Paper Group ANR 228
Scalable Semantic Querying of Text. Using probabilistic programs as proposals. Smart City Development with Urban Transfer Learning. Target Driven Visual Navigation with Hybrid Asynchronous Universal Successor Representations. Towards Robust Training of Neural Networks by Regularizing Adversarial Gradients. A Large-Scale Multi-Institutional Evaluati …
Scalable Semantic Querying of Text
| Title | Scalable Semantic Querying of Text |
| Authors | Xiaolan Wang, Aaron Feng, Behzad Golshan, Alon Halevy, George Mihaila, Hidekazu Oiwa, Wang-Chiew Tan |
| Abstract | We present the KOKO system that takes declarative information extraction to a new level by incorporating advances in natural language processing techniques in its extraction language. KOKO is novel in that its extraction language simultaneously supports conditions on the surface of the text and on the structure of the dependency parse tree of sentences, thereby allowing for more refined extractions. KOKO also supports conditions that are forgiving to linguistic variation of expressing concepts and allows to aggregate evidence from the entire document in order to filter extractions. To scale up, KOKO exploits a multi-indexing scheme and heuristics for efficient extractions. We extensively evaluate KOKO over publicly available text corpora. We show that KOKO indices take up the smallest amount of space, are notably faster and more effective than a number of prior indexing schemes. Finally, we demonstrate KOKO’s scale up on a corpus of 5 million Wikipedia articles. |
| Tasks | |
| Published | 2018-05-03 |
| URL | http://arxiv.org/abs/1805.01083v1 |
| http://arxiv.org/pdf/1805.01083v1.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-semantic-querying-of-text |
| Repo | |
| Framework | |
Using probabilistic programs as proposals
| Title | Using probabilistic programs as proposals |
| Authors | Marco F. Cusumano-Towner, Vikash K. Mansinghka |
| Abstract | Monte Carlo inference has asymptotic guarantees, but can be slow when using generic proposals. Handcrafted proposals that rely on user knowledge about the posterior distribution can be efficient, but are difficult to derive and implement. This paper proposes to let users express their posterior knowledge in the form of proposal programs, which are samplers written in probabilistic programming languages. One strategy for writing good proposal programs is to combine domain-specific heuristic algorithms with neural network models. The heuristics identify high probability regions, and the neural networks model the posterior uncertainty around the outputs of the algorithm. Proposal programs can be used as proposal distributions in importance sampling and Metropolis-Hastings samplers without sacrificing asymptotic consistency, and can be optimized offline using inference compilation. Support for optimizing and using proposal programs is easily implemented in a sampling-based probabilistic programming runtime. The paper illustrates the proposed technique with a proposal program that combines RANSAC and neural networks to accelerate inference in a Bayesian linear regression with outliers model. |
| Tasks | Probabilistic Programming |
| Published | 2018-01-11 |
| URL | http://arxiv.org/abs/1801.03612v2 |
| http://arxiv.org/pdf/1801.03612v2.pdf | |
| PWC | https://paperswithcode.com/paper/using-probabilistic-programs-as-proposals |
| Repo | |
| Framework | |
Smart City Development with Urban Transfer Learning
| Title | Smart City Development with Urban Transfer Learning |
| Authors | Leye Wang, Bin Guo, Qiang Yang |
| Abstract | Nowadays, the smart city development levels of different cities are still unbalanced. For a large number of cities which just started development, the governments will face a critical cold-start problem: ‘how to develop a new smart city service with limited data?'. To address this problem, transfer learning can be leveraged to accelerate the smart city development, which we term the urban transfer learning paradigm. This article investigates the common process of urban transfer learning, aiming to provide city planners and relevant practitioners with guidelines on how to apply this novel learning paradigm. Our guidelines include common transfer strategies to take, general steps to follow, and case studies in public safety, transportation management, etc. We also summarize a few research opportunities and expect this article can attract more researchers to study urban transfer learning. |
