January 31, 2020

3201 words 16 mins read

Paper Group ANR 48

Data-efficient Co-Adaptation of Morphology and Behaviour with Deep Reinforcement Learning. Convergence of gradient descent-ascent analyzed as a Newtonian dynamical system with dissipation. Towards robust audio spoofing detection: a detailed comparison of traditional and learned features. Clustering Degree-Corrected Stochastic Block Model with Outli …

Data-efficient Co-Adaptation of Morphology and Behaviour with Deep Reinforcement Learning


Title	Data-efficient Co-Adaptation of Morphology and Behaviour with Deep Reinforcement Learning
Authors	Kevin Sebastian Luck, Heni Ben Amor, Roberto Calandra
Abstract	Humans and animals are capable of quickly learning new behaviours to solve new tasks. Yet, we often forget that they also rely on a highly specialized morphology that co-adapted with motor control throughout thousands of years. Although compelling, the idea of co-adapting morphology and behaviours in robots is often unfeasible because of the long manufacturing times, and the need to re-design an appropriate controller for each morphology. In this paper, we propose a novel approach to automatically and efficiently co-adapt a robot morphology and its controller. Our approach is based on recent advances in deep reinforcement learning, and specifically the soft actor critic algorithm. Key to our approach is the possibility of leveraging previously tested morphologies and behaviors to estimate the performance of new candidate morphologies. As such, we can make full use of the information available for making more informed decisions, with the ultimate goal of achieving a more data-efficient co-adaptation (i.e., reducing the number of morphologies and behaviors tested). Simulated experiments show that our approach requires drastically less design prototypes to find good morphology-behaviour combinations, making this method particularly suitable for future co-adaptation of robot designs in the real world.
Tasks
Published	2019-11-15
URL	https://arxiv.org/abs/1911.06832v1
PDF	https://arxiv.org/pdf/1911.06832v1.pdf
PWC	https://paperswithcode.com/paper/data-efficient-co-adaptation-of-morphology
Repo
Framework

Convergence of gradient descent-ascent analyzed as a Newtonian dynamical system with dissipation


Title	Convergence of gradient descent-ascent analyzed as a Newtonian dynamical system with dissipation
Authors	H. Sebastian Seung
Abstract	A dynamical system is defined in terms of the gradient of a payoff function. Dynamical variables are of two types, ascent and descent. The ascent variables move in the direction of the gradient, while the descent variables move in the opposite direction. Dynamical systems of this form or very similar forms have been studied in diverse fields such as game theory, optimization, neural networks, and population biology. Gradient descent-ascent is approximated as a Newtonian dynamical system that conserves total energy, defined as the sum of the kinetic energy and a potential energy that is proportional to the payoff function. The error of the approximation is a residual force that violates energy conservation. If the residual force is purely dissipative, then the energy serves as a Lyapunov function, and convergence of bounded trajectories to steady states is guaranteed. A previous convergence theorem due to Kose and Uzawa required the payoff function to be convex in the descent variables, and concave in the ascent variables. Here the assumption is relaxed, so that the payoff function need only be globally `less convex' or` more concave’ in the ascent variables than in the descent variables. Such relative convexity conditions allow the existence of multiple steady states, unlike the convex-concave assumption. When combined with sufficient conditions that imply the existence of a minimax equilibrium, boundedness of trajectories is also assured.
Tasks
Published	2019-03-05
URL	http://arxiv.org/abs/1903.02536v1
PDF	http://arxiv.org/pdf/1903.02536v1.pdf
PWC	https://paperswithcode.com/paper/convergence-of-gradient-descent-ascent
Repo
Framework

Towards robust audio spoofing detection: a detailed comparison of traditional and learned features


