Paper Group ANR 778
Autostacker: A Compositional Evolutionary Learning System. Real-time Lane Marker Detection Using Template Matching with RGB-D Camera. Learning Pretopological Spaces to Model Complex Propagation Phenomena: A Multiple Instance Learning Approach Based on a Logical Modeling. Assessing Language Proficiency from Eye Movements in Reading. Augmenting Strea …
Autostacker: A Compositional Evolutionary Learning System
| Title | Autostacker: A Compositional Evolutionary Learning System |
| Authors | Boyuan Chen, Harvey Wu, Warren Mo, Ishanu Chattopadhyay, Hod Lipson |
| Abstract | We introduce an automatic machine learning (AutoML) modeling architecture called Autostacker, which combines an innovative hierarchical stacking architecture and an Evolutionary Algorithm (EA) to perform efficient parameter search. Neither prior domain knowledge about the data nor feature preprocessing is needed. Using EA, Autostacker quickly evolves candidate pipelines with high predictive accuracy. These pipelines can be used as is or as a starting point for human experts to build on. Autostacker finds innovative combinations and structures of machine learning models, rather than selecting a single model and optimizing its hyperparameters. Compared with other AutoML systems on fifteen datasets, Autostacker achieves state-of-art or competitive performance both in terms of test accuracy and time cost. |
| Tasks | AutoML, Hyperparameter Optimization |
| Published | 2018-03-02 |
| URL | http://arxiv.org/abs/1803.00684v1 |
| http://arxiv.org/pdf/1803.00684v1.pdf | |
| PWC | https://paperswithcode.com/paper/autostacker-a-compositional-evolutionary |
| Repo | |
| Framework | |
Real-time Lane Marker Detection Using Template Matching with RGB-D Camera
| Title | Real-time Lane Marker Detection Using Template Matching with RGB-D Camera |
| Authors | Cong Hoang Quach, Van Lien Tran, Duy Hung Nguyen, Viet Thang Nguyen, Minh Trien Pham, Manh Duong Phung |
| Abstract | This paper addresses the problem of lane detection which is fundamental for self-driving vehicles. Our approach exploits both colour and depth information recorded by a single RGB-D camera to better deal with negative factors such as lighting conditions and lane-like objects. In the approach, colour and depth images are first converted to a half-binary format and a 2D matrix of 3D points. They are then used as the inputs of template matching and geometric feature extraction processes to form a response map so that its values represent the probability of pixels being lane markers. To further improve the results, the template and lane surfaces are finally refined by principal component analysis and lane model fitting techniques. A number of experiments have been conducted on both synthetic and real datasets. The result shows that the proposed approach can effectively eliminate unwanted noise to accurately detect lane markers in various scenarios. Moreover, the processing speed of 20 frames per second under hardware configuration of a popular laptop computer allows the proposed algorithm to be implemented for real-time autonomous driving applications. |
| Tasks | Autonomous Driving, Lane Detection |
| Published | 2018-06-05 |
| URL | http://arxiv.org/abs/1806.01621v1 |
| http://arxiv.org/pdf/1806.01621v1.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-lane-marker-detection-using |
| Repo | |
| Framework | |
Learning Pretopological Spaces to Model Complex Propagation Phenomena: A Multiple Instance Learning Approach Based on a Logical Modeling
| Title | Learning Pretopological Spaces to Model Complex Propagation Phenomena: A Multiple Instance Learning Approach Based on a Logical Modeling |
| Authors | Gaëtan Caillaut, Guillaume Cleuziou |
| Abstract | This paper addresses the problem of learning the concept of “propagation” in the pretopology theoretical formalism. Our proposal is first to define the pseudo-closure operator (modeling the propagation concept) as a logical combination of neighborhoods. We show that learning such an operator lapses into the Multiple Instance (MI) framework, where the learning process is performed on bags of instances instead of individual instances. Though this framework is well suited for this task, its use for learning a pretopological space leads to a set of bags exponential in size. To overcome this issue we thus propose a learning method based on a low estimation of the bags covered by a concept under construction. As an experiment, percolation processes (forest fires typically) are simulated and the corresponding propagation models are learned based on a subset of observations. It reveals that the proposed MI approach is significantly more efficient on the task of propagation model recognition than existing methods. |