| Tasks | Transfer Learning |
| Published | 2018-08-05 |
| URL | http://arxiv.org/abs/1808.01552v2 |
| http://arxiv.org/pdf/1808.01552v2.pdf | |
| PWC | https://paperswithcode.com/paper/smart-city-development-with-urban-transfer |
| Repo | |
| Framework | |
Target Driven Visual Navigation with Hybrid Asynchronous Universal Successor Representations
| Title | Target Driven Visual Navigation with Hybrid Asynchronous Universal Successor Representations |
| Authors | Shamane Siriwardhana, Rivindu Weerasekera, Suranga Nanayakkara |
| Abstract | Being able to navigate to a target with minimal supervision and prior knowledge is critical to creating human-like assistive agents. Prior work on map-based and map-less approaches have limited generalizability. In this paper, we present a novel approach, Hybrid Asynchronous Universal Successor Representations (HAUSR), which overcomes the problem of generalizability to new goals by adapting recent work on Universal Successor Representations with Asynchronous Actor-Critic Agents. We show that the agent was able to successfully reach novel goals and we were able to quickly fine-tune the network for adapting to new scenes. This opens up novel application scenarios where intelligent agents could learn from and adapt to a wide range of environments with minimal human input. |
| Tasks | Visual Navigation |
| Published | 2018-11-27 |
| URL | http://arxiv.org/abs/1811.11312v1 |
| http://arxiv.org/pdf/1811.11312v1.pdf | |
| PWC | https://paperswithcode.com/paper/target-driven-visual-navigation-with-hybrid |
| Repo | |
| Framework | |
Towards Robust Training of Neural Networks by Regularizing Adversarial Gradients
| Title | Towards Robust Training of Neural Networks by Regularizing Adversarial Gradients |
| Authors | Fuxun Yu, Zirui Xu, Yanzhi Wang, Chenchen Liu, Xiang Chen |
| Abstract | In recent years, neural networks have demonstrated outstanding effectiveness in a large amount of applications.However, recent works have shown that neural networks are susceptible to adversarial examples, indicating possible flaws intrinsic to the network structures. To address this problem and improve the robustness of neural networks, we investigate the fundamental mechanisms behind adversarial examples and propose a novel robust training method via regulating adversarial gradients. The regulation effectively squeezes the adversarial gradients of neural networks and significantly increases the difficulty of adversarial example generation.Without any adversarial example involved, the robust training method could generate naturally robust networks, which are near-immune to various types of adversarial examples. Experiments show the naturally robust networks can achieve optimal accuracy against Fast Gradient Sign Method (FGSM) and C&W attacks on MNIST, Cifar10, and Google Speech Command dataset. Moreover, our proposed method also provides neural networks with consistent robustness against transferable attacks. |
| Tasks | |
| Published | 2018-05-23 |
| URL | http://arxiv.org/abs/1805.09370v2 |
| http://arxiv.org/pdf/1805.09370v2.pdf | |
| PWC | https://paperswithcode.com/paper/towards-robust-training-of-neural-networks-by |
| Repo | |
| Framework | |
A Large-Scale Multi-Institutional Evaluation of Advanced Discrimination Algorithms for Buried Threat Detection in Ground Penetrating Radar
| Title | A Large-Scale Multi-Institutional Evaluation of Advanced Discrimination Algorithms for Buried Threat Detection in Ground Penetrating Radar |
| Authors | Jordan M. Malof, Daniel Reichman, Andrew Karem, Hichem Frigui, Dominic K. C. Ho, Joseph N. Wilson, Wen-Hsiung Lee, William Cummings, Leslie M. Collins |
| Abstract | In this paper we consider the development of algorithms for the automatic detection of buried threats using ground penetrating radar (GPR) measurements. GPR is one of the most studied and successful modalities for automatic buried threat detection (BTD), and a large variety of BTD algorithms have been proposed for it. Despite this, large-scale comparisons of GPR-based BTD algorithms are rare in the literature. In this work we report the results of a multi-institutional effort to develop advanced buried threat detection algorithms for a real-world GPR BTD system. The effort involved five institutions with substantial experience with the development of GPR-based BTD algorithms. In this paper we report the