[1807.02301] Sequential Copying Networks
https://arxiv.org/abs/1807.02301
Copying mechanism shows effectiveness in sequence-to-sequence based neural network models for text generation tasks, such as abstractive sentence summarization and question generation. However, existing works on modeling copying or pointing mechanism only considers single word copying from the source sentences. In this paper, we propose a novel copying framework, named Sequential Copying Networks (SeqCopyNet), which not only learns to copy single words, but also copies sequences from the input sentence. It leverages the pointer networks to explicitly select a sub-span from the source side to target side, and integrates this sequential copying mechanism to the generation process in the encoder-decoder paradigm. Experiments on abstractive sentence summarization and question generation tasks show that the proposed SeqCopyNet can copy meaningful spans and outperforms the baseline models.
[1807.02291] Sliced Recurrent Neural Networks
https://arxiv.org/abs/1807.02291
Recurrent neural networks have achieved great success in many NLP tasks. However, they have difficulty in parallelization because of the recurrent structure, so it takes much time to train RNNs. In this paper, we introduce sliced recurrent neural networks (SRNNs), which could be parallelized by slicing the sequences into many subsequences. SRNNs have the ability to obtain high-level information through multiple layers with few extra parameters. We prove that the standard RNN is a special case of the SRNN when we use linear activation functions. Without changing the recurrent units, SRNNs are 136 times as fast as standard RNNs and could be even faster when we train longer sequences. Experiments on six largescale sentiment analysis datasets show that SRNNs achieve better performance than standard RNNs.
[1807.02350] A Variational Time Series Feature Extractor for Action Prediction
https://arxiv.org/abs/1807.02350
We propose a Variational Time Series Feature Extractor (VTSFE), inspired by the VAE-DMP model of Chen et al., to be used for action recognition and prediction. Our method is based on variational autoencoders. It improves VAE-DMP in that it has a better noise inference model, a simpler transition model constraining the acceleration in the trajectories of the latent space, and a tighter lower bound for the variational inference. We apply the method for classification and prediction of whole-body movements on a dataset with 7 tasks and 10 demonstrations per task, recorded with a wearable motion capture suit. The comparison with VAE and VAE-DMP suggests the better performance of our method for feature extraction. An open-source software implementation of each method with TensorFlow is also provided. In addition, a more detailed version of this work can be found in the indicated code repository. Although it was meant to, the VTSFE hasn't been tested for action prediction, due to a lack of time in the context of Maxime Chaveroche's Master thesis at INRIA.
[1807.02490] Deep Multiple Instance Feature Learning via Variational Autoencoder
https://arxiv.org/abs/1807.02490
We describe a novel weakly supervised deep learning framework that combines both the discriminative and generative models to learn meaningful representation in the multiple instance learning (MIL) setting. MIL is a weakly supervised learning problem where labels are associated with groups of instances (referred as bags) instead of individual instances. To address the essential challenge in MIL problems raised from the uncertainty of positive instances label, we use a discriminative model regularized by variational autoencoders (VAEs) to maximize the differences between latent representations of all instances and negative instances. As a result, the hidden layer of the variational autoencoder learns meaningful representation. This representation can effectively be used for MIL problems as illustrated by better performance on the standard benchmark datasets comparing to the state-of-the-art approaches. More importantly, unlike most related studies, the proposed framework can be easily scaled to large dataset problems, as illustrated by the audio event detection and segmentation task. Visualization also confirms the effectiveness of the latent representation in discriminating positive and negative classes.
