Paper Group ANR 450
Dropout Induced Noise for Co-Creative GAN Systems. Unsupervised pre-training helps to conserve views from input distribution. Bayesian Linear Regression on Deep Representations. Matching-based Depth Camera and Mirrors for 3D Reconstruction. On Laughter and Speech-Laugh, Based on Observations of Child-Robot Interaction. Approximate Bayesian computat …
Dropout Induced Noise for Co-Creative GAN Systems
| Title | Dropout Induced Noise for Co-Creative GAN Systems |
| Authors | Sabine Wieluch, Dr. Friedhelm Schwenker |
| Abstract | This paper demonstrates how Dropout can be used in Generative Adversarial Networks to generate multiple different outputs to one input. This method is thought as an alternative to latent space exploration, especially if constraints in the input should be preserved, like in A-to-B translation tasks. |
| Tasks | |
| Published | 2019-09-10 |
| URL | https://arxiv.org/abs/1909.04474v1 |
| https://arxiv.org/pdf/1909.04474v1.pdf | |
| PWC | https://paperswithcode.com/paper/dropout-induced-noise-for-co-creative-gan |
| Repo | |
| Framework | |
Unsupervised pre-training helps to conserve views from input distribution
| Title | Unsupervised pre-training helps to conserve views from input distribution |
| Authors | Nicolas Pinchaud |
| Abstract | We investigate the effects of the unsupervised pre-training method under the perspective of information theory. If the input distribution displays multiple views of the supervision, then unsupervised pre-training allows to learn hierarchical representation which communicates these views across layers, while disentangling the supervision. Disentanglement of supervision leads learned features to be independent conditionally to the label. In case of binary features, we show that conditional independence allows to extract label’s information with a linear model and therefore helps to solve under-fitting. We suppose that representations displaying multiple views help to solve over-fitting because each view provides information that helps to reduce model’s variance. We propose a practical method to measure both disentanglement of supervision and quantity of views within a binary representation. We show that unsupervised pre-training helps to conserve views from input distribution, whereas representations learned using supervised models disregard most of them. |
| Tasks | |
| Published | 2019-05-30 |
| URL | https://arxiv.org/abs/1905.12889v1 |
| https://arxiv.org/pdf/1905.12889v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-pre-training-helps-to-conserve |
| Repo | |
| Framework | |
Bayesian Linear Regression on Deep Representations
| Title | Bayesian Linear Regression on Deep Representations |
| Authors | John Moberg, Lennart Svensson, Juliano Pinto, Henk Wymeersch |
| Abstract | A simple approach to obtaining uncertainty-aware neural networks for regression is to do Bayesian linear regression (BLR) on the representation from the last hidden layer. Recent work [Riquelme et al., 2018, Azizzadenesheli et al., 2018] indicates that the method is promising, though it has been limited to homoscedastic noise. In this paper, we propose a novel variation that enables the method to flexibly model heteroscedastic noise. The method is benchmarked against two prominent alternative methods on a set of standard datasets, and finally evaluated as an uncertainty-aware model in model-based reinforcement learning. Our experiments indicate that the method is competitive with standard ensembling, and ensembles of BLR outperforms the methods we compared to. |
| Tasks | |
| Published | 2019-12-14 |
| URL | https://arxiv.org/abs/1912.06760v1 |
| https://arxiv.org/pdf/1912.06760v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-linear-regression-on-deep |
| Repo | |
| Framework | |
Matching-based Depth Camera and Mirrors for 3D Reconstruction
| Title | Matching-based Depth Camera and Mirrors for 3D Reconstruction |
| Authors | Trong Nguyen Nguyen, Huu Hung Huynh, Jean Meunier |
| Abstract | Reconstructing 3D object models is playing an important role in many applications in the field of computer vision. Instead of employing a collection of cameras and/or sensors as in many studies, this paper proposes a simple way to build a cheaper system for 3D reconstruction using only one depth camera and 2 or more mirrors. Each mirror is equivalently considered as a depth camera at another viewpoint. Since all scene data are provided by only one depth sensor, our approach can be applied to moving objects and does not require any synchronization protocol as with a set of cameras. Some experiments were performed on easy-to-evaluate objects to confirm the reconstruction accuracy of our proposed system. |