| Tasks | Multiple Instance Learning |
| Published | 2018-05-03 |
| URL | http://arxiv.org/abs/1805.01278v1 |
| http://arxiv.org/pdf/1805.01278v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-pretopological-spaces-to-model |
| Repo | |
| Framework | |
Assessing Language Proficiency from Eye Movements in Reading
| Title | Assessing Language Proficiency from Eye Movements in Reading |
| Authors | Yevgeni Berzak, Boris Katz, Roger Levy |
| Abstract | We present a novel approach for determining learners’ second language proficiency which utilizes behavioral traces of eye movements during reading. Our approach provides stand-alone eyetracking based English proficiency scores which reflect the extent to which the learner’s gaze patterns in reading are similar to those of native English speakers. We show that our scores correlate strongly with standardized English proficiency tests. We also demonstrate that gaze information can be used to accurately predict the outcomes of such tests. Our approach yields the strongest performance when the test taker is presented with a suite of sentences for which we have eyetracking data from other readers. However, it remains effective even using eyetracking with sentences for which eye movement data have not been previously collected. By deriving proficiency as an automatic byproduct of eye movements during ordinary reading, our approach offers a potentially valuable new tool for second language proficiency assessment. More broadly, our results open the door to future methods for inferring reader characteristics from the behavioral traces of reading. |
| Tasks | |
| Published | 2018-04-19 |
| URL | http://arxiv.org/abs/1804.07329v2 |
| http://arxiv.org/pdf/1804.07329v2.pdf | |
| PWC | https://paperswithcode.com/paper/assessing-language-proficiency-from-eye |
| Repo | |
| Framework | |
Augmenting Stream Constraint Programming with Eventuality Conditions
| Title | Augmenting Stream Constraint Programming with Eventuality Conditions |
| Authors | Jasper C. H. Lee, Jimmy H. M. Lee, Allen Z. Zhong |
| Abstract | Stream constraint programming is a recent addition to the family of constraint programming frameworks, where variable domains are sets of infinite streams over finite alphabets. Previous works showed promising results for its applicability to real-world planning and control problems. In this paper, motivated by the modelling of planning applications, we improve the expressiveness of the framework by introducing 1) the “until” constraint, a new construct that is adapted from Linear Temporal Logic and 2) the @ operator on streams, a syntactic sugar for which we provide a more efficient solving algorithm over simple desugaring. For both constructs, we propose corresponding novel solving algorithms and prove their correctness. We present competitive experimental results on the Missionaries and Cannibals logic puzzle and a standard path planning application on the grid, by comparing with Apt and Brand’s method for verifying eventuality conditions using a CP approach. |
| Tasks | |
| Published | 2018-06-12 |
| URL | http://arxiv.org/abs/1806.04325v2 |
| http://arxiv.org/pdf/1806.04325v2.pdf | |
| PWC | https://paperswithcode.com/paper/augmenting-stream-constraint-programming-with |
| Repo | |
| Framework | |
A Non-linear Approach to Space Dimension Perception by a Naive Agent
| Title | A Non-linear Approach to Space Dimension Perception by a Naive Agent |
| Authors | Alban Laflaquière, Sylvain Argentieri, Olivia Breysse, Stéphane Genet, Bruno Gas |
| Abstract | Developmental Robotics offers a new approach to numerous AI features that are often taken as granted. Traditionally, perception is supposed to be an inherent capacity of the agent. Moreover, it largely relies on models built by the system’s designer. A new approach is to consider perception as an experimentally acquired ability that is learned exclusively through the analysis of the agent’s sensorimotor flow. Previous works, based on H.Poincar'e’s intuitions and the sensorimotor contingencies theory, allow a simulated agent to extract the dimension of geometrical space in which it is immersed without any a priori knowledge. Those results are limited to infinitesimal movement’s amplitude of the system. In this paper, a non-linear dimension estimation method is proposed to push back this limitation. |