technical details of the advanced algorithms submitted by each institution, representing their latest technical advances, and many state-of-the-art GPR-based BTD algorithms. We also report the results of evaluating the algorithms from each institution on the large experimental dataset used for development. The experimental dataset comprised 120,000 m^2 of GPR data using surface area, from 13 different lanes across two US test sites. The data was collected using a vehicle-mounted GPR system, the variants of which have supplied data for numerous publications. Using these results, we identify the most successful and common processing strategies among the submitted algorithms, and make recommendations for GPR-based BTD algorithm design. |
| Tasks | |
| Published | 2018-03-10 |
| URL | http://arxiv.org/abs/1803.03729v2 |
| http://arxiv.org/pdf/1803.03729v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-large-scale-multi-institutional-evaluation |
| Repo | |
| Framework | |
Research Issues in Mining User Behavioral Rules for Context-Aware Intelligent Mobile Applications
| Title | Research Issues in Mining User Behavioral Rules for Context-Aware Intelligent Mobile Applications |
| Authors | Iqbal H. Sarker |
| Abstract | Context-awareness in smart mobile applications is a growing area of study, because of it’s intelligence in the applications. In order to build context-aware intelligent applications, mining contextual behavioral rules of individual smartphone users utilizing their phone log data is the key. However, to mine these rules, a number of issues, such as the quality of smartphone data, understanding the relevancy of contexts, discretization of continuous contextual data, discovery of useful behavioral rules of individuals and their ordering, knowledge-based interactive post-mining for semantic understanding, and dynamic updating and management of rules according to their present behavior, are investigated. In this paper, we briefly discuss these issues and their potential solution directions for mining individuals’ behavioral rules, for the purpose of building various context-aware intelligent mobile applications. We also summarize a number of real-life rule-based applications that intelligently assist individual smartphone users according to their behavioral rules in their daily activities. |
| Tasks | |
| Published | 2018-10-30 |
| URL | http://arxiv.org/abs/1810.12692v1 |
| http://arxiv.org/pdf/1810.12692v1.pdf | |
| PWC | https://paperswithcode.com/paper/research-issues-in-mining-user-behavioral |
| Repo | |
| Framework | |
An Interpretable Generative Model for Handwritten Digit Image Synthesis
| Title | An Interpretable Generative Model for Handwritten Digit Image Synthesis |
| Authors | Yao Zhu, Saksham Suri, Pranav Kulkarni, Yueru Chen, Jiali Duan, C. -C. Jay Kuo |
| Abstract | An interpretable generative model for handwritten digits synthesis is proposed in this work. Modern image generative models, such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), are trained by backpropagation (BP). The training process is complex and the underlying mechanism is difficult to explain. We propose an interpretable multi-stage PCA method to achieve the same goal and use handwritten digit images synthesis as an illustrative example. First, we derive principal-component-analysis-based (PCA-based) transform kernels at each stage based on the covariance of its inputs. This results in a sequence of transforms that convert input images of correlated pixels to spectral vectors of uncorrelated components. In other words, it is a whitening process. Then, we can synthesize an image based on random vectors and multi-stage transform kernels through a coloring process. The generative model is a feedforward (FF) design since no BP is used in model parameter determination. Its design complexity is significantly lower, and the whole design process is explainable. Finally, we design an FF generative model using the MNIST dataset, compare synthesis results with those obtained by state-of-the-art GAN and VAE methods, and show that the proposed generative model achieves comparable performance. |
| Tasks | Handwritten Digit Image Synthesis, Image Generation |
| Published | 2018-11-11 |
| URL | http://arxiv.org/abs/1811.04507v1 |
| http://arxiv.org/pdf/1811.04507v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-interpretable-generative-model-for |
| Repo | |
| Framework | |
