January 28, 2020

3007 words 15 mins read

Paper Group ANR 934

Robust Recovery Controller for a Quadrupedal Robot using Deep Reinforcement Learning. Results from the Robocademy ITN: Autonomy, Disturbance Rejection and Perception for Advanced Marine Robotics. RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials. Tustin neural networks: a class of recurrent nets for adaptive MPC of mechanical system …

Robust Recovery Controller for a Quadrupedal Robot using Deep Reinforcement Learning


Title	Robust Recovery Controller for a Quadrupedal Robot using Deep Reinforcement Learning
Authors	Joonho Lee, Jemin Hwangbo, Marco Hutter
Abstract	The ability to recover from a fall is an essential feature for a legged robot to navigate in challenging environments robustly. Until today, there has been very little progress on this topic. Current solutions mostly build upon (heuristically) predefined trajectories, resulting in unnatural behaviors and requiring considerable effort in engineering system-specific components. In this paper, we present an approach based on model-free Deep Reinforcement Learning (RL) to control recovery maneuvers of quadrupedal robots using a hierarchical behavior-based controller. The controller consists of four neural network policies including three behaviors and one behavior selector to coordinate them. Each of them is trained individually in simulation and deployed directly on a real system. We experimentally validate our approach on the quadrupedal robot ANYmal, which is a dog-sized quadrupedal system with 12 degrees of freedom. With our method, ANYmal manifests dynamic and reactive recovery behaviors to recover from an arbitrary fall configuration within less than 5 seconds. We tested the recovery maneuver more than 100 times, and the success rate was higher than 97 %.
Tasks
Published	2019-01-22
URL	http://arxiv.org/abs/1901.07517v1
PDF	http://arxiv.org/pdf/1901.07517v1.pdf
PWC	https://paperswithcode.com/paper/robust-recovery-controller-for-a-quadrupedal
Repo
Framework

Results from the Robocademy ITN: Autonomy, Disturbance Rejection and Perception for Advanced Marine Robotics


Title	Results from the Robocademy ITN: Autonomy, Disturbance Rejection and Perception for Advanced Marine Robotics
Authors	Matias Valdenegro-Toro, Mariela De Lucas Alvarez, Mariia Dmitrieva, Bilal Wehbe, Georgios Salavasidis, Shahab Heshmati-Alamdari, Juan F. Fuentes-Pérez, Veronika Yordanova, Klemen Istenič, Thomas Guerneve
Abstract	Marine and Underwater resources are important part of the economy of many countries. This requires significant financial resources into their construction and maintentance. Robotics is expected to fill this void, by automating and/or removing humans from hostile environments in order to easily perform maintenance tasks. The Robocademy Marie Sklodowska-Curie Initial Training Network was funded by the European Union’s FP7 research program in order to train 13 Fellows into world-leading researchers in Marine and Underwater Robotics. The fellows developed guided research into three areas of key importance: Autonomy, Disturbance Rejection, and Perception. This paper presents a summary of the fellows’ research in the three action lines. 71 scientific publications were the primary result of this project, with many other publications currently in the pipeline. Most of the fellows have found employment in Europe, which shows the high demand for this kind of experts. We believe the results from this project are already having an impact in the marine robotics industry, as key technologies are being adopted already.
Tasks
Published	2019-10-29
URL	https://arxiv.org/abs/1910.13144v1
PDF	https://arxiv.org/pdf/1910.13144v1.pdf
PWC	https://paperswithcode.com/paper/results-from-the-robocademy-itn-autonomy
Repo
Framework

RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials


Title	RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials
Authors	Despoina Paschalidou, Ali Osman Ulusoy, Carolin Schmitt, Luc van Gool, Andreas Geiger
Abstract	In this paper, we consider the problem of reconstructing a dense 3D model using images captured from different views. Recent methods based on convolutional neural networks (CNN) allow learning the entire task from data. However, they do not incorporate the physics of image formation such as perspective geometry and occlusion. Instead, classical approaches based on Markov Random Fields (MRF) with ray-potentials explicitly model these physical processes, but they cannot cope with large surface appearance variations across different viewpoints. In this paper, we propose RayNet, which combines the strengths of both frameworks. RayNet integrates a CNN that learns view-invariant feature representations with an MRF that explicitly encodes the physics of perspective projection and occlusion. We train RayNet end-to-end using empirical risk minimization. We thoroughly evaluate our approach on challenging real-world datasets and demonstrate its benefits over a piece-wise trained baseline, hand-crafted models as well as other learning-based approaches.
Tasks	3D Reconstruction
Published	2019-01-06
URL	http://arxiv.org/abs/1901.01535v1
PDF	http://arxiv.org/pdf/1901.01535v1.pdf
PWC	https://paperswithcode.com/paper/raynet-learning-volumetric-3d-reconstruction
Repo
Framework

