Paper Group ANR 676
Declarative Statistics. When can Multi-Site Datasets be Pooled for Regression? Hypothesis Tests, $\ell_2$-consistency and Neuroscience Applications. Happy Travelers Take Big Pictures: A Psychological Study with Machine Learning and Big Data. Learning to Learn Image Classifiers with Visual Analogy. A Deep Learning Approach for Blind Drift Calibratio …
Declarative Statistics
| Title | Declarative Statistics |
| Authors | Roberto Rossi, Özgür Akgün, Steven Prestwich, S. Armagan Tarim |
| Abstract | In this work we introduce declarative statistics, a suite of declarative modelling tools for statistical analysis. Statistical constraints represent the key building block of declarative statistics. First, we introduce a range of relevant counting and matrix constraints and associated decompositions, some of which novel, that are instrumental in the design of statistical constraints. Second, we introduce a selection of novel statistical constraints and associated decompositions, which constitute a self-contained toolbox that can be used to tackle a wide range of problems typically encountered by statisticians. Finally, we deploy these statistical constraints to a wide range of application areas drawn from classical statistics and we contrast our framework against established practices. |
| Tasks | |
| Published | 2017-08-06 |
| URL | http://arxiv.org/abs/1708.01829v2 |
| http://arxiv.org/pdf/1708.01829v2.pdf | |
| PWC | https://paperswithcode.com/paper/declarative-statistics |
| Repo | |
| Framework | |
When can Multi-Site Datasets be Pooled for Regression? Hypothesis Tests, $\ell_2$-consistency and Neuroscience Applications
| Title | When can Multi-Site Datasets be Pooled for Regression? Hypothesis Tests, $\ell_2$-consistency and Neuroscience Applications |
| Authors | Hao Henry Zhou, Yilin Zhang, Vamsi K. Ithapu, Sterling C. Johnson, Grace Wahba, Vikas Singh |
| Abstract | Many studies in biomedical and health sciences involve small sample sizes due to logistic or financial constraints. Often, identifying weak (but scientifically interesting) associations between a set of predictors and a response necessitates pooling datasets from multiple diverse labs or groups. While there is a rich literature in statistical machine learning to address distributional shifts and inference in multi-site datasets, it is less clear ${\it when}$ such pooling is guaranteed to help (and when it does not) – independent of the inference algorithms we use. In this paper, we present a hypothesis test to answer this question, both for classical and high dimensional linear regression. We precisely identify regimes where pooling datasets across multiple sites is sensible, and how such policy decisions can be made via simple checks executable on each site before any data transfer ever happens. With a focus on Alzheimer’s disease studies, we present empirical results showing that in regimes suggested by our analysis, pooling a local dataset with data from an international study improves power. |
| Tasks | |
| Published | 2017-09-02 |
| URL | http://arxiv.org/abs/1709.00640v1 |
| http://arxiv.org/pdf/1709.00640v1.pdf | |
| PWC | https://paperswithcode.com/paper/when-can-multi-site-datasets-be-pooled-for |
| Repo | |
| Framework | |
Happy Travelers Take Big Pictures: A Psychological Study with Machine Learning and Big Data
| Title | Happy Travelers Take Big Pictures: A Psychological Study with Machine Learning and Big Data |
| Authors | Xuefeng Liang, Lixin Fan, Yuen Peng Loh, Yang Liu, Song Tong |
| Abstract | In psychology, theory-driven researches are usually conducted with extensive laboratory experiments, yet rarely tested or disproved with big data. In this paper, we make use of 418K travel photos with traveler ratings to test the influential “broaden-and-build” theory, that suggests positive emotions broaden one’s visual attention. The core hypothesis examined in this study is that positive emotion is associated with a wider attention, hence highly-rated sites would trigger wide-angle photographs. By analyzing travel photos, we find a strong correlation between a preference for wide-angle photos and the high rating of tourist sites on TripAdvisor. We are able to carry out this analysis through the use of deep learning algorithms to classify the photos into wide and narrow angles, and present this study as an exemplar of how big data and deep learning can be used to test laboratory findings in the wild. |
| Tasks | |
| Published | 2017-09-22 |
| URL | http://arxiv.org/abs/1709.07584v1 |
| http://arxiv.org/pdf/1709.07584v1.pdf | |