Title	Towards robust audio spoofing detection: a detailed comparison of traditional and learned features
Authors	Balamurali BT, Kin Wah Edward Lin, Simon Lui, Jer-Ming Chen, Dorien Herremans
Abstract	Automatic speaker verification, like every other biometric system, is vulnerable to spoofing attacks. Using only a few minutes of recorded voice of a genuine client of a speaker verification system, attackers can develop a variety of spoofing attacks that might trick such systems. Detecting these attacks using the audio cues present in the recordings is an important challenge. Most existing spoofing detection systems depend on knowing the used spoofing technique. With this research, we aim at overcoming this limitation, by examining robust audio features, both traditional and those learned through an autoencoder, that are generalizable over different types of replay spoofing. Furthermore, we provide a detailed account of all the steps necessary in setting up state-of-the-art audio feature detection, pre-, and postprocessing, such that the (non-audio expert) machine learning researcher can implement such systems. Finally, we evaluate the performance of our robust replay speaker detection system with a wide variety and different combinations of both extracted and machine learned audio features on the `out in the wild’ ASVspoof 2017 dataset. This dataset contains a variety of new spoofing configurations. Since our focus is on examining which features will ensure robustness, we base our system on a traditional Gaussian Mixture Model-Universal Background Model. We then systematically investigate the relative contribution of each feature set. The fused models, based on both the known audio features and the machine learned features respectively, have a comparable performance with an Equal Error Rate (EER) of 12. The final best performing model, which obtains an EER of 10.8, is a hybrid model that contains both known and machine learned features, thus revealing the importance of incorporating both types of features when developing a robust spoofing prediction model. \|
Tasks	Speaker Verification
Published	2019-05-28
URL	https://arxiv.org/abs/1905.12439v2
PDF	https://arxiv.org/pdf/1905.12439v2.pdf
PWC	https://paperswithcode.com/paper/towards-robust-audio-spoofing-detection-a
Repo
Framework

Clustering Degree-Corrected Stochastic Block Model with Outliers


Title	Clustering Degree-Corrected Stochastic Block Model with Outliers
Authors	Xin Qian, Yudong Chen, Andreea Minca
Abstract	For the degree corrected stochastic block model in the presence of arbitrary or even adversarial outliers, we develop a convex-optimization-based clustering algorithm that includes a penalization term depending on the positive deviation of a node from the expected number of edges to other inliers. We prove that under mild conditions, this method achieves exact recovery of the underlying clusters. Our synthetic experiments show that our algorithm performs well on heterogeneous networks, and in particular those with Pareto degree distributions, for which outliers have a broad range of possible degrees that may enhance their adversarial power. We also demonstrate that our method allows for recovery with significantly lower error rates compared to existing algorithms.
Tasks
Published	2019-06-07
URL	https://arxiv.org/abs/1906.03305v1
PDF	https://arxiv.org/pdf/1906.03305v1.pdf
PWC	https://paperswithcode.com/paper/clustering-degree-corrected-stochastic-block
Repo
Framework

Background Subtraction in Real Applications: Challenges, Current Models and Future Directions


Title	Background Subtraction in Real Applications: Challenges, Current Models and Future Directions
Authors	T. Bouwmans, B. Garcia-Garcia
Abstract	Computer vision applications based on videos often require the detection of moving objects in their first step. Background subtraction is then applied in order to separate the background and the foreground. In literature, background subtraction is surely among the most investigated field in computer vision providing a big amount of publications. Most of them concern the application of mathematical and machine learning models to be more robust to the challenges met in videos. However, the ultimate goal is that the background subtraction methods developed in research could be employed in real applications like traffic surveillance. But looking at the literature, we can remark that there is often a gap between the current methods used in real applications and the current methods in fundamental research. In addition, the videos evaluated in large-scale datasets are not exhaustive in the way that they only covered a part of the complete spectrum of the challenges met in real applications. In this context, we attempt to provide the most exhaustive survey as possible on real applications that used background subtraction in order to identify the real challenges met in practice, the current used background models and to provide future directions. Thus, challenges are investigated in terms of camera, foreground objects and environments. In addition, we identify the background models that are effectively used in these applications in order to find potential usable recent background models in terms of robustness, time and memory requirements.
Tasks
Published	2019-01-11
URL	http://arxiv.org/abs/1901.03577v1
PDF	http://arxiv.org/pdf/1901.03577v1.pdf
PWC	https://paperswithcode.com/paper/background-subtraction-in-real-applications
Repo
Framework