Tustin neural networks: a class of recurrent nets for adaptive MPC of mechanical systems


Title	Tustin neural networks: a class of recurrent nets for adaptive MPC of mechanical systems
Authors	Simone Pozzoli, Marco Gallieri, Riccardo Scattolini
Abstract	The use of recurrent neural networks to represent the dynamics of unstable systems is difficult due to the need to properly initialize their internal states, which in most of the cases do not have any physical meaning, consequent to the non-smoothness of the optimization problem. For this reason, in this paper focus is placed on mechanical systems characterized by a number of degrees of freedom, each one represented by two states, namely position and velocity. For these systems, a new recurrent neural network is proposed: Tustin-Net. Inspired by second-order dynamics, the network hidden states can be straightforwardly estimated, as their differential relationships with the measured states are hardcoded in the forward pass. The proposed structure is used to model a double inverted pendulum and for model-based Reinforcement Learning, where an adaptive Model Predictive Controller scheme using the Unscented Kalman Filter is proposed to deal with parameter changes in the system.
Tasks
Published	2019-11-04
URL	https://arxiv.org/abs/1911.01310v1
PDF	https://arxiv.org/pdf/1911.01310v1.pdf
PWC	https://paperswithcode.com/paper/tustin-neural-networks-a-class-of-recurrent
Repo
Framework

Mining Domain Knowledge: Improved Framework towards Automatically Standardizing Anatomical Structure Nomenclature in Radiotherapy


Title	Mining Domain Knowledge: Improved Framework towards Automatically Standardizing Anatomical Structure Nomenclature in Radiotherapy
Authors	Qiming Yang, Hongyang Chao, Dan Nguyen, Steve Jiang
Abstract	Automatically standardizing nomenclature for anatomical structures in radiotherapy (RT) clinical data is an unmet urgent need in the era of big data and artificial intelligence. Existing methods either can hardly handle cross-institutional datasets or suffer from heavy imbalance and poor-quality delineation in clinical RT datasets. To solve these problems, we propose an automated structure nomenclature standardization framework, 3DNNV, which consists of an improved data processing strategy (ASAC/Voting) and an optimized feature extraction module to simulate clinicians’ domain knowledge and recognition mechanisms to identify heavily imbalanced small-volume organs at risk (OARs) better than other methods. We used partial data from an open-source head-and-neck cancer dataset (HN_PETCT) to train the model, then tested the model on three cross-institutional datasets to demonstrate its generalizability. 3DNNV outperformed the baseline model (ResNet50), achieving a significantly higher average true positive rate (TPR) on the three test datasets (+8.27%, +2.39%, +5.53%). More importantly, the 3DNNV outperformed the baseline, 28.63% to 91.17%, on the F1 score of a small-volume OAR with only 9 training samples, when tested on the HN_UTSW dataset. The developed framework can be used to help standardizing structure nomenclature to facilitate data-driven clinical research in cancer radiotherapy.
Tasks
Published	2019-12-04
URL	https://arxiv.org/abs/1912.02084v1
PDF	https://arxiv.org/pdf/1912.02084v1.pdf
PWC	https://paperswithcode.com/paper/mining-domain-knowledge-improved-framework
Repo
Framework

Tree-Transformer: A Transformer-Based Method for Correction of Tree-Structured Data


