May 6, 2019

3169 words 15 mins read

Paper Group ANR 169

Multi Exit Configuration of Mesoscopic Pedestrian Simulation. A General Framework for Describing Creative Agents. Set-Point Regulation of Linear Continuous-Time Systems using Neuromorphic Vision Sensors. Feature extraction using Latent Dirichlet Allocation and Neural Networks: A case study on movie synopses. Asymptotic Optimality in Stochastic Opti …

Multi Exit Configuration of Mesoscopic Pedestrian Simulation


Title	Multi Exit Configuration of Mesoscopic Pedestrian Simulation
Authors	Allan Lao, Kardi Teknomo
Abstract	A mesoscopic approach to modeling pedestrian simulation with multiple exits is proposed in this paper. A floor field based on Qlearning Algorithm is used. Attractiveness of exits to pedestrian typically is based on shortest path. However, several factors may influence pedestrian choice of exits. Scenarios with multiple exits are presented and effect of Q-learning rewards system on navigation is investigated
Tasks	Q-Learning
Published	2016-09-06
URL	http://arxiv.org/abs/1609.01475v1
PDF	http://arxiv.org/pdf/1609.01475v1.pdf
PWC	https://paperswithcode.com/paper/multi-exit-configuration-of-mesoscopic
Repo
Framework

A General Framework for Describing Creative Agents


Title	A General Framework for Describing Creative Agents
Authors	Valerio Velardo, Mauro Vallati
Abstract	Computational creativity is a subfield of AI focused on developing and studying creative systems. Few academic studies analysing the behaviour of creative agents from a theoretical viewpoint have been proposed. The proposed frameworks are vague and hard to exploit; moreover, such works are focused on a notion of creativity tailored for humans. In this paper we introduce General Creativity, which extends that traditional notion. General Creativity provides the basis for a formalised theoretical framework, that allows one to univocally describe any creative agent, and their behaviour within societies of creative systems. Given the growing number of AI creative systems developed over recent years, it is of fundamental importance to understand how they could influence each other as well as how to gauge their impact on human society. In particular, in this paper we exploit the proposed framework for (i) identifying different forms of creativity; (ii) describing some typical creative agents behaviour, and (iii) analysing the dynamics of societies in which both human and non-human creative systems coexist.
Tasks
Published	2016-04-14
URL	http://arxiv.org/abs/1604.04096v1
PDF	http://arxiv.org/pdf/1604.04096v1.pdf
PWC	https://paperswithcode.com/paper/a-general-framework-for-describing-creative
Repo
Framework

Set-Point Regulation of Linear Continuous-Time Systems using Neuromorphic Vision Sensors


Title	Set-Point Regulation of Linear Continuous-Time Systems using Neuromorphic Vision Sensors
Authors	Prince Singh, Sze Zheng Yong, Emilio Frazzoli
Abstract	Recently developed neuromorphic vision sensors have become promising candidates for agile and autonomous robotic applications primarily due to, in particular, their high temporal resolution and low latency. Each pixel of this sensor independently fires an asynchronous stream of “retinal events” once a change in the light field is detected. Existing computer vision algorithms can only process periodic frames and so a new class of algorithms needs to be developed that can efficiently process these events for control tasks. In this paper, we investigate the problem of regulating a continuous-time linear time invariant (LTI) system to a desired point using measurements from a neuromorphic sensor. We present an $H_\infty$ controller that regulates the LTI system to a desired set-point and provide the set of neuromorphic sensor based cameras for the given system that fulfill the regulation task. The effectiveness of our approach is illustrated on an unstable system.
Tasks
Published	2016-09-18
URL	http://arxiv.org/abs/1609.05483v1
PDF	http://arxiv.org/pdf/1609.05483v1.pdf
PWC	https://paperswithcode.com/paper/set-point-regulation-of-linear-continuous
Repo
Framework

Feature extraction using Latent Dirichlet Allocation and Neural Networks: A case study on movie synopses


