October 17, 2019

3407 words 16 mins read

Paper Group ANR 764

Classifying Data with Local Hamiltonians. Supervising Unsupervised Learning with Evolutionary Algorithm in Deep Neural Network. Learning Flexible and Reusable Locomotion Primitives for a Microrobot. Non-locally Enhanced Encoder-Decoder Network for Single Image De-raining. Low-complexity Recurrent Neural Network-based Polar Decoder with Weight Quant …

Classifying Data with Local Hamiltonians


Title	Classifying Data with Local Hamiltonians
Authors	Johannes Bausch
Abstract	The goal of this work is to define a notion of a quantum neural network to classify data, which exploits the low energy spectrum of a local Hamiltonian. As a concrete application, we build a binary classifier, train it on some actual data and then test its performance on a simple classification task. More specifically, we use Microsoft’s quantum simulator, Liquid, to construct local Hamiltonians that can encode trained classifier functions in their ground space, and which can be probed by measuring the overlap with test states corresponding to the data to be classified. To obtain such a classifier Hamiltonian, we further propose a training scheme based on quantum annealing which is completely closed-off to the environment and which does not depend on external measurements until the very end, avoiding unnecessary decoherence during the annealing procedure. For a network of size n, the trained network can be stored as a list of O(n) coupling strengths. We address the question of which interactions are most suitable for a given classification task, and develop a qubit-saving optimization for the training procedure on a simulated annealing device. Furthermore, a small neural network to classify colors into red vs. blue is trained and tested, and benchmarked against the annealing parameters.
Tasks
Published	2018-07-02
URL	http://arxiv.org/abs/1807.00804v1
PDF	http://arxiv.org/pdf/1807.00804v1.pdf
PWC	https://paperswithcode.com/paper/classifying-data-with-local-hamiltonians
Repo
Framework

Supervising Unsupervised Learning with Evolutionary Algorithm in Deep Neural Network


Title	Supervising Unsupervised Learning with Evolutionary Algorithm in Deep Neural Network
Authors	Takeshi Inagaki
Abstract	A method to control results of gradient descent unsupervised learning in a deep neural network by using evolutionary algorithm is proposed. To process crossover of unsupervisedly trained models, the algorithm evaluates pointwise fitness of individual nodes in neural network. Labeled training data is randomly sampled and breeding process selects nodes by calculating degree of their consistency on different sets of sampled data. This method supervises unsupervised training by evolutionary process. We also introduce modified Restricted Boltzmann Machine which contains repulsive force among nodes in a neural network and it contributes to isolate network nodes each other to avoid accidental degeneration of nodes by evolutionary process. These new methods are applied to document classification problem and it results better accuracy than a traditional fully supervised classifier implemented with linear regression algorithm.
Tasks	Document Classification
Published	2018-03-28
URL	http://arxiv.org/abs/1803.10397v1
PDF	http://arxiv.org/pdf/1803.10397v1.pdf
PWC	https://paperswithcode.com/paper/supervising-unsupervised-learning-with
Repo
Framework

Learning Flexible and Reusable Locomotion Primitives for a Microrobot


Title	Learning Flexible and Reusable Locomotion Primitives for a Microrobot
Authors	Brian Yang, Grant Wang, Roberto Calandra, Daniel Contreras, Sergey Levine, Kristofer Pister
Abstract	The design of gaits for robot locomotion can be a daunting process which requires significant expert knowledge and engineering. This process is even more challenging for robots that do not have an accurate physical model, such as compliant or micro-scale robots. Data-driven gait optimization provides an automated alternative to analytical gait design. In this paper, we propose a novel approach to efficiently learn a wide range of locomotion tasks with walking robots. This approach formalizes locomotion as a contextual policy search task to collect data, and subsequently uses that data to learn multi-objective locomotion primitives that can be used for planning. As a proof-of-concept we consider a simulated hexapod modeled after a recently developed microrobot, and we thoroughly evaluate the performance of this microrobot on different tasks and gaits. Our results validate the proposed controller and learning scheme on single and multi-objective locomotion tasks. Moreover, the experimental simulations show that without any prior knowledge about the robot used (e.g., dynamics model), our approach is capable of learning locomotion primitives within 250 trials and subsequently using them to successfully navigate through a maze.
Tasks
Published	2018-03-01
URL	http://arxiv.org/abs/1803.00196v1
PDF	http://arxiv.org/pdf/1803.00196v1.pdf
PWC	https://paperswithcode.com/paper/learning-flexible-and-reusable-locomotion
Repo
Framework