| Tasks | 3D Reconstruction |
| Published | 2019-08-17 |
| URL | https://arxiv.org/abs/1908.06342v1 |
| https://arxiv.org/pdf/1908.06342v1.pdf | |
| PWC | https://paperswithcode.com/paper/matching-based-depth-camera-and-mirrors-for |
| Repo | |
| Framework | |
On Laughter and Speech-Laugh, Based on Observations of Child-Robot Interaction
| Title | On Laughter and Speech-Laugh, Based on Observations of Child-Robot Interaction |
| Authors | Anton Batliner, Stefan Steidl, Florian Eyben, Björn Schuller |
| Abstract | In this article, we study laughter found in child-robot interaction where it had not been prompted intentionally. Different types of laughter and speech-laugh are annotated and processed. In a descriptive part, we report on the position of laughter and speech-laugh in syntax and dialogue structure, and on communicative functions. In a second part, we report on automatic classification performance and on acoustic characteristics, based on extensive feature selection procedures. |
| Tasks | Feature Selection |
| Published | 2019-08-30 |
| URL | https://arxiv.org/abs/1908.11593v1 |
| https://arxiv.org/pdf/1908.11593v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-laughter-and-speech-laugh-based-on |
| Repo | |
| Framework | |
Approximate Bayesian computation via the energy statistic
| Title | Approximate Bayesian computation via the energy statistic |
| Authors | Hien D. Nguyen, Julyan Arbel, Hongliang Lü, Florence Forbes |
| Abstract | Approximate Bayesian computation (ABC) has become an essential part of the Bayesian toolbox for addressing problems in which the likelihood is prohibitively expensive or entirely unknown, making it intractable. ABC defines a quasi-posterior by comparing observed data with simulated data, traditionally based on some summary statistics, the elicitation of which is regarded as a key difficulty. In recent years, a number of data discrepancy measures bypassing the construction of summary statistics have been proposed, including the Kullback–Leibler divergence, the Wasserstein distance and maximum mean discrepancies. Here we propose a novel importance-sampling (IS) ABC algorithm relying on the so-called \textit{two-sample energy statistic}. We establish a new asymptotic result for the case where both the observed sample size and the simulated data sample size increase to infinity, which highlights to what extent the data discrepancy measure impacts the asymptotic pseudo-posterior. The result holds in the broad setting of IS-ABC methodologies, thus generalizing previous results that have been established only for rejection ABC algorithms. Furthermore, we propose a consistent V-statistic estimator of the energy statistic, under which we show that the large sample result holds. Our proposed energy statistic based ABC algorithm is demonstrated on a variety of models, including a Gaussian mixture, a moving-average model of order two, a bivariate beta and a multivariate $g$-and-$k$ distribution. We find that our proposed method compares well with alternative discrepancy measures. |
| Tasks | |
| Published | 2019-05-14 |
| URL | https://arxiv.org/abs/1905.05884v1 |
| https://arxiv.org/pdf/1905.05884v1.pdf | |
| PWC | https://paperswithcode.com/paper/approximate-bayesian-computation-via-the |
| Repo | |
| Framework | |
Features or Shape? Tackling the False Dichotomy of Time Series Classification
| Title | Features or Shape? Tackling the False Dichotomy of Time Series Classification |
| Authors | Sara Alaee, Alireza Abdoli, Christian Shelton, Amy C. Murillo, Alec C. Gerry, Eamonn Keogh |
| Abstract | Time series classification is an important task in its own right, and it is often a precursor to further downstream analytics. To date, virtually all works in the literature have used either shape-based classification using a distance measure or feature-based classification after finding some suitable features for the domain. It seems to be underappreciated that in many datasets it is the case that some classes are best discriminated with features, while others are best discriminated with shape. Thus, making the shape vs. feature choice will condemn us to poor results, at least for some classes. In this work, we propose a new model for classifying time series that allows the use of both shape and feature-based measures, when warranted. Our algorithm automatically decides which approach is best for which class, and at query time chooses which classifier to trust the most. We evaluate our idea on real world datasets and demonstrate that our ideas produce statistically significant improvement in classification accuracy. |
| Tasks | Time Series, Time Series Classification |
| Published | 2019-12-20 |
