May 7, 2019

2715 words 13 mins read

Paper Group ANR 101

Learning and Tuning Meta-heuristics in Plan Space Planning. Diet2Vec: Multi-scale analysis of massive dietary data. Supervised Syntax-based Alignment between English Sentences and Abstract Meaning Representation Graphs. Evolutionary computation for multicomponent problems: opportunities and future directions. Fast estimation of approximate matrix r …

Learning and Tuning Meta-heuristics in Plan Space Planning


Title	Learning and Tuning Meta-heuristics in Plan Space Planning
Authors	Shashank Shekhar, Deepak Khemani
Abstract	In recent years, the planning community has observed that techniques for learning heuristic functions have yielded improvements in performance. One approach is to use offline learning to learn predictive models from existing heuristics in a domain dependent manner. These learned models are deployed as new heuristic functions. The learned models can in turn be tuned online using a domain independent error correction approach to further enhance their informativeness. The online tuning approach is domain independent but instance specific, and contributes to improved performance for individual instances as planning proceeds. Consequently it is more effective in larger problems. In this paper, we mention two approaches applicable in Partial Order Causal Link (POCL) Planning that is also known as Plan Space Planning. First, we endeavor to enhance the performance of a POCL planner by giving an algorithm for supervised learning. Second, we then discuss an online error minimization approach in POCL framework to minimize the step-error associated with the offline learned models thus enhancing their informativeness. Our evaluation shows that the learning approaches scale up the performance of the planner over standard benchmarks, specially for larger problems.
Tasks
Published	2016-01-27
URL	http://arxiv.org/abs/1601.07483v3
PDF	http://arxiv.org/pdf/1601.07483v3.pdf
PWC	https://paperswithcode.com/paper/learning-and-tuning-meta-heuristics-in-plan
Repo
Framework

Diet2Vec: Multi-scale analysis of massive dietary data


Title	Diet2Vec: Multi-scale analysis of massive dietary data
Authors	Wesley Tansey, Edward W. Lowe Jr., James G. Scott
Abstract	Smart phone apps that enable users to easily track their diets have become widespread in the last decade. This has created an opportunity to discover new insights into obesity and weight loss by analyzing the eating habits of the users of such apps. In this paper, we present diet2vec: an approach to modeling latent structure in a massive database of electronic diet journals. Through an iterative contract-and-expand process, our model learns real-valued embeddings of users’ diets, as well as embeddings for individual foods and meals. We demonstrate the effectiveness of our approach on a real dataset of 55K users of the popular diet-tracking app LoseIt\footnote{http://www.loseit.com/}. To the best of our knowledge, this is the largest fine-grained diet tracking study in the history of nutrition and obesity research. Our results suggest that diet2vec finds interpretable results at all levels, discovering intuitive representations of foods, meals, and diets.
Tasks
Published	2016-12-01
URL	http://arxiv.org/abs/1612.00388v1
PDF	http://arxiv.org/pdf/1612.00388v1.pdf
PWC	https://paperswithcode.com/paper/diet2vec-multi-scale-analysis-of-massive
Repo
Framework

Supervised Syntax-based Alignment between English Sentences and Abstract Meaning Representation Graphs


Title	Supervised Syntax-based Alignment between English Sentences and Abstract Meaning Representation Graphs
Authors	Chenhui Chu, Sadao Kurohashi
Abstract	As alignment links are not given between English sentences and Abstract Meaning Representation (AMR) graphs in the AMR annotation, automatic alignment becomes indispensable for training an AMR parser. Previous studies formalize it as a string-to-string problem and solve it in an unsupervised way, which suffers from data sparseness due to the small size of training data for English-AMR alignment. In this paper, we formalize it as a syntax-based alignment problem and solve it in a supervised manner based on syntax trees, which can address the data sparseness problem by generalizing English-AMR tokens to syntax tags. Experiments verify the effectiveness of the proposed method not only for English-AMR alignment, but also for AMR parsing.
Tasks	Amr Parsing
Published	2016-06-07
URL	http://arxiv.org/abs/1606.02126v4
PDF	http://arxiv.org/pdf/1606.02126v4.pdf
PWC	https://paperswithcode.com/paper/supervised-syntax-based-alignment-between
Repo
Framework

Evolutionary computation for multicomponent problems: opportunities and future directions