Multi-Agent Pathfinding: Definitions, Variants, and Benchmarks


Title	Multi-Agent Pathfinding: Definitions, Variants, and Benchmarks
Authors	Roni Stern, Nathan Sturtevant, Ariel Felner, Sven Koenig, Hang Ma, Thayne Walker, Jiaoyang Li, Dor Atzmon, Liron Cohen, T. K. Satish Kumar, Eli Boyarski, Roman Bartak
Abstract	The MAPF problem is the fundamental problem of planning paths for multiple agents, where the key constraint is that the agents will be able to follow these paths concurrently without colliding with each other. Applications of MAPF include automated warehouses and autonomous vehicles. Research on MAPF has been flourishing in the past couple of years. Different MAPF research papers make different assumptions, e.g., whether agents can traverse the same road at the same time, and have different objective functions, e.g., minimize makespan or sum of agents’ actions costs. These assumptions and objectives are sometimes implicitly assumed or described informally. This makes it difficult to establish appropriate baselines for comparison in research papers, as well as making it difficult for practitioners to find the papers relevant to their concrete application. This paper aims to fill this gap and support researchers and practitioners by providing a unifying terminology for describing common MAPF assumptions and objectives. In addition, we also provide pointers to two MAPF benchmarks. In particular, we introduce a new grid-based benchmark for MAPF, and demonstrate experimentally that it poses a challenge to contemporary MAPF algorithms.
Tasks	Autonomous Vehicles
Published	2019-06-19
URL	https://arxiv.org/abs/1906.08291v1
PDF	https://arxiv.org/pdf/1906.08291v1.pdf
PWC	https://paperswithcode.com/paper/multi-agent-pathfinding-definitions-variants
Repo
Framework

Reinforcement Learning and Adaptive Sampling for Optimized DNN Compilation


Title	Reinforcement Learning and Adaptive Sampling for Optimized DNN Compilation
Authors	Byung Hoon Ahn, Prannoy Pilligundla, Hadi Esmaeilzadeh
Abstract	Achieving faster execution with shorter compilation time can enable further diversity and innovation in neural networks. However, the current paradigm of executing neural networks either relies on hand-optimized libraries, traditional compilation heuristics, or very recently, simulated annealing and genetic algorithms. Our work takes a unique approach by formulating compiler optimizations for neural networks as a reinforcement learning problem, whose solution takes fewer steps to converge. This solution, dubbed ReLeASE, comes with a sampling algorithm that leverages clustering to focus the costly samples (real hardware measurements) on representative points, subsuming an entire subspace. Our adaptive sampling not only reduces the number of samples, but also improves the quality of samples for better exploration in shorter time. As such, experimentation with real hardware shows that reinforcement learning with adaptive sampling provides 4.45x speed up in optimization time over AutoTVM, while also improving inference time of the modern deep networks by 5.6%. Further experiments also confirm that our adaptive sampling can even improve AutoTVM’s simulated annealing by 4.00x.
Tasks
Published	2019-05-30
URL	https://arxiv.org/abs/1905.12799v1
PDF	https://arxiv.org/pdf/1905.12799v1.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-and-adaptive-sampling
Repo
Framework

Model Embedded DRL for Intelligent Greenhouse Control


Title	Model Embedded DRL for Intelligent Greenhouse Control
Authors	Tinghao Zhang, Jingxu Li, Jingfeng Li, Ling Wang, Feng Li, Jie Liu
Abstract	Greenhouse environment is the key to influence crops production. However, it is difficult for classical control methods to give precise environment setpoints, such as temperature, humidity, light intensity and carbon dioxide concentration for greenhouse because it is uncertain nonlinear system. Therefore, an intelligent close loop control framework based on model embedded deep reinforcement learning (MEDRL) is designed for greenhouse environment control. Specifically, computer vision algorithms are used to recognize growing periods and sex of crops, followed by the crop growth models, which can be trained with different growing periods and sex. These model outputs combined with the cost factor provide the setpoints for greenhouse and feedback to the control system in real-time. The whole MEDRL system has capability to conduct optimization control precisely and conveniently, and costs will be greatly reduced compared with traditional greenhouse control approaches.
Tasks
Published	2019-12-01
URL	https://arxiv.org/abs/1912.00020v1
PDF	https://arxiv.org/pdf/1912.00020v1.pdf
PWC	https://paperswithcode.com/paper/model-embedded-drl-for-intelligent-greenhouse
Repo
Framework