Title	Tree-Transformer: A Transformer-Based Method for Correction of Tree-Structured Data
Authors	Jacob Harer, Chris Reale, Peter Chin
Abstract	Many common sequential data sources, such as source code and natural language, have a natural tree-structured representation. These trees can be generated by fitting a sequence to a grammar, yielding a hierarchical ordering of the tokens in the sequence. This structure encodes a high degree of syntactic information, making it ideal for problems such as grammar correction. However, little work has been done to develop neural networks that can operate on and exploit tree-structured data. In this paper we present the Tree-Transformer \textemdash{} a novel neural network architecture designed to translate between arbitrary input and output trees. We applied this architecture to correction tasks in both the source code and natural language domains. On source code, our model achieved an improvement of $25%$ $\text{F}0.5$ over the best sequential method. On natural language, we achieved comparable results to the most complex state of the art systems, obtaining a $10%$ improvement in recall on the CoNLL 2014 benchmark and the highest to date $\text{F}0.5$ score on the AESW benchmark of $50.43$.
Tasks
Published	2019-08-01
URL	https://arxiv.org/abs/1908.00449v1
PDF	https://arxiv.org/pdf/1908.00449v1.pdf
PWC	https://paperswithcode.com/paper/tree-transformer-a-transformer-based-method
Repo
Framework

Dynamic Stale Synchronous Parallel Distributed Training for Deep Learning


Title	Dynamic Stale Synchronous Parallel Distributed Training for Deep Learning
Authors	Xing Zhao, Aijun An, Junfeng Liu, Bao Xin Chen
Abstract	Deep learning is a popular machine learning technique and has been applied to many real-world problems. However, training a deep neural network is very time-consuming, especially on big data. It has become difficult for a single machine to train a large model over large datasets. A popular solution is to distribute and parallelize the training process across multiple machines using the parameter server framework. In this paper, we present a distributed paradigm on the parameter server framework called Dynamic Stale Synchronous Parallel (DSSP) which improves the state-of-the-art Stale Synchronous Parallel (SSP) paradigm by dynamically determining the staleness threshold at the run time. Conventionally to run distributed training in SSP, the user needs to specify a particular staleness threshold as a hyper-parameter. However, a user does not usually know how to set the threshold and thus often finds a threshold value through trial and error, which is time-consuming. Based on workers’ recent processing time, our approach DSSP adaptively adjusts the threshold per iteration at running time to reduce the waiting time of faster workers for synchronization of the globally shared parameters, and consequently increases the frequency of parameters updates (increases iteration throughput), which speedups the convergence rate. We compare DSSP with other paradigms such as Bulk Synchronous Parallel (BSP), Asynchronous Parallel (ASP), and SSP by running deep neural networks (DNN) models over GPU clusters in both homogeneous and heterogeneous environments. The results show that in a heterogeneous environment where the cluster consists of mixed models of GPUs, DSSP converges to a higher accuracy much earlier than SSP and BSP and performs similarly to ASP. In a homogeneous distributed cluster, DSSP has more stable and slightly better performance than SSP and ASP, and converges much faster than BSP.
Tasks
Published	2019-08-16
URL	https://arxiv.org/abs/1908.11848v1
PDF	https://arxiv.org/pdf/1908.11848v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-stale-synchronous-parallel
Repo
Framework

Gradient tree boosting with random output projections for multi-label classification and multi-output regression


Title	Gradient tree boosting with random output projections for multi-label classification and multi-output regression
Authors	Arnaud Joly, Louis Wehenkel, Pierre Geurts
Abstract	In many applications of supervised learning, multiple classification or regression outputs have to be predicted jointly. We consider several extensions of gradient boosting to address such problems. We first propose a straightforward adaptation of gradient boosting exploiting multiple output regression trees as base learners. We then argue that this method is only expected to be optimal when the outputs are fully correlated, as it forces the partitioning induced by the tree base learners to be shared by all outputs. We then propose a novel extension of gradient tree boosting to specifically address this issue. At each iteration of this new method, a regression tree structure is grown to fit a single random projection of the current residuals and the predictions of this tree are fitted linearly to the current residuals of all the outputs, independently. Because of this linear fit, the method can adapt automatically to any output correlation structure. Extensive experiments are conducted with this method, as well as other algorithmic variants, on several artificial and real problems. Randomly projecting the output space is shown to provide a better adaptation to different output correlation patterns and is therefore competitive with the best of the other methods in most settings. Thanks to model sharing, the convergence speed is also improved, reducing the computing times (or the complexity of the model) to reach a specific accuracy.
Tasks	Multi-Label Classification
Published	2019-05-18
URL	https://arxiv.org/abs/1905.07558v1
PDF	https://arxiv.org/pdf/1905.07558v1.pdf
PWC	https://paperswithcode.com/paper/gradient-tree-boosting-with-random-output
Repo
Framework