Learning One-hidden-layer Neural Networks under General Input Distributions
| Title | Learning One-hidden-layer Neural Networks under General Input Distributions |
| Authors | Weihao Gao, Ashok Vardhan Makkuva, Sewoong Oh, Pramod Viswanath |
| Abstract | Significant advances have been made recently on training neural networks, where the main challenge is in solving an optimization problem with abundant critical points. However, existing approaches to address this issue crucially rely on a restrictive assumption: the training data is drawn from a Gaussian distribution. In this paper, we provide a novel unified framework to design loss functions with desirable landscape properties for a wide range of general input distributions. On these loss functions, remarkably, stochastic gradient descent theoretically recovers the true parameters with global initializations and empirically outperforms the existing approaches. Our loss function design bridges the notion of score functions with the topic of neural network optimization. Central to our approach is the task of estimating the score function from samples, which is of basic and independent interest to theoretical statistics. Traditional estimation methods (example: kernel based) fail right at the outset; we bring statistical methods of local likelihood to design a novel estimator of score functions, that provably adapts to the local geometry of the unknown density. |
| Tasks | |
| Published | 2018-10-09 |
| URL | http://arxiv.org/abs/1810.04133v2 |
| http://arxiv.org/pdf/1810.04133v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-one-hidden-layer-neural-networks |
| Repo | |
| Framework | |
Extremely Fast Decision Tree
| Title | Extremely Fast Decision Tree |
| Authors | Chaitanya Manapragada, Geoff Webb, Mahsa Salehi |
| Abstract | We introduce a novel incremental decision tree learning algorithm, Hoeffding Anytime Tree, that is statistically more efficient than the current state-of-the-art, Hoeffding Tree. We demonstrate that an implementation of Hoeffding Anytime Tree—“Extremely Fast Decision Tree”, a minor modification to the MOA implementation of Hoeffding Tree—obtains significantly superior prequential accuracy on most of the largest classification datasets from the UCI repository. Hoeffding Anytime Tree produces the asymptotic batch tree in the limit, is naturally resilient to concept drift, and can be used as a higher accuracy replacement for Hoeffding Tree in most scenarios, at a small additional computational cost. |
| Tasks | |
| Published | 2018-02-24 |
| URL | http://arxiv.org/abs/1802.08780v1 |
| http://arxiv.org/pdf/1802.08780v1.pdf | |
| PWC | https://paperswithcode.com/paper/extremely-fast-decision-tree |
| Repo | |
| Framework | |
New Movement and Transformation Principle of Fuzzy Reasoning and Its Application to Fuzzy Neural Network
| Title | New Movement and Transformation Principle of Fuzzy Reasoning and Its Application to Fuzzy Neural Network |
| Authors | Chung-Jin Kwak, Son-Il Kwak, Dae-Song Kang, Song-Il Choe, Jin-Ung Kim, Hyok-Gi Chea |
| Abstract | In this paper, we propose a new fuzzy reasoning principle, so called Movement and Transformation Principle(MTP). This Principle is to obtain a new fuzzy reasoning result by Movement and Transformation the consequent fuzzy set in response to the Movement, Transformation, and Movement-Transformation operations between the antecedent fuzzy set and fuzzificated observation information. And then we presented fuzzy modus ponens and fuzzy modus tollens based on MTP. We compare proposed method with Mamdani fuzzy system, Sugeno fuzzy system, Wang distance type fuzzy reasoning method and Hellendoorn functional type method. And then we applied to the learning experiments of the fuzzy neural network based on MTP and compared it with the Sugeno method. Through prediction experiments of fuzzy neural network on the precipitation data and security situation data, learning accuracy and time performance are clearly improved. Consequently we show that our method based on MTP is computationally simple and does not involve nonlinear operations, so it is easy to handle mathematically. |
| Tasks | |
| Published | 2018-11-10 |
| URL | http://arxiv.org/abs/1811.04173v1 |
| http://arxiv.org/pdf/1811.04173v1.pdf | |
| PWC | https://paperswithcode.com/paper/new-movement-and-transformation-principle-of |
| Repo | |
| Framework | |
Does data interpolation contradict statistical optimality?