Towards Explainable Artificial Intelligence


Title	Towards Explainable Artificial Intelligence
Authors	Wojciech Samek, Klaus-Robert Müller
Abstract	In recent years, machine learning (ML) has become a key enabling technology for the sciences and industry. Especially through improvements in methodology, the availability of large databases and increased computational power, today’s ML algorithms are able to achieve excellent performance (at times even exceeding the human level) on an increasing number of complex tasks. Deep learning models are at the forefront of this development. However, due to their nested non-linear structure, these powerful models have been generally considered “black boxes”, not providing any information about what exactly makes them arrive at their predictions. Since in many applications, e.g., in the medical domain, such lack of transparency may be not acceptable, the development of methods for visualizing, explaining and interpreting deep learning models has recently attracted increasing attention. This introductory paper presents recent developments and applications in this field and makes a plea for a wider use of explainable learning algorithms in practice.
Tasks
Published	2019-09-26
URL	https://arxiv.org/abs/1909.12072v1
PDF	https://arxiv.org/pdf/1909.12072v1.pdf
PWC	https://paperswithcode.com/paper/towards-explainable-artificial-intelligence
Repo
Framework

Statistical Inferences of Linear Forms for Noisy Matrix Completion


Title	Statistical Inferences of Linear Forms for Noisy Matrix Completion
Authors	Dong Xia, Ming Yuan
Abstract	We introduce a flexible framework for making inferences about general linear forms of a large matrix based on noisy observations of a subset of its entries. In particular, under mild regularity conditions, we develop a universal procedure to construct asymptotically normal estimators of its linear forms through double-sample debiasing and low-rank projection whenever an entry-wise consistent estimator of the matrix is available. These estimators allow us to subsequently construct confidence intervals for and test hypotheses about the linear forms. Our proposal was motivated by a careful perturbation analysis of the empirical singular spaces under the noisy matrix completion model which might be of independent interest.
Tasks	Matrix Completion
Published	2019-08-31
URL	https://arxiv.org/abs/1909.00116v1
PDF	https://arxiv.org/pdf/1909.00116v1.pdf
PWC	https://paperswithcode.com/paper/statistical-inferences-of-linear-forms-for
Repo
Framework

RFBNet: Deep Multimodal Networks with Residual Fusion Blocks for RGB-D Semantic Segmentation


Title	RFBNet: Deep Multimodal Networks with Residual Fusion Blocks for RGB-D Semantic Segmentation
Authors	Liuyuan Deng, Ming Yang, Tianyi Li, Yuesheng He, Chunxiang Wang
Abstract	RGB-D semantic segmentation methods conventionally use two independent encoders to extract features from the RGB and depth data. However, there lacks an effective fusion mechanism to bridge the encoders, for the purpose of fully exploiting the complementary information from multiple modalities. This paper proposes a novel bottom-up interactive fusion structure to model the interdependencies between the encoders. The structure introduces an interaction stream to interconnect the encoders. The interaction stream not only progressively aggregates modality-specific features from the encoders but also computes complementary features for them. To instantiate this structure, the paper proposes a residual fusion block (RFB) to formulate the interdependences of the encoders. The RFB consists of two residual units and one fusion unit with gate mechanism. It learns complementary features for the modality-specific encoders and extracts modality-specific features as well as cross-modal features. Based on the RFB, the paper presents the deep multimodal networks for RGB-D semantic segmentation called RFBNet. The experiments on two datasets demonstrate the effectiveness of modeling the interdependencies and that the RFBNet achieved state-of-the-art performance.
Tasks	Semantic Segmentation
Published	2019-06-29
URL	https://arxiv.org/abs/1907.00135v2
PDF	https://arxiv.org/pdf/1907.00135v2.pdf
PWC	https://paperswithcode.com/paper/rfbnet-deep-multimodal-networks-with-residual
Repo
Framework

M-GWAP: An Online and Multimodal Game With A Purpose in WordPress for Mental States Annotation


Title	M-GWAP: An Online and Multimodal Game With A Purpose in WordPress for Mental States Annotation
Authors	Fabio Paolizzo
Abstract	M-GWAP is a multimodal game with a purpose of that leverages on the wisdom of crowds phenomenon for the annotation of multimedia data in terms of mental states. This game with a purpose is developed in WordPress to allow users implementing the game without programming skills. The game adopts motivational strategies for the player to remain engaged, such as a score system, text motivators while playing, a ranking system to foster competition and mechanics for identify building. The current version of the game was deployed after alpha and beta testing helped refining the game accordingly.
Tasks
Published	2019-05-30
URL	https://arxiv.org/abs/1905.12884v1
PDF	https://arxiv.org/pdf/1905.12884v1.pdf
PWC	https://paperswithcode.com/paper/m-gwap-an-online-and-multimodal-game-with-a
Repo
Framework

