July 29, 2019

2826 words 14 mins read

Paper Group ANR 69

Extracting Lifted Mutual Exclusion Invariants from Temporal Planning Domains. MoodSwipe: A Soft Keyboard that Suggests Messages Based on User-Specified Emotions. Applying Deep Machine Learning for psycho-demographic profiling of Internet users using O.C.E.A.N. model of personality. Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional …

Extracting Lifted Mutual Exclusion Invariants from Temporal Planning Domains


Title	Extracting Lifted Mutual Exclusion Invariants from Temporal Planning Domains
Authors	Sara Bernardini, Fabio Fagnani, David E. Smith
Abstract	We present a technique for automatically extracting mutual exclusion invariants from temporal planning instances. It first identifies a set of invariant templates by inspecting the lifted representation of the domain and then checks these templates against properties that assure invariance. Our technique builds on other approaches to invariant synthesis presented in the literature, but departs from their limited focus on instantaneous actions by addressing temporal domains. To deal with time, we formulate invariance conditions that account for the entire structure of the actions and the possible concurrent interactions between them. As a result, we construct a significantly more comprehensive technique than previous methods, which is able to find not only invariants for temporal domains, but also a broader set of invariants for non-temporal domains. The experimental results reported in this paper provide evidence that identifying a broader set of invariants results in the generation of fewer multi-valued state variables with larger domains. We show that, in turn, this reduction in the number of variables reflects positively on the performance of a number of temporal planners that use a variable/value representation by significantly reducing their running time.
Tasks
Published	2017-02-07
URL	http://arxiv.org/abs/1702.01886v1
PDF	http://arxiv.org/pdf/1702.01886v1.pdf
PWC	https://paperswithcode.com/paper/extracting-lifted-mutual-exclusion-invariants
Repo
Framework

MoodSwipe: A Soft Keyboard that Suggests Messages Based on User-Specified Emotions


Title	MoodSwipe: A Soft Keyboard that Suggests Messages Based on User-Specified Emotions
Authors	Chieh-Yang Huang, Tristan Labetoulle, Ting-Hao Kenneth Huang, Yi-Pei Chen, Hung-Chen Chen, Vallari Srivastava, Lun-Wei Ku
Abstract	We present MoodSwipe, a soft keyboard that suggests text messages given the user-specified emotions utilizing the real dialog data. The aim of MoodSwipe is to create a convenient user interface to enjoy the technology of emotion classification and text suggestion, and at the same time to collect labeled data automatically for developing more advanced technologies. While users select the MoodSwipe keyboard, they can type as usual but sense the emotion conveyed by their text and receive suggestions for their message as a benefit. In MoodSwipe, the detected emotions serve as the medium for suggested texts, where viewing the latter is the incentive to correcting the former. We conduct several experiments to show the superiority of the emotion classification models trained on the dialog data, and further to verify good emotion cues are important context for text suggestion.
Tasks	Emotion Classification
Published	2017-07-22
URL	http://arxiv.org/abs/1707.07191v1
PDF	http://arxiv.org/pdf/1707.07191v1.pdf
PWC	https://paperswithcode.com/paper/moodswipe-a-soft-keyboard-that-suggests-1
Repo
Framework

Applying Deep Machine Learning for psycho-demographic profiling of Internet users using O.C.E.A.N. model of personality