Title	Feature extraction using Latent Dirichlet Allocation and Neural Networks: A case study on movie synopses
Authors	Despoina Christou
Abstract	Feature extraction has gained increasing attention in the field of machine learning, as in order to detect patterns, extract information, or predict future observations from big data, the urge of informative features is crucial. The process of extracting features is highly linked to dimensionality reduction as it implies the transformation of the data from a sparse high-dimensional space, to higher level meaningful abstractions. This dissertation employs Neural Networks for distributed paragraph representations, and Latent Dirichlet Allocation to capture higher level features of paragraph vectors. Although Neural Networks for distributed paragraph representations are considered the state of the art for extracting paragraph vectors, we show that a quick topic analysis model such as Latent Dirichlet Allocation can provide meaningful features too. We evaluate the two methods on the CMU Movie Summary Corpus, a collection of 25,203 movie plot summaries extracted from Wikipedia. Finally, for both approaches, we use K-Nearest Neighbors to discover similar movies, and plot the projected representations using T-Distributed Stochastic Neighbor Embedding to depict the context similarities. These similarities, expressed as movie distances, can be used for movies recommendation. The recommended movies of this approach are compared with the recommended movies from IMDB, which use a collaborative filtering recommendation approach, to show that our two models could constitute either an alternative or a supplementary recommendation approach.
Tasks	Dimensionality Reduction
Published	2016-04-05
URL	http://arxiv.org/abs/1604.01272v1
PDF	http://arxiv.org/pdf/1604.01272v1.pdf
PWC	https://paperswithcode.com/paper/feature-extraction-using-latent-dirichlet
Repo
Framework

Asymptotic Optimality in Stochastic Optimization


Title	Asymptotic Optimality in Stochastic Optimization
Authors	John Duchi, Feng Ruan
Abstract	We study local complexity measures for stochastic convex optimization problems, providing a local minimax theory analogous to that of H'{a}jek and Le Cam for classical statistical problems. We give complementary optimality results, developing fully online methods that adaptively achieve optimal convergence guarantees. Our results provide function-specific lower bounds and convergence results that make precise a correspondence between statistical difficulty and the geometric notion of tilt-stability from optimization. As part of this development, we show how variants of Nesterov’s dual averaging—a stochastic gradient-based procedure—guarantee finite time identification of constraints in optimization problems, while stochastic gradient procedures fail. Additionally, we highlight a gap between problems with linear and nonlinear constraints: standard stochastic-gradient-based procedures are suboptimal even for the simplest nonlinear constraints, necessitating the development of asymptotically optimal Riemannian stochastic gradient methods.
Tasks	Stochastic Optimization
Published	2016-12-16
URL	http://arxiv.org/abs/1612.05612v4
PDF	http://arxiv.org/pdf/1612.05612v4.pdf
PWC	https://paperswithcode.com/paper/asymptotic-optimality-in-stochastic
Repo
Framework

Semi-supervised Inference: General Theory and Estimation of Means


Title	Semi-supervised Inference: General Theory and Estimation of Means
Authors	Anru Zhang, Lawrence D. Brown, T. Tony Cai
Abstract	We propose a general semi-supervised inference framework focused on the estimation of the population mean. As usual in semi-supervised settings, there exists an unlabeled sample of covariate vectors and a labeled sample consisting of covariate vectors along with real-valued responses (“labels”). Otherwise, the formulation is “assumption-lean” in that no major conditions are imposed on the statistical or functional form of the data. We consider both the ideal semi-supervised setting where infinitely many unlabeled samples are available, as well as the ordinary semi-supervised setting in which only a finite number of unlabeled samples is available. Estimators are proposed along with corresponding confidence intervals for the population mean. Theoretical analysis on both the asymptotic distribution and $\ell_2$-risk for the proposed procedures are given. Surprisingly, the proposed estimators, based on a simple form of the least squares method, outperform the ordinary sample mean. The simple, transparent form of the estimator lends confidence to the perception that its asymptotic improvement over the ordinary sample mean also nearly holds even for moderate size samples. The method is further extended to a nonparametric setting, in which the oracle rate can be achieved asymptotically. The proposed estimators are further illustrated by simulation studies and a real data example involving estimation of the homeless population.
Tasks
Published	2016-06-23
URL	http://arxiv.org/abs/1606.07268v2
PDF	http://arxiv.org/pdf/1606.07268v2.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-inference-general-theory-and
Repo
Framework

