (STDM) tasks such as predictive learning, representation learning, anomaly detection and classification. In this paper, we provide a comprehensive survey on recent progress in applying deep learning techniques for STDM. We first categorize the types of spatio-temporal data and briefly introduce the popular deep learning models that are used in STDM. Then a framework is introduced to show a general pipeline of the utilization of deep learning models for STDM. Next we classify existing literatures based on the types of ST data, the data mining tasks, and the deep learning models, followed by the applications of deep learning for STDM in different domains including transportation, climate science, human mobility, location based social network, crime analysis, and neuroscience. Finally, we conclude the limitations of current research and point out future research directions.
Tasks	Anomaly Detection, Representation Learning
Published	2019-06-11
URL	https://arxiv.org/abs/1906.04928v2
PDF	https://arxiv.org/pdf/1906.04928v2.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-spatio-temporal-data-mining
Repo
Framework

Learned 3D Shape Representations Using Fused Geometrically Augmented Images: Application to Facial Expression and Action Unit Detection


Title	Learned 3D Shape Representations Using Fused Geometrically Augmented Images: Application to Facial Expression and Action Unit Detection
Authors	Bilal Taha, Munawar Hayat, Stefano Berretti, Naoufel Werghi
Abstract	This paper proposes an approach to learn generic multi-modal mesh surface representations using a novel scheme for fusing texture and geometric data. Our approach defines an inverse mapping between different geometric descriptors computed on the mesh surface or its down-sampled version, and the corresponding 2D texture image of the mesh, allowing the construction of fused geometrically augmented images (FGAI). This new fused modality enables us to learn feature representations from 3D data in a highly efficient manner by simply employing standard convolutional neural networks in a transfer-learning mode. In contrast to existing methods, the proposed approach is both computationally and memory efficient, preserves intrinsic geometric information and learns highly discriminative feature representation by effectively fusing shape and texture information at data level. The efficacy of our approach is demonstrated for the tasks of facial action unit detection and expression classification. The extensive experiments conducted on the Bosphorus and BU-4DFE datasets, show that our method produces a significant boost in the performance when compared to state-of-the-art solutions
Tasks	Action Unit Detection, Facial Action Unit Detection, Transfer Learning
Published	2019-04-08
URL	http://arxiv.org/abs/1904.04297v1
PDF	http://arxiv.org/pdf/1904.04297v1.pdf
PWC	https://paperswithcode.com/paper/learned-3d-shape-representations-using-fused
Repo
Framework

Missing Features Reconstruction and Its Impact on Classification Accuracy


Title	Missing Features Reconstruction and Its Impact on Classification Accuracy
Authors	Magda Friedjungová, Daniel Vašata, Marcel Jiřina
Abstract	In real-world applications, we can encounter situations when a well-trained model has to be used to predict from a damaged dataset. The damage caused by missing or corrupted values can be either on the level of individual instances or on the level of entire features. Both situations have a negative impact on the usability of the model on such a dataset. This paper focuses on the scenario where entire features are missing which can be understood as a specific case of transfer learning. Our aim is to experimentally research the influence of various imputation methods on the performance of several classification models. The imputation impact is researched on a combination of traditional methods such as k-NN, linear regression, and MICE compared to modern imputation methods such as multi-layer perceptron (MLP) and gradient boosted trees (XGBT). For linear regression, MLP, and XGBT we also propose two approaches to using them for multiple features imputation. The experiments were performed on both real world and artificial datasets with continuous features where different numbers of features, varying from one feature to 50%, were missing. The results show that MICE and linear regression are generally good imputers regardless of the conditions. On the other hand, the performance of MLP and XGBT is strongly dataset dependent. Their performance is the best in some cases, but more often they perform worse than MICE or linear regression.
Tasks	Imputation, Transfer Learning
Published	2019-11-09
URL	https://arxiv.org/abs/1911.03658v1
PDF	https://arxiv.org/pdf/1911.03658v1.pdf
PWC	https://paperswithcode.com/paper/missing-features-reconstruction-and-its
Repo
Framework

Reachability Deficits in Quantum Approximate Optimization


Title	Reachability Deficits in Quantum Approximate Optimization
Authors	V. Akshay, H. Philathong, M. E. S. Morales, J. Biamonte
Abstract	The quantum approximate optimization algorithm (QAOA) has rapidly become a cornerstone of contemporary quantum algorithm development. Despite a growing range of applications, only a few results have been developed towards understanding the algorithms ultimate limitations. Here we report that QAOA exhibits a strong dependence on a problem instances constraint to variable ratio$-$this problem density places a limiting restriction on the algorithms capacity to minimize a corresponding objective function (and hence solve optimization problem instances). Such $reachability~deficits$ persist even in the absence of barren plateaus [McClean et al., 2018] and are outside of the recently reported level-1 QAOA limitations [Hastings 2019]. These findings are among the first to determine strong limitations on variational quantum approximate optimization.
Tasks
Published	2019-06-26
URL	https://arxiv.org/abs/1906.11259v2
PDF	https://arxiv.org/pdf/1906.11259v2.pdf
PWC	https://paperswithcode.com/paper/reachability-deficits-in-quantum-approximate
Repo
Framework