| URL | https://arxiv.org/abs/1912.09614v1 |
| https://arxiv.org/pdf/1912.09614v1.pdf | |
| PWC | https://paperswithcode.com/paper/features-or-shape-tackling-the-false |
| Repo | |
| Framework | |
A Systematic Mapping Study on Testing of Machine Learning Programs
| Title | A Systematic Mapping Study on Testing of Machine Learning Programs |
| Authors | Salman Sherin, Muhammad Uzair khan, Muhammad Zohaib Iqbal |
| Abstract | We aim to conduct a systematic mapping in the area of testing ML programs. We identify, analyze and classify the existing literature to provide an overview of the area. We followed well-established guidelines of systematic mapping to develop a systematic protocol to identify and review the existing literature. We formulate three sets of research questions, define inclusion and exclusion criteria and systematically identify themes for the classification of existing techniques. We also report the quality of the published works using established assessment criteria. we finally selected 37 papers out of 1654 based on our selection criteria up to January 2019. We analyze trends such as contribution facet, research facet, test approach, type of ML and the kind of testing with several other attributes. We also discuss the empirical evidence and reporting quality of selected papers. The data from the study is made publicly available for other researchers and practitioners. We present an overview of the area by answering several research questions. The area is growing rapidly, however, there is lack of enough empirical evidence to compare and assess the effectiveness of the techniques. More publicly available tools are required for use of practitioners and researchers. Further attention is needed on non-functional testing and testing of ML programs using reinforcement learning. We believe that this study can help researchers and practitioners to obtain an overview of the area and identify several sub-areas where more research is required |
| Tasks | |
| Published | 2019-07-11 |
| URL | https://arxiv.org/abs/1907.09427v1 |
| https://arxiv.org/pdf/1907.09427v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-systematic-mapping-study-on-testing-of |
| Repo | |
| Framework | |
Reliable and Low-Complexity MIMO Detector Selection using Neural Network
| Title | Reliable and Low-Complexity MIMO Detector Selection using Neural Network |
| Authors | Shailesh Chaudhari, HyukJoon Kwon, Kee-Bong Song |
| Abstract | In this paper, we propose to dynamically select a MIMO detector using neural network for each resource element (RE) in the transport block of 5G NR/LTE communication system. The objective is to minimize the computational complexity of MIMO detection while keeping the transport block error rate (BLER) close to the BLER when dimension-reduced maximum-likelihood (DR-ML) detection is used. A detector selection problem is formulated to achieve this objective. However, since the problem is high dimensional and NP-hard, we first decompose the problem into smaller problems and train a multi-layer perceptron (MLP) network to obtain the solution. The MLP network is trained to select a low-complexity, yet reliable, detector using instantaneous channel condition in the RE. We first propose a method to generate a labeled dataset to select a low-complexity detector. Then, the MLP is trained twice using quasi-Newton method to select a reliable detector for each RE. The performance of online detector selection is evaluated in 5G NR link level simulator in terms of BLER and the complexity is quantified in terms of the number of Euclidean distance (ED) computations and the number of real additions and multiplication. Results show that the computational complexity in the MIMO detector can be reduced by ~10X using the proposed method. |
| Tasks | |
| Published | 2019-10-11 |
| URL | https://arxiv.org/abs/1910.05369v1 |
| https://arxiv.org/pdf/1910.05369v1.pdf | |
| PWC | https://paperswithcode.com/paper/reliable-and-low-complexity-mimo-detector |
| Repo | |
| Framework | |
Information bottleneck through variational glasses
| Title | Information bottleneck through variational glasses |
| Authors | Slava Voloshynovskiy, Mouad Kondah, Shideh Rezaeifar, Olga Taran, Taras Holotyak, Danilo Jimenez Rezende |
