October 19, 2019

2855 words 14 mins read

Paper Group ANR 279

Gait learning for soft microrobots controlled by light fields. Can rationality be measured?. Entropy Maximization for Markov Decision Processes Under Temporal Logic Constraints. Improved Visual Relocalization by Discovering Anchor Points. Bytes are All You Need: End-to-End Multilingual Speech Recognition and Synthesis with Bytes. Effect of data red …

Gait learning for soft microrobots controlled by light fields


Title	Gait learning for soft microrobots controlled by light fields
Authors	Alexander von Rohr, Sebastian Trimpe, Alonso Marco, Peer Fischer, Stefano Palagi
Abstract	Soft microrobots based on photoresponsive materials and controlled by light fields can generate a variety of different gaits. This inherent flexibility can be exploited to maximize their locomotion performance in a given environment and used to adapt them to changing conditions. Albeit, because of the lack of accurate locomotion models, and given the intrinsic variability among microrobots, analytical control design is not possible. Common data-driven approaches, on the other hand, require running prohibitive numbers of experiments and lead to very sample-specific results. Here we propose a probabilistic learning approach for light-controlled soft microrobots based on Bayesian Optimization (BO) and Gaussian Processes (GPs). The proposed approach results in a learning scheme that is data-efficient, enabling gait optimization with a limited experimental budget, and robust against differences among microrobot samples. These features are obtained by designing the learning scheme through the comparison of different GP priors and BO settings on a semi-synthetic data set. The developed learning scheme is validated in microrobot experiments, resulting in a 115% improvement in a microrobot’s locomotion performance with an experimental budget of only 20 tests. These encouraging results lead the way toward self-adaptive microrobotic systems based on light-controlled soft microrobots and probabilistic learning control.
Tasks	Gaussian Processes
Published	2018-09-10
URL	http://arxiv.org/abs/1809.03225v1
PDF	http://arxiv.org/pdf/1809.03225v1.pdf
PWC	https://paperswithcode.com/paper/gait-learning-for-soft-microrobots-controlled
Repo
Framework

Can rationality be measured?


Title	Can rationality be measured?
Authors	Tshilidzi Marwala
Abstract	This paper studies whether rationality can be computed. Rationality is defined as the use of complete information, which is processed with a perfect biological or physical brain, in an optimized fashion. To compute rationality one needs to quantify how complete is the information, how perfect is the physical or biological brain and how optimized is the entire decision making system. The rationality of a model (i.e. physical or biological brain) is measured by the expected accuracy of the model. The rationality of the optimization procedure is measured as the ratio of the achieved objective (i.e. utility) to the global objective. The overall rationality of a decision is measured as the product of the rationality of the model and the rationality of the optimization procedure. The conclusion reached is that rationality can be computed for convex optimization problems.
Tasks	Decision Making
Published	2018-12-25
URL	http://arxiv.org/abs/1812.10144v1
PDF	http://arxiv.org/pdf/1812.10144v1.pdf
PWC	https://paperswithcode.com/paper/can-rationality-be-measured
Repo
Framework

Entropy Maximization for Markov Decision Processes Under Temporal Logic Constraints


Title	Entropy Maximization for Markov Decision Processes Under Temporal Logic Constraints
Authors	Yagiz Savas, Melkior Ornik, Murat Cubuktepe, Mustafa O. Karabag, Ufuk Topcu
Abstract	We study the problem of synthesizing a policy that maximizes the entropy of a Markov decision process (MDP) subject to a temporal logic constraint. Such a policy minimizes the predictability of the paths it generates, or dually, maximizes the exploration of different paths in an MDP while ensuring the satisfaction of a temporal logic specification. We first show that the maximum entropy of an MDP can be finite, infinite or unbounded. We provide necessary and sufficient conditions under which the maximum entropy of an MDP is finite, infinite or unbounded. We then present an algorithm which is based on a convex optimization problem to synthesize a policy that maximizes the entropy of an MDP. We also show that maximizing the entropy of an MDP is equivalent to maximizing the entropy of the paths that reach a certain set of states in the MDP. Finally, we extend the algorithm to an MDP subject to a temporal logic specification. In numerical examples, we demonstrate the proposed method on different motion planning scenarios and illustrate the relation between the restrictions imposed on the paths by a specification, the maximum entropy, and the predictability of paths.
Tasks	Motion Planning
Published	2018-07-09
URL	https://arxiv.org/abs/1807.03223v3
PDF	https://arxiv.org/pdf/1807.03223v3.pdf
PWC	https://paperswithcode.com/paper/entropy-maximization-for-markov-decision
Repo
Framework