Title	Evolutionary computation for multicomponent problems: opportunities and future directions
Authors	Mohammad Reza Bonyadi, Zbigniew Michalewicz, Frank Neumann, Markus Wagner
Abstract	Over the past 30 years many researchers in the field of evolutionary computation have put a lot of effort to introduce various approaches for solving hard problems. Most of these problems have been inspired by major industries so that solving them, by providing either optimal or near optimal solution, was of major significance. Indeed, this was a very promising trajectory as advances in these problem-solving approaches could result in adding values to major industries. In this paper we revisit this trajectory to find out whether the attempts that started three decades ago are still aligned with the same goal, as complexities of real-world problems increased significantly. We present some examples of modern real-world problems, discuss why they might be difficult to solve, and whether there is any mismatch between these examples and the problems that are investigated in the evolutionary computation area.
Tasks
Published	2016-06-22
URL	http://arxiv.org/abs/1606.06818v1
PDF	http://arxiv.org/pdf/1606.06818v1.pdf
PWC	https://paperswithcode.com/paper/evolutionary-computation-for-multicomponent
Repo
Framework

Fast estimation of approximate matrix ranks using spectral densities


Title	Fast estimation of approximate matrix ranks using spectral densities
Authors	Shashanka Ubaru, Yousef Saad, Abd-Krim Seghouane
Abstract	In many machine learning and data related applications, it is required to have the knowledge of approximate ranks of large data matrices at hand. In this paper, we present two computationally inexpensive techniques to estimate the approximate ranks of such large matrices. These techniques exploit approximate spectral densities, popular in physics, which are probability density distributions that measure the likelihood of finding eigenvalues of the matrix at a given point on the real line. Integrating the spectral density over an interval gives the eigenvalue count of the matrix in that interval. Therefore the rank can be approximated by integrating the spectral density over a carefully selected interval. Two different approaches are discussed to estimate the approximate rank, one based on Chebyshev polynomials and the other based on the Lanczos algorithm. In order to obtain the appropriate interval, it is necessary to locate a gap between the eigenvalues that correspond to noise and the relevant eigenvalues that contribute to the matrix rank. A method for locating this gap and selecting the interval of integration is proposed based on the plot of the spectral density. Numerical experiments illustrate the performance of these techniques on matrices from typical applications.
Tasks
Published	2016-08-19
URL	http://arxiv.org/abs/1608.05754v1
PDF	http://arxiv.org/pdf/1608.05754v1.pdf
PWC	https://paperswithcode.com/paper/fast-estimation-of-approximate-matrix-ranks
Repo
Framework

Hamiltonian operator for spectral shape analysis


Title	Hamiltonian operator for spectral shape analysis
Authors	Yoni Choukroun, Alon Shtern, Alex Bronstein, Ron Kimmel
Abstract	Many shape analysis methods treat the geometry of an object as a metric space that can be captured by the Laplace-Beltrami operator. In this paper, we propose to adapt the classical Hamiltonian operator from quantum mechanics to the field of shape analysis. To this end we study the addition of a potential function to the Laplacian as a generator for dual spaces in which shape processing is performed. We present a general optimization approach for solving variational problems involving the basis defined by the Hamiltonian using perturbation theory for its eigenvectors. The suggested operator is shown to produce better functional spaces to operate with, as demonstrated on different shape analysis tasks.
Tasks
Published	2016-11-07
URL	http://arxiv.org/abs/1611.01990v2
PDF	http://arxiv.org/pdf/1611.01990v2.pdf
PWC	https://paperswithcode.com/paper/hamiltonian-operator-for-spectral-shape
Repo
Framework

Why Do Urban Legends Go Viral?


Title	Why Do Urban Legends Go Viral?
Authors	Marco Guerini, Carlo Strapparava
Abstract	Urban legends are a genre of modern folklore, consisting of stories about rare and exceptional events, just plausible enough to be believed, which tend to propagate inexorably across communities. In our view, while urban legends represent a form of “sticky” deceptive text, they are marked by a tension between the credible and incredible. They should be credible like a news article and incredible like a fairy tale to go viral. In particular we will focus on the idea that urban legends should mimic the details of news (who, where, when) to be credible, while they should be emotional and readable like a fairy tale to be catchy and memorable. Using NLP tools we will provide a quantitative analysis of these prototypical characteristics. We also lay out some machine learning experiments showing that it is possible to recognize an urban legend using just these simple features.
Tasks
Published	2016-01-22
URL	http://arxiv.org/abs/1601.06081v1
PDF	http://arxiv.org/pdf/1601.06081v1.pdf
PWC	https://paperswithcode.com/paper/why-do-urban-legends-go-viral
Repo
Framework