Hopfield Neural Network Flow: A Geometric Viewpoint


Title	Hopfield Neural Network Flow: A Geometric Viewpoint
Authors	Abhishek Halder, Kenneth F. Caluya, Bertrand Travacca, Scott J. Moura
Abstract	We provide gradient flow interpretations for the continuous-time continuous-state Hopfield neural network (HNN). The ordinary and stochastic differential equations associated with the HNN were introduced in the literature as analog optimizers, and were reported to exhibit good performance in numerical experiments. In this work, we point out that the deterministic HNN can be transcribed into Amari’s natural gradient descent, and thereby uncover the explicit relation between the underlying Riemannian metric and the activation functions. By exploiting an equivalence between the natural gradient descent and the mirror descent, we show how the choice of activation function governs the geometry of the HNN dynamics. For the stochastic HNN, we show that the so-called “diffusion machine”, while not a gradient flow itself, induces a gradient flow when lifted in the space of probability measures. We characterize this infinite dimensional flow as the gradient descent of certain free energy with respect to a Wasserstein metric that depends on the geodesic distance on the ground manifold. Furthermore, we demonstrate how this gradient flow interpretation can be used for fast computation via recently developed proximal algorithms.
Tasks
Published	2019-08-04
URL	https://arxiv.org/abs/1908.01270v2
PDF	https://arxiv.org/pdf/1908.01270v2.pdf
PWC	https://paperswithcode.com/paper/hopfield-neural-network-flow-a-geometric
Repo
Framework

Accurate Protein Structure Prediction by Embeddings and Deep Learning Representations


Title	Accurate Protein Structure Prediction by Embeddings and Deep Learning Representations
Authors	Iddo Drori, Darshan Thaker, Arjun Srivatsa, Daniel Jeong, Yueqi Wang, Linyong Nan, Fan Wu, Dimitri Leggas, Jinhao Lei, Weiyi Lu, Weilong Fu, Yuan Gao, Sashank Karri, Anand Kannan, Antonio Moretti, Mohammed AlQuraishi, Chen Keasar, Itsik Pe’er
Abstract	Proteins are the major building blocks of life, and actuators of almost all chemical and biophysical events in living organisms. Their native structures in turn enable their biological functions which have a fundamental role in drug design. This motivates predicting the structure of a protein from its sequence of amino acids, a fundamental problem in computational biology. In this work, we demonstrate state-of-the-art protein structure prediction (PSP) results using embeddings and deep learning models for prediction of backbone atom distance matrices and torsion angles. We recover 3D coordinates of backbone atoms and reconstruct full atom protein by optimization. We create a new gold standard dataset of proteins which is comprehensive and easy to use. Our dataset consists of amino acid sequences, Q8 secondary structures, position specific scoring matrices, multiple sequence alignment co-evolutionary features, backbone atom distance matrices, torsion angles, and 3D coordinates. We evaluate the quality of our structure prediction by RMSD on the latest Critical Assessment of Techniques for Protein Structure Prediction (CASP) test data and demonstrate competitive results with the winning teams and AlphaFold in CASP13 and supersede the results of the winning teams in CASP12. We make our data, models, and code publicly available.
Tasks
Published	2019-11-09
URL	https://arxiv.org/abs/1911.05531v1
PDF	https://arxiv.org/pdf/1911.05531v1.pdf
PWC	https://paperswithcode.com/paper/accurate-protein-structure-prediction-by
Repo
Framework

Entropic Regularisation of Robust Optimal Transport


Title	Entropic Regularisation of Robust Optimal Transport
Authors	Rozenn Dahyot, Hana Alghamdi, Mairead Grogan
Abstract	Grogan et al [11,12] have recently proposed a solution to colour transfer by minimising the Euclidean distance L2 between two probability density functions capturing the colour distributions of two images (palette and target). It was shown to be very competitive to alternative solutions based on Optimal Transport for colour transfer. We show that in fact Grogan et al’s formulation can also be understood as a new robust Optimal Transport based framework with entropy regularisation over marginals.
Tasks
Published	2019-05-29
URL	https://arxiv.org/abs/1905.12678v1
PDF	https://arxiv.org/pdf/1905.12678v1.pdf
PWC	https://paperswithcode.com/paper/entropic-regularisation-of-robust-optimal
Repo
Framework