Structured Learning of Binary Codes with Column Generation


Title	Structured Learning of Binary Codes with Column Generation
Authors	Guosheng Lin, Fayao Liu, Chunhua Shen, Jianxin Wu, Heng Tao Shen
Abstract	Hashing methods aim to learn a set of hash functions which map the original features to compact binary codes with similarity preserving in the Hamming space. Hashing has proven a valuable tool for large-scale information retrieval. We propose a column generation based binary code learning framework for data-dependent hash function learning. Given a set of triplets that encode the pairwise similarity comparison information, our column generation based method learns hash functions that preserve the relative comparison relations within the large-margin learning framework. Our method iteratively learns the best hash functions during the column generation procedure. Existing hashing methods optimize over simple objectives such as the reconstruction error or graph Laplacian related loss functions, instead of the performance evaluation criteria of interest—multivariate performance measures such as the AUC and NDCG. Our column generation based method can be further generalized from the triplet loss to a general structured learning based framework that allows one to directly optimize multivariate performance measures. For optimizing general ranking measures, the resulting optimization problem can involve exponentially or infinitely many variables and constraints, which is more challenging than standard structured output learning. We use a combination of column generation and cutting-plane techniques to solve the optimization problem. To speed-up the training we further explore stage-wise training and propose to use a simplified NDCG loss for efficient inference. We demonstrate the generality of our method by applying it to ranking prediction and image retrieval, and show that it outperforms a few state-of-the-art hashing methods.
Tasks	Image Retrieval, Information Retrieval
Published	2016-02-22
URL	http://arxiv.org/abs/1602.06654v1
PDF	http://arxiv.org/pdf/1602.06654v1.pdf
PWC	https://paperswithcode.com/paper/structured-learning-of-binary-codes-with
Repo
Framework

Self-Reflective Risk-Aware Artificial Cognitive Modeling for Robot Response to Human Behaviors


Title	Self-Reflective Risk-Aware Artificial Cognitive Modeling for Robot Response to Human Behaviors
Authors	Fei Han, Christopher Reardon, Lynne E. Parker, Hao Zhang
Abstract	In order for cooperative robots (“co-robots”) to respond to human behaviors accurately and efficiently in human-robot collaboration, interpretation of human actions, awareness of new situations, and appropriate decision making are all crucial abilities for co-robots. For this purpose, the human behaviors should be interpreted by co-robots in the same manner as human peers. To address this issue, a novel interpretability indicator is introduced so that robot actions are appropriate to the current human behaviors. In addition, the complete consideration of all potential situations of a robot’s environment is nearly impossible in real-world applications, making it difficult for the co-robot to act appropriately and safely in new scenarios. This is true even when the pretrained model is highly accurate in a known situation. For effective and safe teaming with humans, we introduce a new generalizability indicator that allows a co-robot to self-reflect and reason about when an observation falls outside the co-robot’s learned model. Based on topic modeling and two novel indicators, we propose a new Self-reflective Risk-aware Artificial Cognitive (SRAC) model. The co-robots are able to consider action risks and identify new situations so that better decisions can be made. Experiments both using real-world datasets and on physical robots suggest that our SRAC model significantly outperforms the traditional methodology and enables better decision making in response to human activities.
Tasks	Decision Making
Published	2016-05-16
URL	http://arxiv.org/abs/1605.04934v1
PDF	http://arxiv.org/pdf/1605.04934v1.pdf
PWC	https://paperswithcode.com/paper/self-reflective-risk-aware-artificial
Repo
Framework

A Novel Biologically Mechanism-Based Visual Cognition Model–Automatic Extraction of Semantics, Formation of Integrated Concepts and Re-selection Features for Ambiguity


