October 17, 2019

3106 words 15 mins read

Paper Group ANR 759

Paper Group ANR 759

ActiveRemediation: The Search for Lead Pipes in Flint, Michigan. Bringing Order to the Cognitive Fallacy Zoo. Future Semantic Segmentation with Convolutional LSTM. Predictive Learning on Hidden Tree-Structured Ising Models. Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detection. Feature Selection for Unsupervised Doma …

ActiveRemediation: The Search for Lead Pipes in Flint, Michigan

Title ActiveRemediation: The Search for Lead Pipes in Flint, Michigan
Authors Jacob Abernethy, Alex Chojnacki, Arya Farahi, Eric Schwartz, Jared Webb
Abstract We detail our ongoing work in Flint, Michigan to detect pipes made of lead and other hazardous metals. After elevated levels of lead were detected in residents’ drinking water, followed by an increase in blood lead levels in area children, the state and federal governments directed over $125 million to replace water service lines, the pipes connecting each home to the water system. In the absence of accurate records, and with the high cost of determining buried pipe materials, we put forth a number of predictive and procedural tools to aid in the search and removal of lead infrastructure. Alongside these statistical and machine learning approaches, we describe our interactions with government officials in recommending homes for both inspection and replacement, with a focus on the statistical model that adapts to incoming information. Finally, in light of discussions about increased spending on infrastructure development by the federal government, we explore how our approach generalizes beyond Flint to other municipalities nationwide.
Tasks
Published 2018-06-10
URL http://arxiv.org/abs/1806.10692v2
PDF http://arxiv.org/pdf/1806.10692v2.pdf
PWC https://paperswithcode.com/paper/activeremediation-the-search-for-lead-pipes
Repo
Framework

Bringing Order to the Cognitive Fallacy Zoo

Title Bringing Order to the Cognitive Fallacy Zoo
Authors Ardavan S. Nobandegani, William Campoli, Thomas R. Shultz
Abstract In the eyes of a rationalist like Descartes or Spinoza, human reasoning is flawless, marching toward uncovering ultimate truth. A few centuries later, however, culminating in the work of Kahneman and Tversky, human reasoning was portrayed as anything but flawless, filled with numerous misjudgments, biases, and cognitive fallacies. With further investigations, new cognitive fallacies continually emerged, leading to a state of affairs which can fairly be characterized as the cognitive fallacy zoo! In this largely methodological work, we formally present a principled way to bring order to this zoo. We introduce the idea of establishing implication relationships (IRs) between cognitive fallacies, formally characterizing how one fallacy implies another. IR is analogous to, and partly inspired by, the fundamental concept of reduction in computational complexity theory. We present several examples of IRs involving experimentally well-documented cognitive fallacies: base-rate neglect, availability bias, conjunction fallacy, decoy effect, framing effect, and Allais paradox. We conclude by discussing how our work: (i) allows for identifying those pivotal cognitive fallacies whose investigation would be the most rewarding research agenda, and importantly (ii) permits a systematized, guided research program on cognitive fallacies, motivating influential theoretical as well as experimental avenues of future research.
Tasks
Published 2018-10-15
URL http://arxiv.org/abs/1810.06710v1
PDF http://arxiv.org/pdf/1810.06710v1.pdf
PWC https://paperswithcode.com/paper/bringing-order-to-the-cognitive-fallacy-zoo
Repo
Framework

Future Semantic Segmentation with Convolutional LSTM

Title Future Semantic Segmentation with Convolutional LSTM
Authors Seyed shahabeddin Nabavi, Mrigank Rochan, Yang, Wang
Abstract We consider the problem of predicting semantic segmentation of future frames in a video. Given several observed frames in a video, our goal is to predict the semantic segmentation map of future frames that are not yet observed. A reliable solution to this problem is useful in many applications that require real-time decision making, such as autonomous driving. We propose a novel model that uses convolutional LSTM (ConvLSTM) to encode the spatiotemporal information of observed frames for future prediction. We also extend our model to use bidirectional ConvLSTM to capture temporal information in both directions. Our proposed approach outperforms other state-of-the-art methods on the benchmark dataset.
Tasks Autonomous Driving, Decision Making, Future prediction, Semantic Segmentation
Published 2018-07-20
URL http://arxiv.org/abs/1807.07946v1
PDF http://arxiv.org/pdf/1807.07946v1.pdf
PWC https://paperswithcode.com/paper/future-semantic-segmentation-with
Repo
Framework