| Title | Does data interpolation contradict statistical optimality? |
| Authors | Mikhail Belkin, Alexander Rakhlin, Alexandre B. Tsybakov |
| Abstract | We show that learning methods interpolating the training data can achieve optimal rates for the problems of nonparametric regression and prediction with square loss. |
| Tasks | |
| Published | 2018-06-25 |
| URL | http://arxiv.org/abs/1806.09471v1 |
| http://arxiv.org/pdf/1806.09471v1.pdf | |
| PWC | https://paperswithcode.com/paper/does-data-interpolation-contradict |
| Repo | |
| Framework | |
Transfer Learning From Synthetic To Real Images Using Variational Autoencoders For Precise Position Detection
| Title | Transfer Learning From Synthetic To Real Images Using Variational Autoencoders For Precise Position Detection |
| Authors | Tadanobu Inoue, Subhajit Chaudhury, Giovanni De Magistris, Sakyasingha Dasgupta |
| Abstract | Capturing and labeling camera images in the real world is an expensive task, whereas synthesizing labeled images in a simulation environment is easy for collecting large-scale image data. However, learning from only synthetic images may not achieve the desired performance in the real world due to a gap between synthetic and real images. We propose a method that transfers learned detection of an object position from a simulation environment to the real world. This method uses only a significantly limited dataset of real images while leveraging a large dataset of synthetic images using variational autoencoders. Additionally, the proposed method consistently performed well in different lighting conditions, in the presence of other distractor objects, and on different backgrounds. Experimental results showed that it achieved accuracy of 1.5mm to 3.5mm on average. Furthermore, we showed how the method can be used in a real-world scenario like a “pick-and-place” robotic task. |
| Tasks | Transfer Learning |
| Published | 2018-07-04 |
| URL | http://arxiv.org/abs/1807.01990v1 |
| http://arxiv.org/pdf/1807.01990v1.pdf | |
| PWC | https://paperswithcode.com/paper/transfer-learning-from-synthetic-to-real |
| Repo | |
| Framework | |
Neural Aesthetic Image Reviewer
| Title | Neural Aesthetic Image Reviewer |
| Authors | Wenshan Wang, Su Yang, Weishan Zhang, Jiulong Zhang |
| Abstract | Recently, there is a rising interest in perceiving image aesthetics. The existing works deal with image aesthetics as a classification or regression problem. To extend the cognition from rating to reasoning, a deeper understanding of aesthetics should be based on revealing why a high- or low-aesthetic score should be assigned to an image. From such a point of view, we propose a model referred to as Neural Aesthetic Image Reviewer, which can not only give an aesthetic score for an image, but also generate a textual description explaining why the image leads to a plausible rating score. Specifically, we propose two multi-task architectures based on shared aesthetically semantic layers and task-specific embedding layers at a high level for performance improvement on different tasks. To facilitate researches on this problem, we collect the AVA-Reviews dataset, which contains 52,118 images and 312,708 comments in total. Through multi-task learning, the proposed models can rate aesthetic images as well as produce comments in an end-to-end manner. It is confirmed that the proposed models outperform the baselines according to the performance evaluation on the AVA-Reviews dataset. Moreover, we demonstrate experimentally that our model can generate textual reviews related to aesthetics, which are consistent with human perception. |
| Tasks | Multi-Task Learning |
| Published | 2018-02-28 |
| URL | http://arxiv.org/abs/1802.10240v1 |
| http://arxiv.org/pdf/1802.10240v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-aesthetic-image-reviewer |
| Repo | |
| Framework | |
Estimating scale-invariant future in continuous time
| Title | Estimating scale-invariant future in continuous time |
| Authors | Zoran Tiganj, Samuel J. Gershman, Per B. Sederberg, Marc W. Howard |
| Abstract | Natural learners must compute an estimate of future outcomes that follow from a stimulus in continuous time. Widely used reinforcement learning algorithms discretize continuous time and estimate either transition functions from one step to the next (model-based algorithms) or a scalar value of exponentially-discounted future reward using the Bellman equation (model-free algorithms). An important drawback of model-based algorithms is that computational cost grows linearly with the amount of time to be simulated. On the other hand, an important drawback of model-free algorithms is the need to select a time-scale required for exponential discounting. We present a computational mechanism, developed based on work in psychology and neuroscience, for computing a scale-invariant timeline of future outcomes. This mechanism efficiently computes an estimate of inputs as a function of future time on a logarithmically-compressed scale, and can be used to generate a scale-invariant power-law-discounted estimate of expected future reward. The representation of future time retains information about what will happen when. The entire timeline can be constructed in a single parallel operation which generates concrete behavioral and neural predictions. This computational mechanism could be incorporated into future reinforcement learning algorithms. |
| Tasks | |
| Published | 2018-02-18 |
| URL | http://arxiv.org/abs/1802.06426v3 |
| http://arxiv.org/pdf/1802.06426v3.pdf | |
| PWC | https://paperswithcode.com/paper/estimating-scale-invariant-future-in |
| Repo | |
| Framework | |