| PWC | https://paperswithcode.com/paper/happy-travelers-take-big-pictures-a |
| Repo | |
| Framework | |
Learning to Learn Image Classifiers with Visual Analogy
| Title | Learning to Learn Image Classifiers with Visual Analogy |
| Authors | Linjun Zhou, Peng Cui, Shiqiang Yang, Wenwu Zhu, Qi Tian |
| Abstract | Humans are far better learners who can learn a new concept very fast with only a few samples compared with machines. The plausible mystery making the difference is two fundamental learning mechanisms: learning to learn and learning by analogy. In this paper, we attempt to investigate a new human-like learning method by organically combining these two mechanisms. In particular, we study how to generalize the classification parameters from previously learned concepts to a new concept. we first propose a novel Visual Analogy Graph Embedded Regression (VAGER) model to jointly learn a low-dimensional embedding space and a linear mapping function from the embedding space to classification parameters for base classes. We then propose an out-of-sample embedding method to learn the embedding of a new class represented by a few samples through its visual analogy with base classes and derive the classification parameters for the new class. We conduct extensive experiments on ImageNet dataset and the results show that our method could consistently and significantly outperform state-of-the-art baselines. |
| Tasks | Image Classification |
| Published | 2017-10-17 |
| URL | http://arxiv.org/abs/1710.06177v2 |
| http://arxiv.org/pdf/1710.06177v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-learn-image-classifiers-with |
| Repo | |
| Framework | |
A Deep Learning Approach for Blind Drift Calibration of Sensor Networks
| Title | A Deep Learning Approach for Blind Drift Calibration of Sensor Networks |
| Authors | Yuzhi Wang, Anqi Yang, Xiaoming Chen, Pengjun Wang, Yu Wang, Huazhong Yang |
| Abstract | Temporal drift of sensory data is a severe problem impacting the data quality of wireless sensor networks (WSNs). With the proliferation of large-scale and long-term WSNs, it is becoming more important to calibrate sensors when the ground truth is unavailable. This problem is called “blind calibration”. In this paper, we propose a novel deep learning method named projection-recovery network (PRNet) to blindly calibrate sensor measurements online. The PRNet first projects the drifted data to a feature space, and uses a powerful deep convolutional neural network to recover the estimated drift-free measurements. We deploy a 24-sensor testbed and provide comprehensive empirical evidence showing that the proposed method significantly improves the sensing accuracy and drifted sensor detection. Compared with previous methods, PRNet can calibrate 2x of drifted sensors at the recovery rate of 80% under the same level of accuracy requirement. We also provide helpful insights for designing deep neural networks for sensor calibration. We hope our proposed simple and effective approach will serve as a solid baseline in blind drift calibration of sensor networks. |
| Tasks | Calibration |
| Published | 2017-06-16 |
| URL | http://arxiv.org/abs/1707.03682v1 |
| http://arxiv.org/pdf/1707.03682v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-learning-approach-for-blind-drift |
| Repo | |
| Framework | |
Reservoir Computing and Extreme Learning Machines using Pairs of Cellular Automata Rules
| Title | Reservoir Computing and Extreme Learning Machines using Pairs of Cellular Automata Rules |
| Authors | Nathan McDonald |
| Abstract | A framework for implementing reservoir computing (RC) and extreme learning machines (ELMs), two types of artificial neural networks, based on 1D elementary Cellular Automata (CA) is presented, in which two separate CA rules explicitly implement the minimum computational requirements of the reservoir layer: hyperdimensional projection and short-term memory. CAs are cell-based state machines, which evolve in time in accordance with local rules based on a cells current state and those of its neighbors. Notably, simple single cell shift rules as the memory rule in a fixed edge CA afforded reasonable success in conjunction with a variety of projection rules, potentially significantly reducing the optimal solution search space. Optimal iteration counts for the CA rule pairs can be estimated for some tasks based upon the category of the projection rule. Initial results support future hardware realization, where CAs potentially afford orders of magnitude reduction in size, weight, and power (SWaP) requirements compared with floating point RC implementations. |