Predictive Learning on Hidden Tree-Structured Ising Models

Title Predictive Learning on Hidden Tree-Structured Ising Models
Authors Konstantinos E. Nikolakakis, Dionysios S. Kalogerias, Anand D. Sarwate
Abstract We provide high-probability sample complexity guarantees for exact structure recovery and accurate predictive learning using noise-corrupted samples from an acyclic (tree-shaped) graphical model. The hidden variables follow a tree-structured Ising model distribution, whereas the observable variables are generated by a binary symmetric channel taking the hidden variables as its input (flipping each bit independently with some constant probability $q\in [0,1/2)$). This simple model arises naturally in a variety of applications, such as in physics, biology, computer science, and finance. In the absence of noise, the structure learning problem was recently studied by Bresler and Karzand (2018); this paper quantifies how noise in the hidden model impacts the sample complexity of structure learning and marginal distributions’ estimation by proving upper and lower bounds on the sample complexity. Our results generalize state-of-the-art bounds reported in prior work, and they exactly recover the noiseless case ($q=0$). As expected, for any tree with $p$ vertices and probability of incorrect recovery $\delta>0$, the sufficient number of samples remains logarithmic as in the noiseless case, i.e., $\mathcal{O}(\log(p/\delta))$, while the dependence on $q$ is $\mathcal{O}\big( 1/(1-2q)^{4} \big)$ for both aforementioned tasks. We also present a new equivalent of Isserlis’s Theorem for sign-valued tree-structured distributions, yielding a new low-complexity algorithm for higher-order moment estimation.
Tasks
Published 2018-12-11
URL https://arxiv.org/abs/1812.04700v3
PDF https://arxiv.org/pdf/1812.04700v3.pdf
PWC https://paperswithcode.com/paper/predictive-learning-on-hidden-tree-structured
Repo
Framework

Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detection

Title Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detection
Authors Keze Wang, Xiaopeng Yan, Dongyu Zhang, Lei Zhang, Liang Lin
Abstract Though quite challenging, leveraging large-scale unlabeled or partially labeled images in a cost-effective way has increasingly attracted interests for its great importance to computer vision. To tackle this problem, many Active Learning (AL) methods have been developed. However, these methods mainly define their sample selection criteria within a single image context, leading to the suboptimal robustness and impractical solution for large-scale object detection. In this paper, aiming to remedy the drawbacks of existing AL methods, we present a principled Self-supervised Sample Mining (SSM) process accounting for the real challenges in object detection. Specifically, our SSM process concentrates on automatically discovering and pseudo-labeling reliable region proposals for enhancing the object detector via the introduced cross image validation, i.e., pasting these proposals into different labeled images to comprehensively measure their values under different image contexts. By resorting to the SSM process, we propose a new AL framework for gradually incorporating unlabeled or partially labeled data into the model learning while minimizing the annotating effort of users. Extensive experiments on two public benchmarks clearly demonstrate our proposed framework can achieve the comparable performance to the state-of-the-art methods with significantly fewer annotations.
Tasks Active Learning, Object Detection
Published 2018-03-27
URL http://arxiv.org/abs/1803.09867v2
PDF http://arxiv.org/pdf/1803.09867v2.pdf
PWC https://paperswithcode.com/paper/towards-human-machine-cooperation-self
Repo
Framework

Feature Selection for Unsupervised Domain Adaptation using Optimal Transport

Title Feature Selection for Unsupervised Domain Adaptation using Optimal Transport
Authors Léo Gautheron, Ievgen Redko, Carole Lartizien
Abstract In this paper, we propose a new feature selection method for unsupervised domain adaptation based on the emerging optimal transportation theory. We build upon a recent theoretical analysis of optimal transport in domain adaptation and show that it can directly suggest a feature selection procedure leveraging the shift between the domains. Based on this, we propose a novel algorithm that aims to sort features by their similarity across the source and target domains, where the order is obtained by analyzing the coupling matrix representing the solution of the proposed optimal transportation problem. We evaluate our method on a well-known benchmark data set and illustrate its capability of selecting correlated features leading to better classification performances. Furthermore, we show that the proposed algorithm can be used as a pre-processing step for existing domain adaptation techniques ensuring an important speed-up in terms of the computational time while maintaining comparable results. Finally, we validate our algorithm on clinical imaging databases for computer-aided diagnosis task with promising results.
Tasks Domain Adaptation, Feature Selection, Unsupervised Domain Adaptation
Published 2018-06-28
URL http://arxiv.org/abs/1806.10861v1
PDF http://arxiv.org/pdf/1806.10861v1.pdf
PWC https://paperswithcode.com/paper/feature-selection-for-unsupervised-domain
Repo
Framework