Non-locally Enhanced Encoder-Decoder Network for Single Image De-raining


Title	Non-locally Enhanced Encoder-Decoder Network for Single Image De-raining
Authors	Guanbin Li, Xiang He, Wei Zhang, Huiyou Chang, Le Dong, Liang Lin
Abstract	Single image rain streaks removal has recently witnessed substantial progress due to the development of deep convolutional neural networks. However, existing deep learning based methods either focus on the entrance and exit of the network by decomposing the input image into high and low frequency information and employing residual learning to reduce the mapping range, or focus on the introduction of cascaded learning scheme to decompose the task of rain streaks removal into multi-stages. These methods treat the convolutional neural network as an encapsulated end-to-end mapping module without deepening into the rationality and superiority of neural network design. In this paper, we delve into an effective end-to-end neural network structure for stronger feature expression and spatial correlation learning. Specifically, we propose a non-locally enhanced encoder-decoder network framework, which consists of a pooling indices embedded encoder-decoder network to efficiently learn increasingly abstract feature representation for more accurate rain streaks modeling while perfectly preserving the image detail. The proposed encoder-decoder framework is composed of a series of non-locally enhanced dense blocks that are designed to not only fully exploit hierarchical features from all the convolutional layers but also well capture the long-distance dependencies and structural information. Extensive experiments on synthetic and real datasets demonstrate that the proposed method can effectively remove rain-streaks on rainy image of various densities while well preserving the image details, which achieves significant improvements over the recent state-of-the-art methods.
Tasks
Published	2018-08-04
URL	http://arxiv.org/abs/1808.01491v1
PDF	http://arxiv.org/pdf/1808.01491v1.pdf
PWC	https://paperswithcode.com/paper/non-locally-enhanced-encoder-decoder-network
Repo
Framework

Low-complexity Recurrent Neural Network-based Polar Decoder with Weight Quantization Mechanism


Title	Low-complexity Recurrent Neural Network-based Polar Decoder with Weight Quantization Mechanism
Authors	Chieh-Fang Teng, Chen-Hsi Wu, Kuan-Shiuan Ho, An-Yeu Wu
Abstract	Polar codes have drawn much attention and been adopted in 5G New Radio (NR) due to their capacity-achieving performance. Recently, as the emerging deep learning (DL) technique has breakthrough achievements in many fields, neural network decoder was proposed to obtain faster convergence and better performance than belief propagation (BP) decoding. However, neural networks are memory-intensive and hinder the deployment of DL in communication systems. In this work, a low-complexity recurrent neural network (RNN) polar decoder with codebook-based weight quantization is proposed. Our test results show that we can effectively reduce the memory overhead by 98% and alleviate computational complexity with slight performance loss.
Tasks	Quantization
Published	2018-10-29
URL	http://arxiv.org/abs/1810.12154v2
PDF	http://arxiv.org/pdf/1810.12154v2.pdf
PWC	https://paperswithcode.com/paper/low-complexity-recurrent-neural-network-based
Repo
Framework

Axially-shifted pattern illumination for macroscale turbidity suppression and virtual volumetric confocal imaging without axial scanning


Title	Axially-shifted pattern illumination for macroscale turbidity suppression and virtual volumetric confocal imaging without axial scanning
Authors	Shaowei Jiang, Jun Liao, Zichao Bian, Pengming Song, Garrett Soler, Kazunori Hoshino, Guoan Zheng
Abstract	Structured illumination has been widely used for optical sectioning and 3D surface recovery. In a typical implementation, multiple images under non-uniform pattern illumination are used to recover a single object section. Axial scanning of the sample or the objective lens is needed for acquiring the 3D volumetric data. Here we demonstrate the use of axially-shifted pattern illumination (asPI) for virtual volumetric confocal imaging without axial scanning. In the reported approach, we project illumination patterns at a tilted angle with respect to the detection optics. As such, the illumination patterns shift laterally at different z sections and the sample information at different z-sections can be recovered based on the captured 2D images. We demonstrate the reported approach for virtual confocal imaging through a diffusing layer and underwater 3D imaging through diluted milk. We show that we can acquire the entire confocal volume in ~1s with a throughput of 420 megapixels per second. Our approach may provide new insights for developing confocal light ranging and detection systems in degraded visual environments.
Tasks
Published	2018-12-14
URL	http://arxiv.org/abs/1812.06125v1
PDF	http://arxiv.org/pdf/1812.06125v1.pdf
PWC	https://paperswithcode.com/paper/axially-shifted-pattern-illumination-for
Repo
Framework