| Tasks | |
| Published | 2018-10-03 |
| URL | http://arxiv.org/abs/1810.01867v1 |
| http://arxiv.org/pdf/1810.01867v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-non-linear-approach-to-space-dimension |
| Repo | |
| Framework | |
Characterizing multiple instance datasets
| Title | Characterizing multiple instance datasets |
| Authors | Veronika Cheplygina, David M. J. Tax |
| Abstract | In many pattern recognition problems, a single feature vector is not sufficient to describe an object. In multiple instance learning (MIL), objects are represented by sets (\emph{bags}) of feature vectors (\emph{instances}). This requires an adaptation of standard supervised classifiers in order to train and evaluate on these bags of instances. Like for supervised classification, several benchmark datasets and numerous classifiers are available for MIL. When performing a comparison of different MIL classifiers, it is important to understand the differences of the datasets, used in the comparison. Seemingly different (based on factors such as dimensionality) datasets may elicit very similar behaviour in classifiers, and vice versa. This has implications for what kind of conclusions may be drawn from the comparison results. We aim to give an overview of the variability of available benchmark datasets and some popular MIL classifiers. We use a dataset dissimilarity measure, based on the differences between the ROC-curves obtained by different classifiers, and embed this dataset dissimilarity matrix into a low-dimensional space. Our results show that conceptually similar datasets can behave very differently. We therefore recommend examining such dataset characteristics when making comparisons between existing and new MIL classifiers. The datasets are available via Figshare at \url{https://bit.ly/2K9iTja}. |
| Tasks | Multiple Instance Learning |
| Published | 2018-06-21 |
| URL | http://arxiv.org/abs/1806.08186v1 |
| http://arxiv.org/pdf/1806.08186v1.pdf | |
| PWC | https://paperswithcode.com/paper/characterizing-multiple-instance-datasets |
| Repo | |
| Framework | |
Intelligent Drone Swarm for Search and Rescue Operations at Sea
| Title | Intelligent Drone Swarm for Search and Rescue Operations at Sea |
| Authors | Vincenzo Lomonaco, Angelo Trotta, Marta Ziosi, Juan de Dios Yáñez Ávila, Natalia Díaz-Rodríguez |
| Abstract | In recent years, a rising numbers of people arrived in the European Union, traveling across the Mediterranean Sea or overland through Southeast Europe in what has been later named as the European migrant crisis. In the last 5 years, more than 16 thousands people have lost their lives in the Mediterranean sea during the crossing. The United Nations Secretary General Strategy on New Technologies is supporting the use of Artificial Intelligence (AI) and Robotics to accelerate the achievement of the 2030 Sustainable Development Agenda, which includes safe and regular migration processes among the others. In the same spirit, the central idea of this project aims at using AI technology for Search And Rescue (SAR) operations at sea. In particular, we propose an autonomous fleet of self-organizing intelligent drones that would enable the coverage of a broader area, speeding-up the search processes and finally increasing the efficiency and effectiveness of migrants rescue operations. |
| Tasks | |
| Published | 2018-11-13 |
| URL | http://arxiv.org/abs/1811.05291v1 |
| http://arxiv.org/pdf/1811.05291v1.pdf | |
| PWC | https://paperswithcode.com/paper/intelligent-drone-swarm-for-search-and-rescue |
| Repo | |
| Framework | |
Guiding the One-to-one Mapping in CycleGAN via Optimal Transport
| Title | Guiding the One-to-one Mapping in CycleGAN via Optimal Transport |
| Authors | Guansong Lu, Zhiming Zhou, Yuxuan Song, Kan Ren, Yong Yu |