Tree Edit Distance Learning via Adaptive Symbol Embeddings

Title Tree Edit Distance Learning via Adaptive Symbol Embeddings
Authors Benjamin Paaßen, Claudio Gallicchio, Alessio Micheli, Barbara Hammer
Abstract Metric learning has the aim to improve classification accuracy by learning a distance measure which brings data points from the same class closer together and pushes data points from different classes further apart. Recent research has demonstrated that metric learning approaches can also be applied to trees, such as molecular structures, abstract syntax trees of computer programs, or syntax trees of natural language, by learning the cost function of an edit distance, i.e. the costs of replacing, deleting, or inserting nodes in a tree. However, learning such costs directly may yield an edit distance which violates metric axioms, is challenging to interpret, and may not generalize well. In this contribution, we propose a novel metric learning approach for trees which we call embedding edit distance learning (BEDL) and which learns an edit distance indirectly by embedding the tree nodes as vectors, such that the Euclidean distance between those vectors supports class discrimination. We learn such embeddings by reducing the distance to prototypical trees from the same class and increasing the distance to prototypical trees from different classes. In our experiments, we show that BEDL improves upon the state-of-the-art in metric learning for trees on six benchmark data sets, ranging from computer science over biomedical data to a natural-language processing data set containing over 300,000 nodes.
Tasks Metric Learning
Published 2018-06-13
URL http://arxiv.org/abs/1806.05009v3
PDF http://arxiv.org/pdf/1806.05009v3.pdf
PWC https://paperswithcode.com/paper/tree-edit-distance-learning-via-adaptive-1
Repo
Framework

Learning finite-dimensional coding schemes with nonlinear reconstruction maps

Title Learning finite-dimensional coding schemes with nonlinear reconstruction maps
Authors Jaeho Lee, Maxim Raginsky
Abstract This paper generalizes the Maurer–Pontil framework of finite-dimensional lossy coding schemes to the setting where a high-dimensional random vector is mapped to an element of a compact set of latent representations in a lower-dimensional Euclidean space, and the reconstruction map belongs to a given class of nonlinear maps. Under this setup, which encompasses a broad class of unsupervised representation learning problems, we establish a connection to approximate generative modeling under structural constraints using the tools from the theory of optimal transportation. Next, we consider problem of learning a coding scheme on the basis of a finite collection of training samples and present generalization bounds that hold with high probability. We then illustrate the general theory in the setting where the reconstruction maps are implemented by deep neural nets.
Tasks Representation Learning, Unsupervised Representation Learning
Published 2018-12-23
URL http://arxiv.org/abs/1812.09658v2
PDF http://arxiv.org/pdf/1812.09658v2.pdf
PWC https://paperswithcode.com/paper/learning-finite-dimensional-coding-schemes
Repo
Framework

CapsNet comparative performance evaluation for image classification

Title CapsNet comparative performance evaluation for image classification
Authors Rinat Mukhometzianov, Juan Carrillo
Abstract Image classification has become one of the main tasks in the field of computer vision technologies. In this context, a recent algorithm called CapsNet that implements an approach based on activity vectors and dynamic routing between capsules may overcome some of the limitations of the current state of the art artificial neural networks (ANN) classifiers, such as convolutional neural networks (CNN). In this paper, we evaluated the performance of the CapsNet algorithm in comparison with three well-known classifiers (Fisher-faces, LeNet, and ResNet). We tested the classification accuracy on four datasets with a different number of instances and classes, including images of faces, traffic signs, and everyday objects. The evaluation results show that even for simple architectures, training the CapsNet algorithm requires significant computational resources and its classification performance falls below the average accuracy values of the other three classifiers. However, we argue that CapsNet seems to be a promising new technique for image classification, and further experiments using more robust computation resources and re-fined CapsNet architectures may produce better outcomes.
Tasks Image Classification
Published 2018-05-28
URL http://arxiv.org/abs/1805.11195v1
PDF http://arxiv.org/pdf/1805.11195v1.pdf
PWC https://paperswithcode.com/paper/capsnet-comparative-performance-evaluation
Repo
Framework