[1807.02401] Learning a Representation Map for Robot Navigation using Deep Variational Autoencoder
https://arxiv.org/abs/1807.02401
The aim of this work is to use Variational Autoencoder (VAE) to learn a representation of an indoor environment that can be used for robot navigation. We use images extracted from a video, in which a camera takes a tour around a house, for training the VAE model with a 4 dimensional latent space. After the model is trained, each real frame has a corresponding representation point on manifold in the latent space, and each representation point has corresponding reconstructed image. For the navigation problem, we map the starting image and destination image to the latent space, then optimize a path on the learned manifold connecting the two points, and finally map the path back through decoder to a sequence of images. The ideal sequence of images should correspond to a route that is spatially continuous - i.e. neighbor images in the route should correspond to neighbor locations in physical space. Such a route could be used for navigation with computer vision techniques, i.e. a robot could follow the image sequence from starting location to destination in the environment step by step. We implement this algorithm, but find in our experimental results that the resulting route is not satisfactory. The route consist of several discontinuous image frames along the ideal routes, so that the route could not be followed by a robot with computer vision techniques in practice. In our evaluation, we propose two reasons for our failure to automatically find continuous routes: (1) The VAE tends to capture global structures, but discard the details; (2) the Euclidean similarity metric used for measuring continuity between house images is sub-optimal. For further work, we propose: trying other generative models like VAE-GANs which may be better at reconstructing the details to learn the representation map, and adjusting the similarity metric in the path selecting algorithm.
[1807.02323] Optimal Sensor Data Fusion Architecture for Object Detection in Adverse Weather Conditions
https://arxiv.org/abs/1807.02323
A good and robust sensor data fusion in diverse weather conditions is a quite challenging task. There are several fusion architectures in the literature, e.g. the sensor data can be fused right at the beginning (Early Fusion), or they can be first processed separately and then concatenated later (Late Fusion). In this work, different fusion architectures are compared and evaluated by means of object detection tasks, in which the goal is to recognize and localize predefined objects in a stream of data. Usually, state-of-the-art object detectors based on neural networks are highly optimized for good weather conditions, since the well-known benchmarks only consist of sensor data recorded in optimal weather conditions. Therefore, the performance of these approaches decreases enormously or even fails in adverse weather conditions. In this work, different sensor fusion architectures are compared for good and adverse weather conditions for finding the optimal fusion architecture for diverse weather situations. A new training strategy is also introduced such that the performance of the object detector is greatly enhanced in adverse weather scenarios or if a sensor fails. Furthermore, the paper responds to the question if the detection accuracy can be increased further by providing the neural network with a-priori knowledge such as the spatial calibration of the sensors.
[1807.02287] Outperforming Good-Turing: Preliminary Report
https://arxiv.org/abs/1807.02287
Estimating a large alphabet probability distribution from a limited number of samples is a fundamental problem in machine learning and statistics. A variety of estimation schemes have been proposed over the years, mostly inspired by the early work of Laplace and the seminal contribution of Good and Turing. One of the basic assumptions shared by most commonly-used estimators is the unique correspondence between the symbol's sample frequency and its estimated probability. In this work we tackle this paradigmatic assumption; we claim that symbols with "similar" frequencies shall be assigned the same estimated probability value. This way we regulate the number of parameters and improve generalization. In this preliminary report we show that by applying an ensemble of such regulated estimators, we introduce a dramatic enhancement in the estimation accuracy (typically up to 50%), compared to currently known methods. An implementation of our suggested method is publicly available at the first author's web-page.
[1807.02284] Continuous-Scale Kinetic Fluid Simulation
https://arxiv.org/abs/1807.02284
Kinetic approaches, i.e., methods based on the lattice Boltzmann equations, have long been recognized as an appealing alternative for solving incompressible Navier-Stokes equations in computational fluid dynamics. However, such approaches have not been widely adopted in graphics mainly due to the underlying inaccuracy, instability and inflexibility. In this paper, we try to tackle these problems in order to make kinetic approaches practical for graphical applications. To achieve more accurate and stable simulations, we propose to employ the non-orthogonal central-moment-relaxation model, where we develop a novel adaptive relaxation method to retain both stability and accuracy in turbulent flows. To achieve flexibility, we propose a novel continuous-scale formulation that enables samples at arbitrary resolutions to easily communicate with each other in a more continuous sense and with loose geometrical constraints, which allows efficient and adaptive sample construction to better match the physical scale. Such a capability directly leads to an automatic sample construction which generates static and dynamic scales at initialization and during simulation, respectively. This effectively makes our method suitable for simulating turbulent flows with arbitrary geometrical boundaries. Our simulation results with applications to smoke animations show the benefits of our method, with comparisons for justification and verification.