Title	A Novel Biologically Mechanism-Based Visual Cognition Model–Automatic Extraction of Semantics, Formation of Integrated Concepts and Re-selection Features for Ambiguity
Authors	Peijie Yin, Hong Qiao, Wei Wu, Lu Qi, YinLin Li, Shanlin Zhong, Bo Zhang
Abstract	Integration between biology and information science benefits both fields. Many related models have been proposed, such as computational visual cognition models, computational motor control models, integrations of both and so on. In general, the robustness and precision of recognition is one of the key problems for object recognition models. In this paper, inspired by features of human recognition process and their biological mechanisms, a new integrated and dynamic framework is proposed to mimic the semantic extraction, concept formation and feature re-selection in human visual processing. The main contributions of the proposed model are as follows: (1) Semantic feature extraction: Local semantic features are learnt from episodic features that are extracted from raw images through a deep neural network; (2) Integrated concept formation: Concepts are formed with local semantic information and structural information learnt through network. (3) Feature re-selection: When ambiguity is detected during recognition process, distinctive features according to the difference between ambiguous candidates are re-selected for recognition. Experimental results on hand-written digits and facial shape dataset show that, compared with other methods, the new proposed model exhibits higher robustness and precision for visual recognition, especially in the condition when input samples are smantic ambiguous. Meanwhile, the introduced biological mechanisms further strengthen the interaction between neuroscience and information science.
Tasks	Object Recognition
Published	2016-03-25
URL	http://arxiv.org/abs/1603.07886v1
PDF	http://arxiv.org/pdf/1603.07886v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-biologically-mechanism-based-visual
Repo
Framework

StalemateBreaker: A Proactive Content-Introducing Approach to Automatic Human-Computer Conversation


Title	StalemateBreaker: A Proactive Content-Introducing Approach to Automatic Human-Computer Conversation
Authors	Xiang Li, Lili Mou, Rui Yan, Ming Zhang
Abstract	Existing open-domain human-computer conversation systems are typically passive: they either synthesize or retrieve a reply provided a human-issued utterance. It is generally presumed that humans should take the role to lead the conversation and introduce new content when a stalemate occurs, and that the computer only needs to “respond.” In this paper, we propose StalemateBreaker, a conversation system that can proactively introduce new content when appropriate. We design a pipeline to determine when, what, and how to introduce new content during human-computer conversation. We further propose a novel reranking algorithm Bi-PageRank-HITS to enable rich interaction between conversation context and candidate replies. Experiments show that both the content-introducing approach and the reranking algorithm are effective. Our full StalemateBreaker model outperforms a state-of-the-practice conversation system by +14.4% p@1 when a stalemate occurs.
Tasks
Published	2016-04-15
URL	http://arxiv.org/abs/1604.04358v1
PDF	http://arxiv.org/pdf/1604.04358v1.pdf
PWC	https://paperswithcode.com/paper/stalematebreaker-a-proactive-content
Repo
Framework

Hierarchical Attention Model for Improved Machine Comprehension of Spoken Content


Title	Hierarchical Attention Model for Improved Machine Comprehension of Spoken Content
Authors	Wei Fang, Jui-Yang Hsu, Hung-yi Lee, Lin-Shan Lee
Abstract	Multimedia or spoken content presents more attractive information than plain text content, but the former is more difficult to display on a screen and be selected by a user. As a result, accessing large collections of the former is much more difficult and time-consuming than the latter for humans. It’s therefore highly attractive to develop machines which can automatically understand spoken content and summarize the key information for humans to browse over. In this endeavor, a new task of machine comprehension of spoken content was proposed recently. The initial goal was defined as the listening comprehension test of TOEFL, a challenging academic English examination for English learners whose native languages are not English. An Attention-based Multi-hop Recurrent Neural Network (AMRNN) architecture was also proposed for this task, which considered only the sequential relationship within the speech utterances. In this paper, we propose a new Hierarchical Attention Model (HAM), which constructs multi-hopped attention mechanism over tree-structured rather than sequential representations for the utterances. Improved comprehension performance robust with respect to ASR errors were obtained.
Tasks	Reading Comprehension
Published	2016-08-28
URL	http://arxiv.org/abs/1608.07775v3
PDF	http://arxiv.org/pdf/1608.07775v3.pdf
PWC	https://paperswithcode.com/paper/hierarchical-attention-model-for-improved
Repo
Framework

Latent Embeddings for Zero-shot Classification


Title	Latent Embeddings for Zero-shot Classification
Authors	Yongqin Xian, Zeynep Akata, Gaurav Sharma, Quynh Nguyen, Matthias Hein, Bernt Schiele
Abstract	We present a novel latent embedding model for learning a compatibility function between image and class embeddings, in the context of zero-shot classification. The proposed method augments the state-of-the-art bilinear compatibility model by incorporating latent variables. Instead of learning a single bilinear map, it learns a collection of maps with the selection, of which map to use, being a latent variable for the current image-class pair. We train the model with a ranking based objective function which penalizes incorrect rankings of the true class for a given image. We empirically demonstrate that our model improves the state-of-the-art for various class embeddings consistently on three challenging publicly available datasets for the zero-shot setting. Moreover, our method leads to visually highly interpretable results with clear clusters of different fine-grained object properties that correspond to different latent variable maps.
Tasks	Zero-Shot Learning
Published	2016-03-29
URL	http://arxiv.org/abs/1603.08895v2
PDF	http://arxiv.org/pdf/1603.08895v2.pdf
PWC	https://paperswithcode.com/paper/latent-embeddings-for-zero-shot
Repo
Framework