| Tasks | |
| Published | 2017-03-16 |
| URL | http://arxiv.org/abs/1703.05807v1 |
| http://arxiv.org/pdf/1703.05807v1.pdf | |
| PWC | https://paperswithcode.com/paper/reservoir-computing-and-extreme-learning |
| Repo | |
| Framework | |
Trigger for the SoLid Reactor Antineutrino Experiment
| Title | Trigger for the SoLid Reactor Antineutrino Experiment |
| Authors | Lukas On Arnold |
| Abstract | SoLid, located at SCK-CEN in Mol, Belgium, is a reactor antineutrino experiment at a very short baseline of 5.5 – 10m aiming at the search for sterile neutrinos and for high precision measurement of the neutrino energy spectrum of Uranium-235. It uses a novel approach using Lithium-6 sheets and PVT cubes as scintillators for tagging the Inverse Beta-Decay products (neutron and positron). Being located overground and close to the BR2 research reactor, the experiment faces a large amount of backgrounds. Efficient real-time background and noise rejection is essential in order to increase the signal-background ratio for precise oscillation measurement and decrease data production to a rate which can be handled by the online software. Therefore, a reliable distinction between the neutrons and background signals is crucial. This can be performed online with a dedicated firmware trigger. A peak counting algorithm and an algorithm measuring time over threshold have been identified as performing well both in terms of efficiency and fake rate, and have been implemented onto FPGA. |
| Tasks | |
| Published | 2017-04-16 |
| URL | http://arxiv.org/abs/1704.04706v2 |
| http://arxiv.org/pdf/1704.04706v2.pdf | |
| PWC | https://paperswithcode.com/paper/trigger-for-the-solid-reactor-antineutrino |
| Repo | |
| Framework | |
SRPGAN: Perceptual Generative Adversarial Network for Single Image Super Resolution
| Title | SRPGAN: Perceptual Generative Adversarial Network for Single Image Super Resolution |
| Authors | Bingzhe Wu, Haodong Duan, Zhichao Liu, Guangyu Sun |
| Abstract | Single image super resolution (SISR) is to reconstruct a high resolution image from a single low resolution image. The SISR task has been a very attractive research topic over the last two decades. In recent years, convolutional neural network (CNN) based models have achieved great performance on SISR task. Despite the breakthroughs achieved by using CNN models, there are still some problems remaining unsolved, such as how to recover high frequency details of high resolution images. Previous CNN based models always use a pixel wise loss, such as l2 loss. Although the high resolution images constructed by these models have high peak signal-to-noise ratio (PSNR), they often tend to be blurry and lack high-frequency details, especially at a large scaling factor. In this paper, we build a super resolution perceptual generative adversarial network (SRPGAN) framework for SISR tasks. In the framework, we propose a robust perceptual loss based on the discriminator of the built SRPGAN model. We use the Charbonnier loss function to build the content loss and combine it with the proposed perceptual loss and the adversarial loss. Compared with other state-of-the-art methods, our method has demonstrated great ability to construct images with sharp edges and rich details. We also evaluate our method on different benchmarks and compare it with previous CNN based methods. The results show that our method can achieve much higher structural similarity index (SSIM) scores on most of the benchmarks than the previous state-of-art methods. |
| Tasks | Image Super-Resolution, Super-Resolution |
| Published | 2017-12-16 |
| URL | http://arxiv.org/abs/1712.05927v2 |
| http://arxiv.org/pdf/1712.05927v2.pdf | |
| PWC | https://paperswithcode.com/paper/srpgan-perceptual-generative-adversarial |
| Repo | |
| Framework | |
Dynamic Stochastic Approximation for Multi-stage Stochastic Optimization
| Title | Dynamic Stochastic Approximation for Multi-stage Stochastic Optimization |
| Authors | Guanghui Lan, Zhiqiang Zhou |