| Abstract | Information bottleneck (IB) principle [1] has become an important element in information-theoretic analysis of deep models. Many state-of-the-art generative models of both Variational Autoencoder (VAE) [2; 3] and Generative Adversarial Networks (GAN) [4] families use various bounds on mutual information terms to introduce certain regularization constraints [5; 6; 7; 8; 9; 10]. Accordingly, the main difference between these models consists in add regularization constraints and targeted objectives. In this work, we will consider the IB framework for three classes of models that include supervised, unsupervised and adversarial generative models. We will apply a variational decomposition leading a common structure and allowing easily establish connections between these models and analyze underlying assumptions. Based on these results, we focus our analysis on unsupervised setup and reconsider the VAE family. In particular, we present a new interpretation of VAE family based on the IB framework using a direct decomposition of mutual information terms and show some interesting connections to existing methods such as VAE [2; 3], beta-VAE [11], AAE [12], InfoVAE [5] and VAE/GAN [13]. Instead of adding regularization constraints to an evidence lower bound (ELBO) [2; 3], which itself is a lower bound, we show that many known methods can be considered as a product of variational decomposition of mutual information terms in the IB framework. The proposed decomposition might also contribute to the interpretability of generative models of both VAE and GAN families and create a new insights to a generative compression [14; 15; 16; 17]. It can also be of interest for the analysis of novelty detection based on one-class classifiers [18] with the IB based discriminators. |
| Tasks | |
| Published | 2019-12-02 |
| URL | https://arxiv.org/abs/1912.00830v2 |
| https://arxiv.org/pdf/1912.00830v2.pdf | |
| PWC | https://paperswithcode.com/paper/information-bottleneck-through-variational |
| Repo | |
| Framework | |
ATCSpeech: a multilingual pilot-controller speech corpus from real Air Traffic Control environment
| Title | ATCSpeech: a multilingual pilot-controller speech corpus from real Air Traffic Control environment |
| Authors | Bo Yang, Xianlong Tan, Zhengmao Chen, Bing Wang, Dan Li, Zhongping Yang, Xiping Wu, Yi Lin |
| Abstract | Automatic Speech Recognition (ASR) is greatly developed in recent years, which expedites many applications on other fields. For the ASR research, speech corpus is always an essential foundation, especially for the vertical industry, such as Air Traffic Control (ATC). There are some speech corpora for common applications, public or paid. However, for the ATC, it is difficult to collect raw speeches from real systems due to safety issues. More importantly, for a supervised learning task like ASR, annotating the transcription is a more laborious work, which hugely restricts the prospect of ASR application. In this paper, a multilingual speech corpus (ATCSpeech) from real ATC systems, including accented Mandarin Chinese and English, is built and released to encourage the non-commercial ASR research in ATC domain. The corpus is detailly introduced from the perspective of data amount, speaker gender and role, speech quality and other attributions. In addition, the performance of our baseline ASR models is also reported. A community edition for our speech database can be applied and used under a special contrast. To our best knowledge, this is the first work that aims at building a real and multilingual ASR corpus for the air traffic related research. |
| Tasks | Speech Recognition |
| Published | 2019-11-26 |
| URL | https://arxiv.org/abs/1911.11365v1 |
| https://arxiv.org/pdf/1911.11365v1.pdf | |
| PWC | https://paperswithcode.com/paper/atcspeech-a-multilingual-pilot-controller |
| Repo | |
| Framework | |
Conditional Invertible Flow for Point Cloud Generation
| Title | Conditional Invertible Flow for Point Cloud Generation |
| Authors | Michał Stypułkowski, Maciej Zamorski, Maciej Zięba, Jan Chorowski |
| Abstract | This paper focuses on a novel generative approach for 3D point clouds that makes use of invertible flow-based models. The main idea of the method is to treat a point cloud as a probability density in 3D space that is modeled using a cloud-specific neural network. To capture the similarity between point clouds we rely on parameter sharing among networks, with each cloud having only a small embedding vector that defines it. We use invertible flows networks to generate the individual point clouds, and to regularize the embedding vectors. We evaluate the generative capabilities of the model both in qualitative and quantitative manner. |
| Tasks | Point Cloud Generation |
| Published | 2019-10-16 |
| URL | https://arxiv.org/abs/1910.07344v1 |
| https://arxiv.org/pdf/1910.07344v1.pdf | |
| PWC | https://paperswithcode.com/paper/conditional-invertible-flow-for-point-cloud |
| Repo | |
| Framework | |
Adaptive Approximation and Estimation of Deep Neural Network with Intrinsic Dimensionality
| Title | Adaptive Approximation and Estimation of Deep Neural Network with Intrinsic Dimensionality |