Title	Applying Deep Machine Learning for psycho-demographic profiling of Internet users using O.C.E.A.N. model of personality
Authors	Iaroslav Omelianenko
Abstract	In the modern era, each Internet user leaves enormous amounts of auxiliary digital residuals (footprints) by using a variety of on-line services. All this data is already collected and stored for many years. In recent works, it was demonstrated that it’s possible to apply simple machine learning methods to analyze collected digital footprints and to create psycho-demographic profiles of individuals. However, while these works clearly demonstrated the applicability of machine learning methods for such an analysis, created simple prediction models still lacks accuracy necessary to be successfully applied for practical needs. We have assumed that using advanced deep machine learning methods may considerably increase the accuracy of predictions. We started with simple machine learning methods to estimate basic prediction performance and moved further by applying advanced methods based on shallow and deep neural networks. Then we compared prediction power of studied models and made conclusions about its performance. Finally, we made hypotheses how prediction accuracy can be further improved. As result of this work, we provide full source code used in the experiments for all interested researchers and practitioners in corresponding GitHub repository. We believe that applying deep machine learning for psycho-demographic profiling may have an enormous impact on the society (for good or worse) and provides means for Artificial Intelligence (AI) systems to better understand humans by creating their psychological profiles. Thus AI agents may achieve the human-like ability to participate in conversation (communication) flow by anticipating human opponents’ reactions, expectations, and behavior.
Tasks
Published	2017-03-07
URL	http://arxiv.org/abs/1703.06914v2
PDF	http://arxiv.org/pdf/1703.06914v2.pdf
PWC	https://paperswithcode.com/paper/applying-deep-machine-learning-for-psycho
Repo
Framework

Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization


Title	Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization
Authors	Frederick Tung, Srikanth Muralidharan, Greg Mori
Abstract	When approaching a novel visual recognition problem in a specialized image domain, a common strategy is to start with a pre-trained deep neural network and fine-tune it to the specialized domain. If the target domain covers a smaller visual space than the source domain used for pre-training (e.g. ImageNet), the fine-tuned network is likely to be over-parameterized. However, applying network pruning as a post-processing step to reduce the memory requirements has drawbacks: fine-tuning and pruning are performed independently; pruning parameters are set once and cannot adapt over time; and the highly parameterized nature of state-of-the-art pruning methods make it prohibitive to manually search the pruning parameter space for deep networks, leading to coarse approximations. We propose a principled method for jointly fine-tuning and compressing a pre-trained convolutional network that overcomes these limitations. Experiments on two specialized image domains (remote sensing images and describable textures) demonstrate the validity of the proposed approach.
Tasks	Network Pruning
Published	2017-07-28
URL	http://arxiv.org/abs/1707.09102v1
PDF	http://arxiv.org/pdf/1707.09102v1.pdf
PWC	https://paperswithcode.com/paper/fine-pruning-joint-fine-tuning-and
Repo
Framework

Hierarchically-Attentive RNN for Album Summarization and Storytelling


Title	Hierarchically-Attentive RNN for Album Summarization and Storytelling
Authors	Licheng Yu, Mohit Bansal, Tamara L. Berg
Abstract	We address the problem of end-to-end visual storytelling. Given a photo album, our model first selects the most representative (summary) photos, and then composes a natural language story for the album. For this task, we make use of the Visual Storytelling dataset and a model composed of three hierarchically-attentive Recurrent Neural Nets (RNNs) to: encode the album photos, select representative (summary) photos, and compose the story. Automatic and human evaluations show our model achieves better performance on selection, generation, and retrieval than baselines.
Tasks	Visual Storytelling
Published	2017-08-09
URL	http://arxiv.org/abs/1708.02977v1
PDF	http://arxiv.org/pdf/1708.02977v1.pdf
PWC	https://paperswithcode.com/paper/hierarchically-attentive-rnn-for-album
Repo
Framework

Legal Question Answering using Ranking SVM and Deep Convolutional Neural Network


Title	Legal Question Answering using Ranking SVM and Deep Convolutional Neural Network
Authors	Phong-Khac Do, Huy-Tien Nguyen, Chien-Xuan Tran, Minh-Tien Nguyen, Minh-Le Nguyen
Abstract	This paper presents a study of employing Ranking SVM and Convolutional Neural Network for two missions: legal information retrieval and question answering in the Competition on Legal Information Extraction/Entailment. For the first task, our proposed model used a triple of features (LSI, Manhattan, Jaccard), and is based on paragraph level instead of article level as in previous studies. In fact, each single-paragraph article corresponds to a particular paragraph in a huge multiple-paragraph article. For the legal question answering task, additional statistical features from information retrieval task integrated into Convolutional Neural Network contribute to higher accuracy.
Tasks	Information Retrieval, Question Answering
Published	2017-03-16
URL	http://arxiv.org/abs/1703.05320v1
PDF	http://arxiv.org/pdf/1703.05320v1.pdf
PWC	https://paperswithcode.com/paper/legal-question-answering-using-ranking-svm
Repo
Framework