V-PROM: A Benchmark for Visual Reasoning Using Visual Progressive Matrices


Title	V-PROM: A Benchmark for Visual Reasoning Using Visual Progressive Matrices
Authors	Damien Teney, Peng Wang, Jiewei Cao, Lingqiao Liu, Chunhua Shen, Anton van den Hengel
Abstract	One of the primary challenges faced by deep learning is the degree to which current methods exploit superficial statistics and dataset bias, rather than learning to generalise over the specific representations they have experienced. This is a critical concern because generalisation enables robust reasoning over unseen data, whereas leveraging superficial statistics is fragile to even small changes in data distribution. To illuminate the issue and drive progress towards a solution, we propose a test that explicitly evaluates abstract reasoning over visual data. We introduce a large-scale benchmark of visual questions that involve operations fundamental to many high-level vision tasks, such as comparisons of counts and logical operations on complex visual properties. The benchmark directly measures a method’s ability to infer high-level relationships and to generalise them over image-based concepts. It includes multiple training/test splits that require controlled levels of generalization. We evaluate a range of deep learning architectures, and find that existing models, including those popular for vision-and-language tasks, are unable to solve seemingly-simple instances. Models using relational networks fare better but leave substantial room for improvement.
Tasks	Visual Reasoning
Published	2019-07-29
URL	https://arxiv.org/abs/1907.12271v1
PDF	https://arxiv.org/pdf/1907.12271v1.pdf
PWC	https://paperswithcode.com/paper/v-prom-a-benchmark-for-visual-reasoning-using
Repo
Framework

Two Stream Networks for Self-Supervised Ego-Motion Estimation


Title	Two Stream Networks for Self-Supervised Ego-Motion Estimation
Authors	Rares Ambrus, Vitor Guizilini, Jie Li, Sudeep Pillai, Adrien Gaidon
Abstract	Learning depth and camera ego-motion from raw unlabeled RGB video streams is seeing exciting progress through self-supervision from strong geometric cues. To leverage not only appearance but also scene geometry, we propose a novel self-supervised two-stream network using RGB and inferred depth information for accurate visual odometry. In addition, we introduce a sparsity-inducing data augmentation policy for ego-motion learning that effectively regularizes the pose network to enable stronger generalization performance. As a result, we show that our proposed two-stream pose network achieves state-of-the-art results among learning-based methods on the KITTI odometry benchmark, and is especially suited for self-supervision at scale. Our experiments on a large-scale urban driving dataset of 1 million frames indicate that the performance of our proposed architecture does indeed scale progressively with more data.
Tasks	Data Augmentation, Motion Estimation, Visual Odometry
Published	2019-10-04
URL	https://arxiv.org/abs/1910.01764v3
PDF	https://arxiv.org/pdf/1910.01764v3.pdf
PWC	https://paperswithcode.com/paper/two-stream-networks-for-self-supervised-ego
Repo
Framework

Efficient Deep Learning of GMMs


Title	Efficient Deep Learning of GMMs
Authors	Shirin Jalali, Carl Nuzman, Iraj Saniee
Abstract	We show that a collection of Gaussian mixture models (GMMs) in $R^{n}$ can be optimally classified using $O(n)$ neurons in a neural network with two hidden layers (deep neural network), whereas in contrast, a neural network with a single hidden layer (shallow neural network) would require at least $O(\exp(n))$ neurons or possibly exponentially large coefficients. Given the universality of the Gaussian distribution in the feature spaces of data, e.g., in speech, image and text, our result sheds light on the observed efficiency of deep neural networks in practical classification problems.
Tasks
Published	2019-02-15
URL	http://arxiv.org/abs/1902.05707v1
PDF	http://arxiv.org/pdf/1902.05707v1.pdf
PWC	https://paperswithcode.com/paper/efficient-deep-learning-of-gmms
Repo
Framework