Topology-Aware Non-Rigid Point Cloud Registration


Title	Topology-Aware Non-Rigid Point Cloud Registration
Authors	Konstantinos Zampogiannis, Cornelia Fermuller, Yiannis Aloimonos
Abstract	In this paper, we introduce a non-rigid registration pipeline for pairs of unorganized point clouds that may be topologically different. Standard warp field estimation algorithms, even under robust, discontinuity-preserving regularization, tend to produce erratic motion estimates on boundaries associated with `close-to-open' topology changes. We overcome this limitation by exploiting backward motion: in the opposite motion direction, a` close-to-open’ event becomes open-to-close', which is by default handled correctly. At the core of our approach lies a general, topology-agnostic warp field estimation algorithm, similar to those employed in recently introduced dynamic reconstruction systems from RGB-D input. We improve motion estimation on boundaries associated with topology changes in an efficient post-processing phase. Based on both forward and (inverted) backward warp hypotheses, we explicitly detect regions of the deformed geometry that undergo topological changes by means of local deformation criteria and broadly classify them as contacts’ or `separations’. Subsequently, the two motion hypotheses are seamlessly blended on a local basis, according to the type and proximity of detected events. Our method achieves state-of-the-art motion estimation accuracy on the MPI Sintel dataset. Experiments on a custom dataset with topological event annotations demonstrate the effectiveness of our pipeline in estimating motion on event boundaries, as well as promising performance in explicit topological event detection. \|
Tasks	Motion Estimation, Point Cloud Registration
Published	2018-11-16
URL	https://arxiv.org/abs/1811.07014v3
PDF	https://arxiv.org/pdf/1811.07014v3.pdf
PWC	https://paperswithcode.com/paper/topology-aware-non-rigid-point-cloud
Repo
Framework

The Heart of an Image: Quantum Superposition and Entanglement in Visual Perception


Title	The Heart of an Image: Quantum Superposition and Entanglement in Visual Perception
Authors	Jonito Aerts Arguelles
Abstract	We analyse the way in which the principle that ‘the whole is greater than the sum of its parts’ manifests itself with phenomena of visual perception. For this investigation we use insights and techniques coming from quantum cognition, and more specifically we are inspired by the correspondence of this principle with the phenomenon of the conjunction effect in human cognition. We identify entities of meaning within artefacts of visual perception and rely on how such entities are modelled for corpuses of texts such as the webpages of the World-Wide Web for our study of how they appear in phenomena of visual perception. We identify concretely the conjunction effect in visual artefacts and analyse its structure in the example of a photograph. We also analyse quantum entanglement between different aspects of meaning in artefacts of visual perception. We confirm its presence by showing that well elected experiments on images retrieved accordingly by Google Images give rise to probabilities and expectation values violating the Clauser Horne Shimony Holt version of Bell’s inequalities. We point out how this approach can lead to a mathematical description of the meaning content of a visual artefact such as a photograph.
Tasks
Published	2018-01-31
URL	http://arxiv.org/abs/1802.02216v1
PDF	http://arxiv.org/pdf/1802.02216v1.pdf
PWC	https://paperswithcode.com/paper/the-heart-of-an-image-quantum-superposition
Repo
Framework

Semi-Supervised Learning for Neural Keyphrase Generation


Title	Semi-Supervised Learning for Neural Keyphrase Generation
Authors	Hai Ye, Lu Wang
Abstract	We study the problem of generating keyphrases that summarize the key points for a given document. While sequence-to-sequence (seq2seq) models have achieved remarkable performance on this task (Meng et al., 2017), model training often relies on large amounts of labeled data, which is only applicable to resource-rich domains. In this paper, we propose semi-supervised keyphrase generation methods by leveraging both labeled data and large-scale unlabeled samples for learning. Two strategies are proposed. First, unlabeled documents are first tagged with synthetic keyphrases obtained from unsupervised keyphrase extraction methods or a selflearning algorithm, and then combined with labeled samples for training. Furthermore, we investigate a multi-task learning framework to jointly learn to generate keyphrases as well as the titles of the articles. Experimental results show that our semi-supervised learning-based methods outperform a state-of-the-art model trained with labeled data only.
Tasks	Multi-Task Learning
Published	2018-08-21
URL	https://arxiv.org/abs/1808.06773v2
PDF	https://arxiv.org/pdf/1808.06773v2.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-learning-for-neural-keyphrase
Repo
Framework