Improved Visual Relocalization by Discovering Anchor Points


Title	Improved Visual Relocalization by Discovering Anchor Points
Authors	Soham Saha, Girish Varma, C. V. Jawahar
Abstract	We address the visual relocalization problem of predicting the location and camera orientation or pose (6DOF) of the given input scene. We propose a method based on how humans determine their location using the visible landmarks. We define anchor points uniformly across the route map and propose a deep learning architecture which predicts the most relevant anchor point present in the scene as well as the relative offsets with respect to it. The relevant anchor point need not be the nearest anchor point to the ground truth location, as it might not be visible due to the pose. Hence we propose a multi task loss function, which discovers the relevant anchor point, without needing the ground truth for it. We validate the effectiveness of our approach by experimenting on CambridgeLandmarks (large scale outdoor scenes) as well as 7 Scenes (indoor scenes) using variousCNN feature extractors. Our method improves the median error in indoor as well as outdoor localization datasets compared to the previous best deep learning model known as PoseNet (with geometric re-projection loss) using the same feature extractor. We improve the median error in localization in the specific case of Street scene, by over 8m.
Tasks
Published	2018-11-11
URL	http://arxiv.org/abs/1811.04370v1
PDF	http://arxiv.org/pdf/1811.04370v1.pdf
PWC	https://paperswithcode.com/paper/improved-visual-relocalization-by-discovering
Repo
Framework

Bytes are All You Need: End-to-End Multilingual Speech Recognition and Synthesis with Bytes


Title	Bytes are All You Need: End-to-End Multilingual Speech Recognition and Synthesis with Bytes
Authors	Bo Li, Yu Zhang, Tara Sainath, Yonghui Wu, William Chan
Abstract	We present two end-to-end models: Audio-to-Byte (A2B) and Byte-to-Audio (B2A), for multilingual speech recognition and synthesis. Prior work has predominantly used characters, sub-words or words as the unit of choice to model text. These units are difficult to scale to languages with large vocabularies, particularly in the case of multilingual processing. In this work, we model text via a sequence of Unicode bytes, specifically, the UTF-8 variable length byte sequence for each character. Bytes allow us to avoid large softmaxes in languages with large vocabularies, and share representations in multilingual models. We show that bytes are superior to grapheme characters over a wide variety of languages in monolingual end-to-end speech recognition. Additionally, our multilingual byte model outperform each respective single language baseline on average by 4.4% relatively. In Japanese-English code-switching speech, our multilingual byte model outperform our monolingual baseline by 38.6% relatively. Finally, we present an end-to-end multilingual speech synthesis model using byte representations which matches the performance of our monolingual baselines.
Tasks	End-To-End Speech Recognition, Speech Recognition, Speech Synthesis
Published	2018-11-22
URL	http://arxiv.org/abs/1811.09021v1
PDF	http://arxiv.org/pdf/1811.09021v1.pdf
PWC	https://paperswithcode.com/paper/bytes-are-all-you-need-end-to-end
Repo
Framework