Gradient Boosting Machine: A Survey


Title	Gradient Boosting Machine: A Survey
Authors	Zhiyuan He, Danchen Lin, Thomas Lau, Mike Wu
Abstract	In this survey, we discuss several different types of gradient boosting algorithms and illustrate their mathematical frameworks in detail: 1. introduction of gradient boosting leads to 2. objective function optimization, 3. loss function estimations, and 4. model constructions. 5. application of boosting in ranking.
Tasks
Published	2019-08-19
URL	https://arxiv.org/abs/1908.06951v1
PDF	https://arxiv.org/pdf/1908.06951v1.pdf
PWC	https://paperswithcode.com/paper/gradient-boosting-machine-a-survey
Repo
Framework

Learned imaging with constraints and uncertainty quantification


Title	Learned imaging with constraints and uncertainty quantification
Authors	Felix J. Herrmann, Ali Siahkoohi, Gabrio Rizzuti
Abstract	We outline new approaches to incorporate ideas from deep learning into wave-based least-squares imaging. The aim, and main contribution of this work, is the combination of handcrafted constraints with deep convolutional neural networks, as a way to harness their remarkable ease of generating natural images. The mathematical basis underlying our method is the expectation-maximization framework, where data are divided in batches and coupled to additional “latent” unknowns. These unknowns are pairs of elements from the original unknown space (but now coupled to a specific data batch) and network inputs. In this setting, the neural network controls the similarity between these additional parameters, acting as a “center” variable. The resulting problem amounts to a maximum-likelihood estimation of the network parameters when the augmented data model is marginalized over the latent variables.
Tasks
Published	2019-09-13
URL	https://arxiv.org/abs/1909.06473v2
PDF	https://arxiv.org/pdf/1909.06473v2.pdf
PWC	https://paperswithcode.com/paper/learned-imaging-with-constraints-and
Repo
Framework

Feedback graph regret bounds for Thompson Sampling and UCB


Title	Feedback graph regret bounds for Thompson Sampling and UCB
Authors	Thodoris Lykouris, Eva Tardos, Drishti Wali
Abstract	We study the stochastic multi-armed bandit problem with the graph-based feedback structure introduced by Mannor and Shamir. We analyze the performance of the two most prominent stochastic bandit algorithms, Thompson Sampling and Upper Confidence Bound (UCB), in the graph-based feedback setting. We show that these algorithms achieve regret guarantees that combine the graph structure and the gaps between the means of the arm distributions. Surprisingly this holds despite the fact that these algorithms do not explicitly use the graph structure to select arms; they observe the additional feedback but do not explore based on it. Towards this result we introduce a “layering technique” highlighting the commonalities in the two algorithms.
Tasks
Published	2019-05-23
URL	https://arxiv.org/abs/1905.09898v3
PDF	https://arxiv.org/pdf/1905.09898v3.pdf
PWC	https://paperswithcode.com/paper/graph-regret-bounds-for-thompson-sampling-and
Repo
Framework

Noise-Stable Rigid Graphs for Euclidean Embedding


Title	Noise-Stable Rigid Graphs for Euclidean Embedding
Authors	Zishuo Zhao
Abstract	We proposed a new criterion \textit{noise-stability}, which revised the classical rigidity theory, for evaluation of MDS algorithms which can truthfully represent the fidelity of global structure reconstruction; then we proved the noise-stability of the cMDS algorithm in generic conditions, which provides a rigorous theoretical guarantee for the precision and theoretical bounds for Euclidean embedding and its application in fields including wireless sensor network localization and satellite positioning. Furthermore, we looked into previous work about minimum-cost globally rigid spanning subgraph, and proposed an algorithm to construct a minimum-cost noise-stable spanning graph in the Euclidean space, which enabled reliable localization on sparse graphs of noisy distance constraints with linear numbers of edges and sublinear costs in total edge lengths. Additionally, this algorithm also suggests a scheme to reconstruct point clouds from pairwise distances at a minimum of $O(n)$ time complexity, down from $O(n^3)$ for cMDS.
Tasks
Published	2019-07-15
URL	https://arxiv.org/abs/1907.06441v4
PDF	https://arxiv.org/pdf/1907.06441v4.pdf
PWC	https://paperswithcode.com/paper/noise-stable-rigid-graphs-for-euclidean
Repo
Framework