Local White Matter Architecture Defines Functional Brain Dynamics


Title	Local White Matter Architecture Defines Functional Brain Dynamics
Authors	Yo Joong Choe, Sivaraman Balakrishnan, Aarti Singh, Jean M. Vettel, Timothy Verstynen
Abstract	Large bundles of myelinated axons, called white matter, anatomically connect disparate brain regions together and compose the structural core of the human connectome. We recently proposed a method of measuring the local integrity along the length of each white matter fascicle, termed the local connectome. If communication efficiency is fundamentally constrained by the integrity along the entire length of a white matter bundle, then variability in the functional dynamics of brain networks should be associated with variability in the local connectome. We test this prediction using two statistical approaches that are capable of handling the high dimensionality of data. First, by performing statistical inference on distance-based correlations, we show that similarity in the local connectome between individuals is significantly correlated with similarity in their patterns of functional connectivity. Second, by employing variable selection using sparse canonical correlation analysis and cross-validation, we show that segments of the local connectome are predictive of certain patterns of functional brain dynamics. These results are consistent with the hypothesis that structural variability along axon bundles constrains communication between disparate brain regions.
Tasks
Published	2018-04-22
URL	http://arxiv.org/abs/1804.08154v2
PDF	http://arxiv.org/pdf/1804.08154v2.pdf
PWC	https://paperswithcode.com/paper/local-white-matter-architecture-defines
Repo
Framework

To Create What You Tell: Generating Videos from Captions


Title	To Create What You Tell: Generating Videos from Captions
Authors	Yingwei Pan, Zhaofan Qiu, Ting Yao, Houqiang Li, Tao Mei
Abstract	We are creating multimedia contents everyday and everywhere. While automatic content generation has played a fundamental challenge to multimedia community for decades, recent advances of deep learning have made this problem feasible. For example, the Generative Adversarial Networks (GANs) is a rewarding approach to synthesize images. Nevertheless, it is not trivial when capitalizing on GANs to generate videos. The difficulty originates from the intrinsic structure where a video is a sequence of visually coherent and semantically dependent frames. This motivates us to explore semantic and temporal coherence in designing GANs to generate videos. In this paper, we present a novel Temporal GANs conditioning on Captions, namely TGANs-C, in which the input to the generator network is a concatenation of a latent noise vector and caption embedding, and then is transformed into a frame sequence with 3D spatio-temporal convolutions. Unlike the naive discriminator which only judges pairs as fake or real, our discriminator additionally notes whether the video matches the correct caption. In particular, the discriminator network consists of three discriminators: video discriminator classifying realistic videos from generated ones and optimizes video-caption matching, frame discriminator discriminating between real and fake frames and aligning frames with the conditioning caption, and motion discriminator emphasizing the philosophy that the adjacent frames in the generated videos should be smoothly connected as in real ones. We qualitatively demonstrate the capability of our TGANs-C to generate plausible videos conditioning on the given captions on two synthetic datasets (SBMG and TBMG) and one real-world dataset (MSVD). Moreover, quantitative experiments on MSVD are performed to validate our proposal via Generative Adversarial Metric and human study.
Tasks
Published	2018-04-23
URL	http://arxiv.org/abs/1804.08264v1
PDF	http://arxiv.org/pdf/1804.08264v1.pdf
PWC	https://paperswithcode.com/paper/to-create-what-you-tell-generating-videos
Repo
Framework


Title	Leolani: a reference machine with a theory of mind for social communication
Authors	Piek Vossen, Selene Baez, Lenka Bajčetić, Bram Kraaijeveld
Abstract	Our state of mind is based on experiences and what other people tell us. This may result in conflicting information, uncertainty, and alternative facts. We present a robot that models relativity of knowledge and perception within social interaction following principles of the theory of mind. We utilized vision and speech capabilities on a Pepper robot to build an interaction model that stores the interpretations of perceptions and conversations in combination with provenance on its sources. The robot learns directly from what people tell it, possibly in relation to its perception. We demonstrate how the robot’s communication is driven by hunger to acquire more knowledge from and on people and objects, to resolve uncertainties and conflicts, and to share awareness of the per- ceived environment. Likewise, the robot can make reference to the world and its knowledge about the world and the encounters with people that yielded this knowledge.
Tasks
Published	2018-06-05
URL	http://arxiv.org/abs/1806.01526v1
PDF	http://arxiv.org/pdf/1806.01526v1.pdf
PWC	https://paperswithcode.com/paper/leolani-a-reference-machine-with-a-theory-of
Repo
Framework