Effect of data reduction on sequence-to-sequence neural TTS


Title	Effect of data reduction on sequence-to-sequence neural TTS
Authors	Javier Latorre, Jakub Lachowicz, Jaime Lorenzo-Trueba, Thomas Merritt, Thomas Drugman, Srikanth Ronanki, Klimkov Viacheslav
Abstract	Recent speech synthesis systems based on sampling from autoregressive neural networks models can generate speech almost undistinguishable from human recordings. However, these models require large amounts of data. This paper shows that the lack of data from one speaker can be compensated with data from other speakers. The naturalness of Tacotron2-like models trained on a blend of 5k utterances from 7 speakers is better than that of speaker dependent models trained on 15k utterances, but in terms of stability multi-speaker models are always more stable. We also demonstrate that models mixing only 1250 utterances from a target speaker with 5k utterances from another 6 speakers can produce significantly better quality than state-of-the-art DNN-guided unit selection systems trained on more than 10 times the data from the target speaker.
Tasks	Speech Synthesis
Published	2018-11-15
URL	http://arxiv.org/abs/1811.06315v2
PDF	http://arxiv.org/pdf/1811.06315v2.pdf
PWC	https://paperswithcode.com/paper/effect-of-data-reduction-on-sequence-to
Repo
Framework

Homogeneity of a region in the logarithmic image processing framework: application to region growing algorithms


Title	Homogeneity of a region in the logarithmic image processing framework: application to region growing algorithms
Authors	Michel Jourlin, Guillaume Noyel
Abstract	The current paper deals with the role played by Logarithmic Image Processing (LIP) operators for evaluating the homogeneity of a region. Two new criteria of heterogeneity are introduced, one based on the LIP addition and the other based on the LIP scalar multiplication. Such tools are able to manage Region Growing algorithms following the Revol’s technique: starting from an initial seed, they consist of applying specific dilations to the growing region while its inhomogeneity level does not exceed a certain level. The new approaches we introduce are significantly improving Revol’s existing technique by making it robust to contrast variations in images. Such a property strongly reduces the chaining effect arising in region growing processes.
Tasks
Published	2018-06-27
URL	http://arxiv.org/abs/1806.10472v1
PDF	http://arxiv.org/pdf/1806.10472v1.pdf
PWC	https://paperswithcode.com/paper/homogeneity-of-a-region-in-the-logarithmic
Repo
Framework

A distinct approach to diagnose Dengue Fever with the help of Soft Set Theory


Title	A distinct approach to diagnose Dengue Fever with the help of Soft Set Theory
Authors	Maaz Amjad, fariha Bukhari, Iqra Ameer, Alexander Gelbukh
Abstract	Mathematics has played a substantial role to revolutionize the medical science. Intelligent systems based on mathematical theories have proved to be efficient in diagnosing various diseases. In this paper, we used an expert system based on soft set theory and fuzzy set theory named as a soft expert system to diagnose tropical disease dengue. The objective to use soft expert system is to predict the risk level of a patient having dengue fever by using input variables like age, TLC, SGOT, platelets count and blood pressure. The proposed method explicitly demonstrates the exact percentage of the risk level of dengue fever automatically circumventing for all possible (medical) imprecisions.
Tasks
Published	2018-05-22
URL	http://arxiv.org/abs/1805.09169v3
PDF	http://arxiv.org/pdf/1805.09169v3.pdf
PWC	https://paperswithcode.com/paper/a-distinct-approach-to-diagnose-dengue-fever
Repo
Framework

A Cognitive Approach to Real-time Rescheduling using SOAR-RL


Title	A Cognitive Approach to Real-time Rescheduling using SOAR-RL
Authors	Juan Cruz Barsce, Jorge A. Palombarini, Ernesto C. Martínez
Abstract	Ensuring flexible and efficient manufacturing of customized products in an increasing dynamic and turbulent environment without sacrificing cost effectiveness, product quality and on-time delivery has become a key issue for most industrial enterprises. A promising approach to cope with this challenge is the integration of cognitive capabilities in systems and processes with the aim of expanding the knowledge base used to perform managerial and operational tasks. In this work, a novel approach to real-time rescheduling is proposed in order to achieve sustainable improvements in flexibility and adaptability of production systems through the integration of artificial cognitive capabilities, involving perception, reasoning/learning and planning skills. Moreover, an industrial example is discussed where the SOAR cognitive architecture capabilities are integrated in a software prototype, showing that the approach enables the rescheduling system to respond to events in an autonomic way, and to acquire experience through intensive simulation while performing repair tasks.
Tasks
Published	2018-05-12
URL	http://arxiv.org/abs/1805.04749v1
PDF	http://arxiv.org/pdf/1805.04749v1.pdf
PWC	https://paperswithcode.com/paper/a-cognitive-approach-to-real-time
Repo
Framework