MarioQA: Answering Questions by Watching Gameplay Videos


Title	MarioQA: Answering Questions by Watching Gameplay Videos
Authors	Jonghwan Mun, Paul Hongsuck Seo, Ilchae Jung, Bohyung Han
Abstract	We present a framework to analyze various aspects of models for video question answering (VideoQA) using customizable synthetic datasets, which are constructed automatically from gameplay videos. Our work is motivated by the fact that existing models are often tested only on datasets that require excessively high-level reasoning or mostly contain instances accessible through single frame inferences. Hence, it is difficult to measure capacity and flexibility of trained models, and existing techniques often rely on ad-hoc implementations of deep neural networks without clear insight into datasets and models. We are particularly interested in understanding temporal relationships between video events to solve VideoQA problems; this is because reasoning temporal dependency is one of the most distinct components in videos from images. To address this objective, we automatically generate a customized synthetic VideoQA dataset using {\em Super Mario Bros.} gameplay videos so that it contains events with different levels of reasoning complexity. Using the dataset, we show that properly constructed datasets with events in various complexity levels are critical to learn effective models and improve overall performance.
Tasks	Question Answering, Video Question Answering
Published	2016-12-06
URL	http://arxiv.org/abs/1612.01669v2
PDF	http://arxiv.org/pdf/1612.01669v2.pdf
PWC	https://paperswithcode.com/paper/marioqa-answering-questions-by-watching
Repo
Framework

Leveraging Video Descriptions to Learn Video Question Answering


Title	Leveraging Video Descriptions to Learn Video Question Answering
Authors	Kuo-Hao Zeng, Tseng-Hung Chen, Ching-Yao Chuang, Yuan-Hong Liao, Juan Carlos Niebles, Min Sun
Abstract	We propose a scalable approach to learn video-based question answering (QA): answer a “free-form natural language question” about a video content. Our approach automatically harvests a large number of videos and descriptions freely available online. Then, a large number of candidate QA pairs are automatically generated from descriptions rather than manually annotated. Next, we use these candidate QA pairs to train a number of video-based QA methods extended fromMN (Sukhbaatar et al. 2015), VQA (Antol et al. 2015), SA (Yao et al. 2015), SS (Venugopalan et al. 2015). In order to handle non-perfect candidate QA pairs, we propose a self-paced learning procedure to iteratively identify them and mitigate their effects in training. Finally, we evaluate performance on manually generated video-based QA pairs. The results show that our self-paced learning procedure is effective, and the extended SS model outperforms various baselines.
Tasks	Question Answering, Video Question Answering, Visual Question Answering
Published	2016-11-12
URL	http://arxiv.org/abs/1611.04021v2
PDF	http://arxiv.org/pdf/1611.04021v2.pdf
PWC	https://paperswithcode.com/paper/leveraging-video-descriptions-to-learn-video
Repo
Framework

An Alternative Matting Laplacian


Title	An Alternative Matting Laplacian
Authors	François Pitié
Abstract	Cutting out and object and estimate its transparency mask is a key task in many applications. We take on the work on closed-form matting by Levin et al., that is used at the core of many matting techniques, and propose an alternative formulation that offers more flexible controls over the matting priors. We also show that this new approach is efficient at upscaling transparency maps from coarse estimates.
Tasks
Published	2016-05-16
URL	http://arxiv.org/abs/1605.04785v1
PDF	http://arxiv.org/pdf/1605.04785v1.pdf
PWC	https://paperswithcode.com/paper/an-alternative-matting-laplacian
Repo
Framework

Learning Discriminative Features via Label Consistent Neural Network


Title	Learning Discriminative Features via Label Consistent Neural Network
Authors	Zhuolin Jiang, Yaming Wang, Larry Davis, Walt Andrews, Viktor Rozgic
Abstract	Deep Convolutional Neural Networks (CNN) enforces supervised information only at the output layer, and hidden layers are trained by back propagating the prediction error from the output layer without explicit supervision. We propose a supervised feature learning approach, Label Consistent Neural Network, which enforces direct supervision in late hidden layers. We associate each neuron in a hidden layer with a particular class label and encourage it to be activated for input signals from the same class. More specifically, we introduce a label consistency regularization called “discriminative representation error” loss for late hidden layers and combine it with classification error loss to build our overall objective function. This label consistency constraint alleviates the common problem of gradient vanishing and tends to faster convergence; it also makes the features derived from late hidden layers discriminative enough for classification even using a simple $k$-NN classifier, since input signals from the same class will have very similar representations. Experimental results demonstrate that our approach achieves state-of-the-art performances on several public benchmarks for action and object category recognition.
Tasks
Published	2016-02-03
URL	http://arxiv.org/abs/1602.01168v2
PDF	http://arxiv.org/pdf/1602.01168v2.pdf
PWC	https://paperswithcode.com/paper/learning-discriminative-features-via-label
Repo
Framework

Challenges in video based object detection in maritime scenario using computer vision