Domain Adaptation on Graphs by Learning Graph Topologies: Theoretical Analysis and an Algorithm


Title	Domain Adaptation on Graphs by Learning Graph Topologies: Theoretical Analysis and an Algorithm
Authors	Elif Vural
Abstract	Traditional machine learning algorithms assume that the training and test data have the same distribution, while this assumption does not necessarily hold in real applications. Domain adaptation methods take into account the deviations in the data distribution. In this work, we study the problem of domain adaptation on graphs. We consider a source graph and a target graph constructed with samples drawn from data manifolds. We study the problem of estimating the unknown class labels on the target graph using the label information on the source graph and the similarity between the two graphs. We particularly focus on a setting where the target label function is learnt such that its spectrum is similar to that of the source label function. We first propose a theoretical analysis of domain adaptation on graphs and present performance bounds that characterize the target classification error in terms of the properties of the graphs and the data manifolds. We show that the classification performance improves as the topologies of the graphs get more balanced, i.e., as the numbers of neighbors of different graph nodes become more proportionate, and weak edges with small weights are avoided. Our results also suggest that graph edges between too distant data samples should be avoided for good generalization performance. We then propose a graph domain adaptation algorithm inspired by our theoretical findings, which estimates the label functions while learning the source and target graph topologies at the same time. The joint graph learning and label estimation problem is formulated through an objective function relying on our performance bounds, which is minimized with an alternating optimization scheme. Experiments on synthetic and real data sets suggest that the proposed method outperforms baseline approaches.
Tasks	Domain Adaptation
Published	2018-12-17
URL	http://arxiv.org/abs/1812.06944v2
PDF	http://arxiv.org/pdf/1812.06944v2.pdf
PWC	https://paperswithcode.com/paper/domain-adaptation-on-graphs-by-learning-graph
Repo
Framework

Explaining Queries over Web Tables to Non-Experts


Title	Explaining Queries over Web Tables to Non-Experts
Authors	Jonathan Berant, Daniel Deutch, Amir Globerson, Tova Milo, Tomer Wolfson
Abstract	Designing a reliable natural language (NL) interface for querying tables has been a longtime goal of researchers in both the data management and natural language processing (NLP) communities. Such an interface receives as input an NL question, translates it into a formal query, executes the query and returns the results. Errors in the translation process are not uncommon, and users typically struggle to understand whether their query has been mapped correctly. We address this problem by explaining the obtained formal queries to non-expert users. Two methods for query explanations are presented: the first translates queries into NL, while the second method provides a graphic representation of the query cell-based provenance (in its execution on a given table). Our solution augments a state-of-the-art NL interface over web tables, enhancing it in both its training and deployment phase. Experiments, including a user study conducted on Amazon Mechanical Turk, show our solution to improve both the correctness and reliability of an NL interface.
Tasks
Published	2018-08-14
URL	http://arxiv.org/abs/1808.04614v1
PDF	http://arxiv.org/pdf/1808.04614v1.pdf
PWC	https://paperswithcode.com/paper/explaining-queries-over-web-tables-to-non
Repo
Framework

Learning Mixtures of Linear Regressions with Nearly Optimal Complexity


Title	Learning Mixtures of Linear Regressions with Nearly Optimal Complexity
Authors	Yuanzhi Li, Yingyu Liang
Abstract	Mixtures of Linear Regressions (MLR) is an important mixture model with many applications. In this model, each observation is generated from one of the several unknown linear regression components, where the identity of the generated component is also unknown. Previous works either assume strong assumptions on the data distribution or have high complexity. This paper proposes a fixed parameter tractable algorithm for the problem under general conditions, which achieves global convergence and the sample complexity scales nearly linearly in the dimension. In particular, different from previous works that require the data to be from the standard Gaussian, the algorithm allows the data from Gaussians with different covariances. When the conditional number of the covariances and the number of components are fixed, the algorithm has nearly optimal sample complexity $N = \tilde{O}(d)$ as well as nearly optimal computational complexity $\tilde{O}(Nd)$, where $d$ is the dimension of the data space. To the best of our knowledge, this approach provides the first such recovery guarantee for this general setting.
Tasks
Published	2018-02-22
URL	https://arxiv.org/abs/1802.07895v3
PDF	https://arxiv.org/pdf/1802.07895v3.pdf
PWC	https://paperswithcode.com/paper/learning-mixtures-of-linear-regressions-with
Repo
Framework