Synthesizing Deep Neural Network Architectures using Biological Synaptic Strength Distributions


Title	Synthesizing Deep Neural Network Architectures using Biological Synaptic Strength Distributions
Authors	A. H. Karimi, M. J. Shafiee, A. Ghodsi, A. Wong
Abstract	In this work, we perform an exploratory study on synthesizing deep neural networks using biological synaptic strength distributions, and the potential influence of different distributions on modelling performance particularly for the scenario associated with small data sets. Surprisingly, a CNN with convolutional layer synaptic strengths drawn from biologically-inspired distributions such as log-normal or correlated center-surround distributions performed relatively well suggesting a possibility for designing deep neural network architectures that do not require many data samples to learn, and can sidestep current training procedures while maintaining or boosting modelling performance.
Tasks
Published	2017-07-01
URL	http://arxiv.org/abs/1707.00081v1
PDF	http://arxiv.org/pdf/1707.00081v1.pdf
PWC	https://paperswithcode.com/paper/synthesizing-deep-neural-network
Repo
Framework

Generative Interest Estimation for Document Recommendations


Title	Generative Interest Estimation for Document Recommendations
Authors	Danijar Hafner, Alexander Immer, Willi Raschkowski, Fabian Windheuser
Abstract	Learning distributed representations of documents has pushed the state-of-the-art in several natural language processing tasks and was successfully applied to the field of recommender systems recently. In this paper, we propose a novel content-based recommender system based on learned representations and a generative model of user interest. Our method works as follows: First, we learn representations on a corpus of text documents. Then, we capture a user’s interest as a generative model in the space of the document representations. In particular, we model the distribution of interest for each user as a Gaussian mixture model (GMM). Recommendations can be obtained directly by sampling from a user’s generative model. Using Latent semantic analysis (LSA) as comparison, we compute and explore document representations on the Delicious bookmarks dataset, a standard benchmark for recommender systems. We then perform density estimation in both spaces and show that learned representations outperform LSA in terms of predictive performance.
Tasks	Density Estimation, Recommendation Systems
Published	2017-11-28
URL	http://arxiv.org/abs/1711.10327v1
PDF	http://arxiv.org/pdf/1711.10327v1.pdf
PWC	https://paperswithcode.com/paper/generative-interest-estimation-for-document
Repo
Framework

Users Constraints in Itemset Mining


Title	Users Constraints in Itemset Mining
Authors	Christian Bessiere, Nadjib Lazaar, Yahia Lebbah, Mehdi Maamar
Abstract	Discovering significant itemsets is one of the fundamental problems in data mining. It has recently been shown that constraint programming is a flexible way to tackle data mining tasks. With a constraint programming approach, we can easily express and efficiently answer queries with users constraints on items. However, in many practical cases it is possible that queries also express users constraints on the dataset itself. For instance, asking for a particular itemset in a particular part of the dataset. This paper presents a general constraint programming model able to handle any kind of query on the items or the dataset for itemset mining.
Tasks
Published	2017-12-31
URL	http://arxiv.org/abs/1801.00345v2
PDF	http://arxiv.org/pdf/1801.00345v2.pdf
PWC	https://paperswithcode.com/paper/users-constraints-in-itemset-mining
Repo
Framework

Extracting Traffic Primitives Directly from Naturalistically Logged Data for Self-Driving Applications