Analysis Methods in Neural Language Processing: A Survey


Title	Analysis Methods in Neural Language Processing: A Survey
Authors	Yonatan Belinkov, James Glass
Abstract	The field of natural language processing has seen impressive progress in recent years, with neural network models replacing many of the traditional systems. A plethora of new models have been proposed, many of which are thought to be opaque compared to their feature-rich counterparts. This has led researchers to analyze, interpret, and evaluate neural networks in novel and more fine-grained ways. In this survey paper, we review analysis methods in neural language processing, categorize them according to prominent research trends, highlight existing limitations, and point to potential directions for future work.
Tasks
Published	2018-12-21
URL	http://arxiv.org/abs/1812.08951v2
PDF	http://arxiv.org/pdf/1812.08951v2.pdf
PWC	https://paperswithcode.com/paper/analysis-methods-in-neural-language
Repo
Framework

On the role of ML estimation and Bregman divergences in sparse representation of covariance and precision matrices


Title	On the role of ML estimation and Bregman divergences in sparse representation of covariance and precision matrices
Authors	Branko Brkljač, Željen Trpovski
Abstract	Sparse representation of structured signals requires modelling strategies that maintain specific signal properties, in addition to preserving original information content and achieving simpler signal representation. Therefore, the major design challenge is to introduce adequate problem formulations and offer solutions that will efficiently lead to desired representations. In this context, sparse representation of covariance and precision matrices, which appear as feature descriptors or mixture model parameters, respectively, will be in the main focus of this paper.
Tasks
Published	2018-10-27
URL	http://arxiv.org/abs/1810.11718v1
PDF	http://arxiv.org/pdf/1810.11718v1.pdf
PWC	https://paperswithcode.com/paper/on-the-role-of-ml-estimation-and-bregman
Repo
Framework

A Generative Model for Natural Sounds Based on Latent Force Modelling


Title	A Generative Model for Natural Sounds Based on Latent Force Modelling
Authors	William J. Wilkinson, Joshua D. Reiss, Dan Stowell
Abstract	Recent advances in analysis of subband amplitude envelopes of natural sounds have resulted in convincing synthesis, showing subband amplitudes to be a crucial component of perception. Probabilistic latent variable analysis is particularly revealing, but existing approaches don’t incorporate prior knowledge about the physical behaviour of amplitude envelopes, such as exponential decay and feedback. We use latent force modelling, a probabilistic learning paradigm that incorporates physical knowledge into Gaussian process regression, to model correlation across spectral subband envelopes. We augment the standard latent force model approach by explicitly modelling correlations over multiple time steps. Incorporating this prior knowledge strengthens the interpretation of the latent functions as the source that generated the signal. We examine this interpretation via an experiment which shows that sounds generated by sampling from our probabilistic model are perceived to be more realistic than those generated by similar models based on nonnegative matrix factorisation, even in cases where our model is outperformed from a reconstruction error perspective.
Tasks
Published	2018-02-02
URL	http://arxiv.org/abs/1802.00680v2
PDF	http://arxiv.org/pdf/1802.00680v2.pdf
PWC	https://paperswithcode.com/paper/a-generative-model-for-natural-sounds-based
Repo
Framework