| Authors | Ryumei Nakada, Masaaki Imaizumi |
| Abstract | We prove that the performance of deep neural networks (DNNs) is mainly determined by an intrinsic low-dimensionality of covariates. DNNs have been providing an outstanding performance empirically, hence, the theoretical properties of DNNs are actively investigated to understand their mechanism. In particular, the behavior of DNNs with respect to high-dimensional data is one of the most important concerns. However, this issue has not been sufficiently investigated from the aspect of covariates, although high-dimensional data have an intrinsic low dimensionality in practice. In this paper, we derive bounds for an approximation error and an estimation error (i.e., a generalization error) by DNNs with intrinsically low-dimensional covariates. To the end, we utilize the notion of the Minkowski dimension and develop a novel proof technique. Consequently, we show that convergence rates of the errors by DNNs do not depend on the nominal high dimensionality of data, but on its lower intrinsic dimension. We also show that the rate is optimal in the minimax sense. We identify an advantage of DNNs by showing that DNNs can handle a broader class of intrinsic low-dimensional data compared to other adaptive estimators. Finally, we conduct a numerical simulation to validate the theoretical facts. |
| Tasks | |
| Published | 2019-07-04 |
| URL | https://arxiv.org/abs/1907.02177v2 |
| https://arxiv.org/pdf/1907.02177v2.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-approximation-and-estimation-of-deep |
| Repo | |
| Framework | |
A Unified Approach to Robust Mean Estimation
| Title | A Unified Approach to Robust Mean Estimation |
| Authors | Adarsh Prasad, Sivaraman Balakrishnan, Pradeep Ravikumar |
| Abstract | In this paper, we develop connections between two seemingly disparate, but central, models in robust statistics: Huber’s epsilon-contamination model and the heavy-tailed noise model. We provide conditions under which this connection provides near-statistically-optimal estimators. Building on this connection, we provide a simple variant of recent computationally-efficient algorithms for mean estimation in Huber’s model, which given our connection entails that the same efficient sample-pruning based estimators is simultaneously robust to heavy-tailed noise and Huber contamination. Furthermore, we complement our efficient algorithms with statistically-optimal albeit computationally intractable estimators, which are simultaneously optimally robust in both models. We study the empirical performance of our proposed estimators on synthetic datasets, and find that our methods convincingly outperform a variety of practical baselines. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://arxiv.org/abs/1907.00927v1 |
| https://arxiv.org/pdf/1907.00927v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-unified-approach-to-robust-mean-estimation |
| Repo | |
| Framework | |
Multi-Scale RCNN Model for Financial Time-series Classification
| Title | Multi-Scale RCNN Model for Financial Time-series Classification |
| Authors | Liu Guang, Wang Xiaojie, Li Ruifan |
| Abstract | Financial time-series classification (FTC) is extremely valuable for investment management. In past decades, it draws a lot of attention from a wide extent of research areas, especially Artificial Intelligence (AI). Existing researches majorly focused on exploring the effects of the Multi-Scale (MS) property or the Temporal Dependency (TD) within financial time-series. Unfortunately, most previous researches fail to combine these two properties effectively and often fall short of accuracy and profitability. To effectively combine and utilize both properties of financial time-series, we propose a Multi-Scale Temporal Dependent Recurrent Convolutional Neural Network (MSTD-RCNN) for FTC. In the proposed method, the MS features are simultaneously extracted by convolutional units to precisely describe the state of the financial market. Moreover, the TD and complementary across different scales are captured through a Recurrent Neural Network. The proposed method is evaluated on three financial time-series datasets which source from the Chinese stock market. Extensive experimental results indicate that our model achieves the state-of-the-art performance in trend classification and simulated trading, compared with classical and advanced baseline models. |
| Tasks | Time Series, Time Series Classification |
| Published | 2019-11-21 |
| URL | https://arxiv.org/abs/1911.09359v1 |
| https://arxiv.org/pdf/1911.09359v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-scale-rcnn-model-for-financial-time |
| Repo | |
| Framework | |