Title	Challenges in video based object detection in maritime scenario using computer vision
Authors	D. K. Prasad, C. K. Prasath, D. Rajan, L. Rachmawati, E. Rajabaly, C. Quek
Abstract	This paper discusses the technical challenges in maritime image processing and machine vision problems for video streams generated by cameras. Even well documented problems of horizon detection and registration of frames in a video are very challenging in maritime scenarios. More advanced problems of background subtraction and object detection in video streams are very challenging. Challenges arising from the dynamic nature of the background, unavailability of static cues, presence of small objects at distant backgrounds, illumination effects, all contribute to the challenges as discussed here.
Tasks	Object Detection
Published	2016-08-03
URL	http://arxiv.org/abs/1608.01079v1
PDF	http://arxiv.org/pdf/1608.01079v1.pdf
PWC	https://paperswithcode.com/paper/challenges-in-video-based-object-detection-in
Repo
Framework

Analyzing coevolutionary games with dynamic fitness landscapes


Title	Analyzing coevolutionary games with dynamic fitness landscapes
Authors	Hendrik Richter
Abstract	Coevolutionary games cast players that may change their strategies as well as their networks of interaction. In this paper a framework is introduced for describing coevolutionary game dynamics by landscape models. It is shown that coevolutionary games invoke dynamic landscapes. Numerical experiments are shown for a prisoner’s dilemma (PD) and a snow drift (SD) game that both use either birth-death (BD) or death-birth (DB) strategy updating. The resulting landscapes are analyzed with respect to modality and ruggedness
Tasks
Published	2016-03-21
URL	http://arxiv.org/abs/1603.06374v1
PDF	http://arxiv.org/pdf/1603.06374v1.pdf
PWC	https://paperswithcode.com/paper/analyzing-coevolutionary-games-with-dynamic
Repo
Framework

What is the Best Feature Learning Procedure in Hierarchical Recognition Architectures?


Title	What is the Best Feature Learning Procedure in Hierarchical Recognition Architectures?
Authors	Kevin Jarrett, Koray Kvukcuoglu, Karol Gregor, Yann LeCun
Abstract	(This paper was written in November 2011 and never published. It is posted on arXiv.org in its original form in June 2016). Many recent object recognition systems have proposed using a two phase training procedure to learn sparse convolutional feature hierarchies: unsupervised pre-training followed by supervised fine-tuning. Recent results suggest that these methods provide little improvement over purely supervised systems when the appropriate nonlinearities are included. This paper presents an empirical exploration of the space of learning procedures for sparse convolutional networks to assess which method produces the best performance. In our study, we introduce an augmentation of the Predictive Sparse Decomposition method that includes a discriminative term (DPSD). We also introduce a new single phase supervised learning procedure that places an L1 penalty on the output state of each layer of the network. This forces the network to produce sparse codes without the expensive pre-training phase. Using DPSD with a new, complex predictor that incorporates lateral inhibition, combined with multi-scale feature pooling, and supervised refinement, the system achieves a 70.6% recognition rate on Caltech-101. With the addition of convolutional training, a 77% recognition was obtained on the CIfAR-10 dataset.
Tasks	Object Recognition
Published	2016-06-05
URL	http://arxiv.org/abs/1606.01535v1
PDF	http://arxiv.org/pdf/1606.01535v1.pdf
PWC	https://paperswithcode.com/paper/what-is-the-best-feature-learning-procedure
Repo
Framework

Reinforcement Learning Using Quantum Boltzmann Machines


Title	Reinforcement Learning Using Quantum Boltzmann Machines
Authors	Daniel Crawford, Anna Levit, Navid Ghadermarzy, Jaspreet S. Oberoi, Pooya Ronagh
Abstract	We investigate whether quantum annealers with select chip layouts can outperform classical computers in reinforcement learning tasks. We associate a transverse field Ising spin Hamiltonian with a layout of qubits similar to that of a deep Boltzmann machine (DBM) and use simulated quantum annealing (SQA) to numerically simulate quantum sampling from this system. We design a reinforcement learning algorithm in which the set of visible nodes representing the states and actions of an optimal policy are the first and last layers of the deep network. In absence of a transverse field, our simulations show that DBMs are trained more effectively than restricted Boltzmann machines (RBM) with the same number of nodes. We then develop a framework for training the network as a quantum Boltzmann machine (QBM) in the presence of a significant transverse field for reinforcement learning. This method also outperforms the reinforcement learning method that uses RBMs.
Tasks
Published	2016-12-17
URL	http://arxiv.org/abs/1612.05695v3
PDF	http://arxiv.org/pdf/1612.05695v3.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-using-quantum
Repo
Framework