| Abstract | CycleGAN is capable of learning a one-to-one mapping between two data distributions without paired examples, achieving the task of unsupervised data translation. However, there is no theoretical guarantee on the property of the learned one-to-one mapping in CycleGAN. In this paper, we experimentally find that, under some circumstances, the one-to-one mapping learned by CycleGAN is just a random one within the large feasible solution space. Based on this observation, we explore to add extra constraints such that the one-to-one mapping is controllable and satisfies more properties related to specific tasks. We propose to solve an optimal transport mapping restrained by a task-specific cost function that reflects the desired properties, and use the barycenters of optimal transport mapping to serve as references for CycleGAN. Our experiments indicate that the proposed algorithm is capable of learning a one-to-one mapping with the desired properties. |
| Tasks | |
| Published | 2018-11-15 |
| URL | http://arxiv.org/abs/1811.06284v1 |
| http://arxiv.org/pdf/1811.06284v1.pdf | |
| PWC | https://paperswithcode.com/paper/guiding-the-one-to-one-mapping-in-cyclegan |
| Repo | |
| Framework | |
On the Direction of Discrimination: An Information-Theoretic Analysis of Disparate Impact in Machine Learning
| Title | On the Direction of Discrimination: An Information-Theoretic Analysis of Disparate Impact in Machine Learning |
| Authors | Hao Wang, Berk Ustun, Flavio P. Calmon |
| Abstract | In the context of machine learning, disparate impact refers to a form of systematic discrimination whereby the output distribution of a model depends on the value of a sensitive attribute (e.g., race or gender). In this paper, we propose an information-theoretic framework to analyze the disparate impact of a binary classification model. We view the model as a fixed channel, and quantify disparate impact as the divergence in output distributions over two groups. Our aim is to find a correction function that can perturb the input distributions of each group to align their output distributions. We present an optimization problem that can be solved to obtain a correction function that will make the output distributions statistically indistinguishable. We derive closed-form expressions to efficiently compute the correction function, and demonstrate the benefits of our framework on a recidivism prediction problem based on the ProPublica COMPAS dataset. |
| Tasks | |
| Published | 2018-01-16 |
| URL | http://arxiv.org/abs/1801.05398v3 |
| http://arxiv.org/pdf/1801.05398v3.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-direction-of-discrimination-an |
| Repo | |
| Framework | |
Vision System for AGI: Problems and Directions
| Title | Vision System for AGI: Problems and Directions |
| Authors | Alexey Potapov, Sergey Rodionov, Maxim Peterson, Oleg Shcherbakov, Innokentii Zhdanov, Nikolai Skorobogatko |
| Abstract | What frameworks and architectures are necessary to create a vision system for AGI? In this paper, we propose a formal model that states the task of perception within AGI. We show the role of discriminative and generative models in achieving efficient and general solution of this task, thus specifying the task in more detail. We discuss some existing generative and discriminative models and demonstrate their insufficiency for our purposes. Finally, we discuss some architectural dilemmas and open questions. |
| Tasks | |
| Published | 2018-07-10 |
| URL | http://arxiv.org/abs/1807.03887v1 |
| http://arxiv.org/pdf/1807.03887v1.pdf | |
| PWC | https://paperswithcode.com/paper/vision-system-for-agi-problems-and-directions |
| Repo | |
| Framework | |
Dilated DenseNets for Relational Reasoning
| Title | Dilated DenseNets for Relational Reasoning |
| Authors | Antreas Antoniou, Agnieszka Słowik, Elliot J. Crowley, Amos Storkey |
| Abstract | Despite their impressive performance in many tasks, deep neural networks often struggle at relational reasoning. This has recently been remedied with the introduction of a plug-in relational module that considers relations between pairs of objects. Unfortunately, this is combinatorially expensive. In this extended abstract, we show that a DenseNet incorporating dilated convolutions excels at relational reasoning on the Sort-of-CLEVR dataset, allowing us to forgo this relational module and its associated expense. |
| Tasks | Relational Reasoning |
| Published | 2018-11-01 |
| URL | http://arxiv.org/abs/1811.00410v1 |
| http://arxiv.org/pdf/1811.00410v1.pdf | |
| PWC | https://paperswithcode.com/paper/dilated-densenets-for-relational-reasoning |
| Repo | |
| Framework | |
Robust high dimensional factor models with applications to statistical machine learning
| Title | Robust high dimensional factor models with applications to statistical machine learning |