Mapping the Dialog Act Annotations of the LEGO Corpus into the Communicative Functions of ISO 24617-2


Title	Mapping the Dialog Act Annotations of the LEGO Corpus into the Communicative Functions of ISO 24617-2
Authors	Eugénio Ribeiro, Ricardo Ribeiro, David Martins de Matos
Abstract	In this paper we present strategies for mapping the dialog act annotations of the LEGO corpus into the communicative functions of the ISO 24617-2 standard. Using these strategies, we obtained an additional 347 dialogs annotated according to the standard. This is particularly important given the reduced amount of existing data in those conditions due to the recency of the standard. Furthermore, these are dialogs from a widely explored corpus for dialog related tasks. However, its dialog annotations have been neglected due to their high domain-dependency, which renders them unuseful outside the context of the corpus. Thus, through our mapping process, we both obtain more data annotated according to a recent standard and provide useful dialog act annotations for a widely explored corpus in the context of dialog research.
Tasks
Published	2016-12-05
URL	http://arxiv.org/abs/1612.01404v1
PDF	http://arxiv.org/pdf/1612.01404v1.pdf
PWC	https://paperswithcode.com/paper/mapping-the-dialog-act-annotations-of-the
Repo
Framework

Learning deep structured network for weakly supervised change detection


Title	Learning deep structured network for weakly supervised change detection
Authors	Salman H Khan, Xuming He, Fatih Porikli, Mohammed Bennamoun, Ferdous Sohel, Roberto Togneri
Abstract	Conventional change detection methods require a large number of images to learn background models or depend on tedious pixel-level labeling by humans. In this paper, we present a weakly supervised approach that needs only image-level labels to simultaneously detect and localize changes in a pair of images. To this end, we employ a deep neural network with DAG topology to learn patterns of change from image-level labeled training data. On top of the initial CNN activations, we define a CRF model to incorporate the local differences and context with the dense connections between individual pixels. We apply a constrained mean-field algorithm to estimate the pixel-level labels, and use the estimated labels to update the parameters of the CNN in an iterative EM framework. This enables imposing global constraints on the observed foreground probability mass function. Our evaluations on four benchmark datasets demonstrate superior detection and localization performance.
Tasks
Published	2016-06-07
URL	http://arxiv.org/abs/1606.02009v2
PDF	http://arxiv.org/pdf/1606.02009v2.pdf
PWC	https://paperswithcode.com/paper/learning-deep-structured-network-for-weakly
Repo
Framework

Language free character recognition using character sketch and center of gravity shifting


Title	Language free character recognition using character sketch and center of gravity shifting
Authors	Masoud Nosrati, Fakhereh Rahimi, Ronak Karimi
Abstract	In this research, we present a heuristic method for character recognition. For this purpose, a sketch is constructed from the image that contains the character to be recognized. This sketch contains the most important pixels of image that are representatives of original image. These points are the most probable points in pixel-by-pixel matching of image that adapt to target image. Furthermore, a technique called gravity shifting is utilized for taking over the problem of elongation of characters. The consequence of combining sketch and gravity techniques leaded to a language free character recognition method. This method can be implemented independently for real-time uses or in combination of other classifiers as a feature extraction algorithm. Low complexity and acceptable performance are the most impressive features of this method that let it to be simply implemented in mobile and battery-limited computing devices. Results show that in the best case 86% of accuracy is obtained and in the worst case 28% of recognized characters are accurate.
Tasks
Published	2016-08-03
URL	http://arxiv.org/abs/1608.01391v1
PDF	http://arxiv.org/pdf/1608.01391v1.pdf
PWC	https://paperswithcode.com/paper/language-free-character-recognition-using
Repo
Framework