Title	Extracting Traffic Primitives Directly from Naturalistically Logged Data for Self-Driving Applications
Authors	Wenshuo Wang, Ding Zhao
Abstract	Developing an automated vehicle, that can handle complicated driving scenarios and appropriately interact with other road users, requires the ability to semantically learn and understand driving environment, oftentimes, based on analyzing massive amounts of naturalistic driving data. An important paradigm that allows automated vehicles to both learn from human drivers and gain insights is understanding the principal compositions of the entire traffic, termed as traffic primitives. However, the exploding data growth presents a great challenge in extracting primitives from high-dimensional time-series traffic data with various types of road users engaged. Therefore, automatically extracting primitives is becoming one of the cost-efficient ways to help autonomous vehicles understand and predict the complex traffic scenarios. In addition, the extracted primitives from raw data should 1) be appropriate for automated driving applications and also 2) be easily used to generate new traffic scenarios. However, existing literature does not provide a method to automatically learn these primitives from large-scale traffic data. The contribution of this paper has two manifolds. The first one is that we proposed a new framework to generate new traffic scenarios from a handful of limited traffic data. The second one is that we introduce a nonparametric Bayesian learning method – a sticky hierarchical Dirichlet process hidden Markov model – to automatically extract primitives from multidimensional traffic data without prior knowledge of the primitive settings. The developed method is then validated using one day of naturalistic driving data. Experiment results show that the nonparametric Bayesian learning method is able to extract primitives from traffic scenarios where both the binary and continuous events coexist.
Tasks	Autonomous Vehicles, Time Series
Published	2017-09-11
URL	http://arxiv.org/abs/1709.03553v3
PDF	http://arxiv.org/pdf/1709.03553v3.pdf
PWC	https://paperswithcode.com/paper/extracting-traffic-primitives-directly-from
Repo
Framework

Efficient Implementation of a Recognition System Using the Cortex Ventral Stream Model


Title	Efficient Implementation of a Recognition System Using the Cortex Ventral Stream Model
Authors	Ahmad W. Bitar, Mohammad M. Mansour, Ali Chehab
Abstract	In this paper, an efficient implementation for a recognition system based on the original HMAX model of the visual cortex is proposed. Various optimizations targeted to increase accuracy at the so-called layers S1, C1, and S2 of the HMAX model are proposed. At layer S1, all unimportant information such as illumination and expression variations are eliminated from the images. Each image is then convolved with 64 separable Gabor filters in the spatial domain. At layer C1, the minimum scales values are exploited to be embedded into the maximum ones using the additive embedding space. At layer S2, the prototypes are generated in a more efficient way using Partitioning Around Medoid (PAM) clustering algorithm. The impact of these optimizations in terms of accuracy and computational complexity was evaluated on the Caltech101 database, and compared with the baseline performance using support vector machine (SVM) and nearest neighbor (NN) classifiers. The results show that our model provides significant improvement in accuracy at the S1 layer by more than 10% where the computational complexity is also reduced. The accuracy is slightly increased for both approximations at the C1 and S2 layers.
Tasks
Published	2017-11-21
URL	http://arxiv.org/abs/1711.07827v1
PDF	http://arxiv.org/pdf/1711.07827v1.pdf
PWC	https://paperswithcode.com/paper/efficient-implementation-of-a-recognition
Repo
Framework

You said that?