| Abstract | In this paper, we consider multi-stage stochastic optimization problems with convex objectives and conic constraints at each stage. We present a new stochastic first-order method, namely the dynamic stochastic approximation (DSA) algorithm, for solving these types of stochastic optimization problems. We show that DSA can achieve an optimal ${\cal O}(1/\epsilon^4)$ rate of convergence in terms of the total number of required scenarios when applied to a three-stage stochastic optimization problem. We further show that this rate of convergence can be improved to ${\cal O}(1/\epsilon^2)$ when the objective function is strongly convex. We also discuss variants of DSA for solving more general multi-stage stochastic optimization problems with the number of stages $T > 3$. The developed DSA algorithms only need to go through the scenario tree once in order to compute an $\epsilon$-solution of the multi-stage stochastic optimization problem. As a result, the memory required by DSA only grows linearly with respect to the number of stages. To the best of our knowledge, this is the first time that stochastic approximation type methods are generalized for multi-stage stochastic optimization with $T \ge 3$. |
| Tasks | Stochastic Optimization |
| Published | 2017-07-11 |
| URL | https://arxiv.org/abs/1707.03324v2 |
| https://arxiv.org/pdf/1707.03324v2.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-stochastic-approximation-for-multi |
| Repo | |
| Framework | |
Genetic Algorithms for Evolving Computer Chess Programs
| Title | Genetic Algorithms for Evolving Computer Chess Programs |
| Authors | Eli David, H. Jaap van den Herik, Moshe Koppel, Nathan S. Netanyahu |
| Abstract | This paper demonstrates the use of genetic algorithms for evolving: 1) a grandmaster-level evaluation function, and 2) a search mechanism for a chess program, the parameter values of which are initialized randomly. The evaluation function of the program is evolved by learning from databases of (human) grandmaster games. At first, the organisms are evolved to mimic the behavior of human grandmasters, and then these organisms are further improved upon by means of coevolution. The search mechanism is evolved by learning from tactical test suites. Our results show that the evolved program outperforms a two-time world computer chess champion and is at par with the other leading computer chess programs. |
| Tasks | |
| Published | 2017-11-21 |
| URL | http://arxiv.org/abs/1711.08337v1 |
| http://arxiv.org/pdf/1711.08337v1.pdf | |
| PWC | https://paperswithcode.com/paper/genetic-algorithms-for-evolving-computer |
| Repo | |
| Framework | |
Métodos de Otimização Combinatória Aplicados ao Problema de Compressão MultiFrases
| Title | Métodos de Otimização Combinatória Aplicados ao Problema de Compressão MultiFrases |
| Authors | Elvys Linhares Pontes, Thiago Gouveia da Silva, Andréa Carneiro Linhares, Juan-Manuel Torres-Moreno, Stéphane Huet |
| Abstract | The Internet has led to a dramatic increase in the amount of available information. In this context, reading and understanding this flow of information have become costly tasks. In the last years, to assist people to understand textual data, various Natural Language Processing (NLP) applications based on Combinatorial Optimization have been devised. However, for Multi-Sentences Compression (MSC), method which reduces the sentence length without removing core information, the insertion of optimization methods requires further study to improve the performance of MSC. This article describes a method for MSC using Combinatorial Optimization and Graph Theory to generate more informative sentences while maintaining their grammaticality. An experiment led on a corpus of 40 clusters of sentences shows that our system has achieved a very good quality and is better than the state-of-the-art. |
| Tasks | Combinatorial Optimization |
| Published | 2017-03-19 |
| URL | http://arxiv.org/abs/1703.06501v1 |
| http://arxiv.org/pdf/1703.06501v1.pdf | |
| PWC | https://paperswithcode.com/paper/metodos-de-otimizacao-combinatoria-aplicados |
| Repo | |
| Framework | |
Comparative Analysis of Open Source Frameworks for Machine Learning with Use Case in Single-Threaded and Multi-Threaded Modes
| Title | Comparative Analysis of Open Source Frameworks for Machine Learning with Use Case in Single-Threaded and Multi-Threaded Modes |
| Authors | Yuriy Kochura, Sergii Stirenko, Anis Rojbi, Oleg Alienin, Michail Novotarskiy, Yuri Gordienko |
| Abstract | The basic features of some of the most versatile and popular open source frameworks for machine learning (TensorFlow, Deep Learning4j, and H2O) are considered and compared. Their comparative analysis was performed and conclusions were made as to the advantages and disadvantages of these platforms. The performance tests for the de facto standard MNIST data set were carried out on H2O framework for deep learning algorithms designed for CPU and GPU platforms for single-threaded and multithreaded modes of operation. |
| Tasks | |
| Published | 2017-06-07 |
| URL | http://arxiv.org/abs/1706.02248v1 |