[1807.02222] Digital Geometry, a Survey
https://arxiv.org/abs/1807.02222
This paper provides an overview of modern digital geometry and topology through mathematical principles, algorithms, and measurements. It also covers recent developments in the applications of digital geometry and topology including image processing, computer vision, and data science. Recent research strongly showed that digital geometry has made considerable contributions to modelings and algorithms in image segmentation, algorithmic analysis, and BigData analytics.
[1807.02200] Natural Language Processing for Music Knowledge Discovery
https://arxiv.org/abs/1807.02200
Today, a massive amount of musical knowledge is stored in written form, with testimonies dated as far back as several centuries ago. In this work, we present different Natural Language Processing (NLP) approaches to harness the potential of these text collections for automatic music knowledge discovery, covering different phases in a prototypical NLP pipeline, namely corpus compilation, text-mining, information extraction, knowledge graph generation and sentiment analysis. Each of these approaches is presented alongside different use cases (i.e., flamenco, Renaissance and popular music) where large collections of documents are processed, and conclusions stemming from data-driven analyses are presented and discussed.
[1807.02192] A Survey of Knowledge Representation and Retrieval for Learning in Service Robotics
https://arxiv.org/abs/1807.02192
[1807.02143] Spatiotemporal KSVD Dictionary Learning for Online Multi-target Tracking
https://arxiv.org/abs/1807.02143
[1807.02326] Causal Deep Information Bottleneck
https://arxiv.org/abs/1807.02326
Estimating causal effects in the presence of latent confounding is a frequently occurring problem in several tasks. In real world applications such as medicine, accounting for the effects of latent confounding is even more challenging as a result of high-dimensional and noisy data. In this work, we propose estimating the causal effect from the perspective of the information bottleneck principle by explicitly identifying a low-dimensional representation of latent confounding. In doing so, we prove theoretically that the proposed model can be used to recover the average causal effect. Experiments on both synthetic data and existing causal benchmarks illustrate that our method achieves state-of-the-art performance in terms of prediction accuracy and sample efficiency, without sacrificing interpretability.
[1807.02235] Towards more Reliable Transfer Learning
https://arxiv.org/abs/1807.02235
Multi-source transfer learning has been proven effective when within-target labeled data is scarce. Previous work focuses primarily on exploiting domain similarities and assumes that source domains are richly or at least comparably labeled. While this strong assumption is never true in practice, this paper relaxes it and addresses challenges related to sources with diverse labeling volume and diverse reliability. The first challenge is combining domain similarity and source reliability by proposing a new transfer learning method that utilizes both source-target similarities and inter-source relationships. The second challenge involves pool-based active learning where the oracle is only available in source domains, resulting in an integrated active transfer learning framework that incorporates distribution matching and uncertainty sampling. Extensive experiments on synthetic and two real-world datasets clearly demonstrate the superiority of our proposed methods over several baselines including state-of-the-art transfer learning methods.
[1807.02492] Dynamic Load Balancing for Compressible Multiphase Turbulence
https://arxiv.org/abs/1807.02492
CMT-nek is a new scientific application for performing high fidelity predictive simulations of particle laden explosively dispersed turbulent flows. CMT-nek involves detailed simulations, is compute intensive and is targeted to be deployed on exascale platforms. The moving particles are the main source of load imbalance as the application is executed on parallel processors. In a demonstration problem, all the particles are initially in a closed container until a detonation occurs and the particles move apart. If all processors get an equal share of the fluid domain, then only some of the processors get sections of the domain that are initially laden with particles, leading to disparate load on the processors. In order to eliminate load imbalance in different processors and to speedup the makespan, we present different load balancing algorithms for CMT-nek on large scale multi-core platforms consisting of hundred of thousands of cores. The detailed process of the load balancing algorithms are presented. The performance of the different load balancing algorithms are compared and the associated overheads are analyzed. Evaluations on the application with and without load balancing are conducted and these show that with load balancing, simulation time becomes faster by a factor of up to 9.97.
Teamin官网—微信群助手|微信群管理|微信文档|团队协作工具
https://www.teamin.cc/
Teamin－快乐工作
https://app.teamin.cc/page/main.html