Title	You said that?
Authors	Joon Son Chung, Amir Jamaludin, Andrew Zisserman
Abstract	We present a method for generating a video of a talking face. The method takes as inputs: (i) still images of the target face, and (ii) an audio speech segment; and outputs a video of the target face lip synched with the audio. The method runs in real time and is applicable to faces and audio not seen at training time. To achieve this we propose an encoder-decoder CNN model that uses a joint embedding of the face and audio to generate synthesised talking face video frames. The model is trained on tens of hours of unlabelled videos. We also show results of re-dubbing videos using speech from a different person.
Tasks
Published	2017-05-08
URL	http://arxiv.org/abs/1705.02966v2
PDF	http://arxiv.org/pdf/1705.02966v2.pdf
PWC	https://paperswithcode.com/paper/you-said-that
Repo
Framework

Sparse learning of stochastic dynamic equations


Title	Sparse learning of stochastic dynamic equations
Authors	Lorenzo Boninsegna, Feliks Nüske, Cecilia Clementi
Abstract	With the rapid increase of available data for complex systems, there is great interest in the extraction of physically relevant information from massive datasets. Recently, a framework called Sparse Identification of Nonlinear Dynamics (SINDy) has been introduced to identify the governing equations of dynamical systems from simulation data. In this study, we extend SINDy to stochastic dynamical systems, which are frequently used to model biophysical processes. We prove the asymptotic correctness of stochastics SINDy in the infinite data limit, both in the original and projected variables. We discuss algorithms to solve the sparse regression problem arising from the practical implementation of SINDy, and show that cross validation is an essential tool to determine the right level of sparsity. We demonstrate the proposed methodology on two test systems, namely, the diffusion in a one-dimensional potential, and the projected dynamics of a two-dimensional diffusion process.
Tasks	Sparse Learning
Published	2017-12-06
URL	http://arxiv.org/abs/1712.02432v1
PDF	http://arxiv.org/pdf/1712.02432v1.pdf
PWC	https://paperswithcode.com/paper/sparse-learning-of-stochastic-dynamic
Repo
Framework

Metropolis Sampling


Title	Metropolis Sampling
Authors	Luca Martino, Victor Elvira
Abstract	Monte Carlo (MC) sampling methods are widely applied in Bayesian inference, system simulation and optimization problems. The Markov Chain Monte Carlo (MCMC) algorithms are a well-known class of MC methods which generate a Markov chain with the desired invariant distribution. In this document, we focus on the Metropolis-Hastings (MH) sampler, which can be considered as the atom of the MCMC techniques, introducing the basic notions and different properties. We describe in details all the elements involved in the MH algorithm and the most relevant variants. Several improvements and recent extensions proposed in the literature are also briefly discussed, providing a quick but exhaustive overview of the current Metropolis-based sampling’s world.
Tasks	Bayesian Inference
Published	2017-04-15
URL	http://arxiv.org/abs/1704.04629v1
PDF	http://arxiv.org/pdf/1704.04629v1.pdf
PWC	https://paperswithcode.com/paper/metropolis-sampling
Repo
Framework

A Universal Variance Reduction-Based Catalyst for Nonconvex Low-Rank Matrix Recovery


Title	A Universal Variance Reduction-Based Catalyst for Nonconvex Low-Rank Matrix Recovery
Authors	Lingxiao Wang, Xiao Zhang, Quanquan Gu
Abstract	We propose a generic framework based on a new stochastic variance-reduced gradient descent algorithm for accelerating nonconvex low-rank matrix recovery. Starting from an appropriate initial estimator, our proposed algorithm performs projected gradient descent based on a novel semi-stochastic gradient specifically designed for low-rank matrix recovery. Based upon the mild restricted strong convexity and smoothness conditions, we derive a projected notion of the restricted Lipschitz continuous gradient property, and prove that our algorithm enjoys linear convergence rate to the unknown low-rank matrix with an improved computational complexity. Moreover, our algorithm can be employed to both noiseless and noisy observations, where the optimal sample complexity and the minimax optimal statistical rate can be attained respectively. We further illustrate the superiority of our generic framework through several specific examples, both theoretically and experimentally.
Tasks
Published	2017-01-09
URL	http://arxiv.org/abs/1701.02301v2
PDF	http://arxiv.org/pdf/1701.02301v2.pdf
PWC	https://paperswithcode.com/paper/a-universal-variance-reduction-based-catalyst
Repo
Framework