| http://arxiv.org/pdf/1706.02248v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparative-analysis-of-open-source |
| Repo | |
| Framework | |
Deep Learning Based Regression and Multi-class Models for Acute Oral Toxicity Prediction with Automatic Chemical Feature Extraction
| Title | Deep Learning Based Regression and Multi-class Models for Acute Oral Toxicity Prediction with Automatic Chemical Feature Extraction |
| Authors | Youjun Xu, Jianfeng Pei, Luhua Lai |
| Abstract | For quantitative structure-property relationship (QSPR) studies in chemoinformatics, it is important to get interpretable relationship between chemical properties and chemical features. However, the predictive power and interpretability of QSPR models are usually two different objectives that are difficult to achieve simultaneously. A deep learning architecture using molecular graph encoding convolutional neural networks (MGE-CNN) provided a universal strategy to construct interpretable QSPR models with high predictive power. Instead of using application-specific preset molecular descriptors or fingerprints, the models can be resolved using raw and pertinent features without manual intervention or selection. In this study, we developed acute oral toxicity (AOT) models of compounds using the MGE-CNN architecture as a case study. Three types of high-level predictive models: regression model (deepAOT-R), multi-classification model (deepAOT-C) and multi-task model (deepAOT-CR) for AOT evaluation were constructed. These models highly outperformed previously reported models. For the two external datasets containing 1673 (test set I) and 375 (test set II) compounds, the R2 and mean absolute error (MAE) of deepAOT-R on the test set I were 0.864 and 0.195, and the prediction accuracy of deepAOT-C was 95.5% and 96.3% on the test set I and II, respectively. The two external prediction accuracy of deepAOT-CR is 95.0% and 94.1%, while the R2 and MAE are 0.861 and 0.204 for test set I, respectively. |
| Tasks | |
| Published | 2017-04-16 |
| URL | http://arxiv.org/abs/1704.04718v3 |
| http://arxiv.org/pdf/1704.04718v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-based-regression-and-multi |
| Repo | |
| Framework | |
Storytelling Agents with Personality and Adaptivity
| Title | Storytelling Agents with Personality and Adaptivity |
| Authors | Zhichao Hu, Marilyn A. Walker, Michael Neff, Jean E. Fox Tree |
| Abstract | We explore the expression of personality and adaptivity through the gestures of virtual agents in a storytelling task. We conduct two experiments using four different dialogic stories. We manipulate agent personality on the extraversion scale, whether the agents adapt to one another in their gestural performance and agent gender. Our results show that subjects are able to perceive the intended variation in extraversion between different virtual agents, independently of the story they are telling and the gender of the agent. A second study shows that subjects also prefer adaptive to nonadaptive virtual agents. |
| Tasks | |
| Published | 2017-09-04 |
| URL | http://arxiv.org/abs/1709.01188v1 |
| http://arxiv.org/pdf/1709.01188v1.pdf | |
| PWC | https://paperswithcode.com/paper/storytelling-agents-with-personality-and |
| Repo | |
| Framework | |
How well does your sampler really work?
| Title | How well does your sampler really work? |
| Authors | Ryan Turner, Brady Neal |
| Abstract | We present a new data-driven benchmark system to evaluate the performance of new MCMC samplers. Taking inspiration from the COCO benchmark in optimization, we view this task as having critical importance to machine learning and statistics given the rate at which new samplers are proposed. The common hand-crafted examples to test new samplers are unsatisfactory; we take a meta-learning-like approach to generate benchmark examples from a large corpus of data sets and models. Surrogates of posteriors found in real problems are created using highly flexible density models including modern neural network based approaches. We provide new insights into the real effective sample size of various samplers per unit time and the estimation efficiency of the samplers per sample. Additionally, we provide a meta-analysis to assess the predictive utility of various MCMC diagnostics and perform a nonparametric regression to combine them. |
| Tasks | Meta-Learning |
| Published | 2017-12-16 |
| URL | http://arxiv.org/abs/1712.06006v1 |
| http://arxiv.org/pdf/1712.06006v1.pdf | |
| PWC | https://paperswithcode.com/paper/how-well-does-your-sampler-really-work |
| Repo | |
| Framework | |