| Authors | Jianqing Fan, Kaizheng Wang, Yiqiao Zhong, Ziwei Zhu |
| Abstract | Factor models are a class of powerful statistical models that have been widely used to deal with dependent measurements that arise frequently from various applications from genomics and neuroscience to economics and finance. As data are collected at an ever-growing scale, statistical machine learning faces some new challenges: high dimensionality, strong dependence among observed variables, heavy-tailed variables and heterogeneity. High-dimensional robust factor analysis serves as a powerful toolkit to conquer these challenges. This paper gives a selective overview on recent advance on high-dimensional factor models and their applications to statistics including Factor-Adjusted Robust Model selection (FarmSelect) and Factor-Adjusted Robust Multiple testing (FarmTest). We show that classical methods, especially principal component analysis (PCA), can be tailored to many new problems and provide powerful tools for statistical estimation and inference. We highlight PCA and its connections to matrix perturbation theory, robust statistics, random projection, false discovery rate, etc., and illustrate through several applications how insights from these fields yield solutions to modern challenges. We also present far-reaching connections between factor models and popular statistical learning problems, including network analysis and low-rank matrix recovery. |
| Tasks | Model Selection |
| Published | 2018-08-12 |
| URL | http://arxiv.org/abs/1808.03889v1 |
| http://arxiv.org/pdf/1808.03889v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-high-dimensional-factor-models-with |
| Repo | |
| Framework | |
Story Understanding in Video Advertisements
| Title | Story Understanding in Video Advertisements |
| Authors | Keren Ye, Kyle Buettner, Adriana Kovashka |
| Abstract | In order to resonate with the viewers, many video advertisements explore creative narrative techniques such as “Freytag’s pyramid” where a story begins with exposition, followed by rising action, then climax, concluding with denouement. In the dramatic structure of ads in particular, climax depends on changes in sentiment. We dedicate our study to understand the dynamic structure of video ads automatically. To achieve this, we first crowdsource climax annotations on 1,149 videos from the Video Ads Dataset, which already provides sentiment annotations. We then use both unsupervised and supervised methods to predict the climax. Based on the predicted peak, the low-level visual and audio cues, and semantically meaningful context features, we build a sentiment prediction model that outperforms the current state-of-the-art model of sentiment prediction in video ads by 25%. In our ablation study, we show that using our context features, and modeling dynamics with an LSTM, are both crucial factors for improved performance. |
| Tasks | |
| Published | 2018-07-29 |
| URL | http://arxiv.org/abs/1807.11122v1 |
| http://arxiv.org/pdf/1807.11122v1.pdf | |
| PWC | https://paperswithcode.com/paper/story-understanding-in-video-advertisements |
| Repo | |
| Framework | |
Impact of Sentiment Detection to Recognize Toxic and Subversive Online Comments
| Title | Impact of Sentiment Detection to Recognize Toxic and Subversive Online Comments |
| Authors | Éloi Brassard-Gourdeau, Richard Khoury |
| Abstract | The presence of toxic content has become a major problem for many online communities. Moderators try to limit this problem by implementing more and more refined comment filters, but toxic users are constantly finding new ways to circumvent them. Our hypothesis is that while modifying toxic content and keywords to fool filters can be easy, hiding sentiment is harder. In this paper, we explore various aspects of sentiment detection and their correlation to toxicity, and use our results to implement a toxicity detection tool. We then test how adding the sentiment information helps detect toxicity in three different real-world datasets, and incorporate subversion to these datasets to simulate a user trying to circumvent the system. Our results show sentiment information has a positive impact on toxicity detection against a subversive user. |
| Tasks | |
| Published | 2018-12-04 |
| URL | http://arxiv.org/abs/1812.01704v1 |
| http://arxiv.org/pdf/1812.01704v1.pdf | |
| PWC | https://paperswithcode.com/paper/impact-of-sentiment-detection-to-recognize |
| Repo | |
| Framework | |