Deep Reinforcement Learning for Page-wise Recommendations


Title	Deep Reinforcement Learning for Page-wise Recommendations
Authors	Xiangyu Zhao, Long Xia, Liang Zhang, Zhuoye Ding, Dawei Yin, Jiliang Tang
Abstract	Recommender systems can mitigate the information overload problem by suggesting users’ personalized items. In real-world recommendations such as e-commerce, a typical interaction between the system and its users is – users are recommended a page of items and provide feedback; and then the system recommends a new page of items. To effectively capture such interaction for recommendations, we need to solve two key problems – (1) how to update recommending strategy according to user’s \textit{real-time feedback}, and 2) how to generate a page of items with proper display, which pose tremendous challenges to traditional recommender systems. In this paper, we study the problem of page-wise recommendations aiming to address aforementioned two challenges simultaneously. In particular, we propose a principled approach to jointly generate a set of complementary items and the corresponding strategy to display them in a 2-D page; and propose a novel page-wise recommendation framework based on deep reinforcement learning, DeepPage, which can optimize a page of items with proper display based on real-time feedback from users. The experimental results based on a real-world e-commerce dataset demonstrate the effectiveness of the proposed framework.
Tasks	Recommendation Systems
Published	2018-05-07
URL	http://arxiv.org/abs/1805.02343v2
PDF	http://arxiv.org/pdf/1805.02343v2.pdf
PWC	https://paperswithcode.com/paper/deep-reinforcement-learning-for-page-wise
Repo
Framework

Improving Graph Convolutional Networks with Non-Parametric Activation Functions


Title	Improving Graph Convolutional Networks with Non-Parametric Activation Functions
Authors	Simone Scardapane, Steven Van Vaerenbergh, Danilo Comminiello, Aurelio Uncini
Abstract	Graph neural networks (GNNs) are a class of neural networks that allow to efficiently perform inference on data that is associated to a graph structure, such as, e.g., citation networks or knowledge graphs. While several variants of GNNs have been proposed, they only consider simple nonlinear activation functions in their layers, such as rectifiers or squashing functions. In this paper, we investigate the use of graph convolutional networks (GCNs) when combined with more complex activation functions, able to adapt from the training data. More specifically, we extend the recently proposed kernel activation function, a non-parametric model which can be implemented easily, can be regularized with standard $\ell_p$-norms techniques, and is smooth over its entire domain. Our experimental evaluation shows that the proposed architecture can significantly improve over its baseline, while similar improvements cannot be obtained by simply increasing the depth or size of the original GCN.
Tasks	Knowledge Graphs
Published	2018-02-26
URL	http://arxiv.org/abs/1802.09405v1
PDF	http://arxiv.org/pdf/1802.09405v1.pdf
PWC	https://paperswithcode.com/paper/improving-graph-convolutional-networks-with
Repo
Framework

Sparse Principal Component Analysis via Variable Projection


Title	Sparse Principal Component Analysis via Variable Projection
Authors	N. Benjamin Erichson, Peng Zheng, Krithika Manohar, Steven L. Brunton, J. Nathan Kutz, Aleksandr Y. Aravkin
Abstract	Sparse principal component analysis (SPCA) has emerged as a powerful technique for data analysis, providing improved interpretation of low-rank structures by identifying localized spatial structures in the data and disambiguating between distinct time scales. We demonstrate a robust and scalable SPCA algorithm by formulating it as a value-function optimization problem. This viewpoint leads to a flexible and computationally efficient algorithm. It can further leverage randomized methods from linear algebra to extend the approach to the large-scale (big data) setting. Our proposed innovation also allows for a robust SPCA formulation which can obtain meaningful sparse components in spite of grossly corrupted input data. The proposed algorithms are demonstrated using both synthetic and real world data, showing exceptional computational efficiency and diagnostic performance.
Tasks
Published	2018-04-01
URL	http://arxiv.org/abs/1804.00341v2
PDF	http://arxiv.org/pdf/1804.00341v2.pdf
PWC	https://paperswithcode.com/paper/sparse-principal-component-analysis-via-2
Repo
Framework