The Logical Essentials of Bayesian Reasoning

Title The Logical Essentials of Bayesian Reasoning
Authors Bart Jacobs, Fabio Zanasi
Abstract This chapter offers an accessible introduction to the channel-based approach to Bayesian probability theory. This framework rests on algebraic and logical foundations, inspired by the methodologies of programming language semantics. It offers a uniform, structured and expressive language for describing Bayesian phenomena in terms of familiar programming concepts, like channel, predicate transformation and state transformation. The introduction also covers inference in Bayesian networks, which will be modelled by a suitable calculus of string diagrams.
Tasks
Published 2018-04-03
URL http://arxiv.org/abs/1804.01193v2
PDF http://arxiv.org/pdf/1804.01193v2.pdf
PWC https://paperswithcode.com/paper/the-logical-essentials-of-bayesian-reasoning
Repo
Framework

PSO-based Fuzzy Markup Language for Student Learning Performance Evaluation and Educational Application

Title PSO-based Fuzzy Markup Language for Student Learning Performance Evaluation and Educational Application
Authors Chang-Shing Lee, Mei-Hui Wang, Chi-Shiang Wang, Olivier Teytaud, Jialin Liu, Su-Wei Lin, Pi-Hsia Hung
Abstract This paper proposes an agent with particle swarm optimization (PSO) based on a Fuzzy Markup Language (FML) for students learning performance evaluation and educational applications, and the proposed agent is according to the response data from a conventional test and an item response theory. First, we apply a GS-based parameter estimation mechanism to estimate the items parameters according to the response data, and then to compare its results with those of an IRT-based Bayesian parameter estimation mechanism. In addition, we propose a static-IRT test assembly mechanism to assemble a form for the conventional test. The presented FML-based dynamic assessment mechanism infers the probability of making a correct response to the item for a student with various abilities. Moreover, this paper also proposes a novel PFML learning mechanism for optimizing the parameters between items and students. Finally, we adopt a K-fold cross validation mechanism to evaluate the performance of the proposed agent. Experimental results show that the novel PFML learning mechanism for the parameter estimation and learning optimization performs favorably. We believe the proposed PFML will be a reference for education research and pedagogy and an important co-learning mechanism for future human-machine educational applications.
Tasks
Published 2018-02-24
URL http://arxiv.org/abs/1802.08822v1
PDF http://arxiv.org/pdf/1802.08822v1.pdf
PWC https://paperswithcode.com/paper/pso-based-fuzzy-markup-language-for-student
Repo
Framework

Where is my Device? - Detecting the Smart Device’s Wearing Location in the Context of Active Safety for Vulnerable Road Users

Title Where is my Device? - Detecting the Smart Device’s Wearing Location in the Context of Active Safety for Vulnerable Road Users
Authors Maarten Bieshaar
Abstract This article describes an approach to detect the wearing location of smart devices worn by pedestrians and cyclists. The detection, which is based solely on the sensors of the smart devices, is important context-information which can be used to parametrize subsequent algorithms, e.g. for dead reckoning or intention detection to improve the safety of vulnerable road users. The wearing location recognition can in terms of Organic Computing (OC) be seen as a step towards self-awareness and self-adaptation. For the wearing location detection a two-stage process is presented. It is subdivided into moving detection followed by the wearing location classification. Finally, the approach is evaluated on a real world dataset consisting of pedestrians and cyclists.
Tasks
Published 2018-03-06
URL http://arxiv.org/abs/1803.02097v1
PDF http://arxiv.org/pdf/1803.02097v1.pdf
PWC https://paperswithcode.com/paper/where-is-my-device-detecting-the-smart
Repo
Framework

Interactive Learning with Corrective Feedback for Policies based on Deep Neural Networks

Title Interactive Learning with Corrective Feedback for Policies based on Deep Neural Networks
Authors Rodrigo Pérez-Dattari, Carlos Celemin, Javier Ruiz-del-Solar, Jens Kober
Abstract Deep Reinforcement Learning (DRL) has become a powerful strategy to solve complex decision making problems based on Deep Neural Networks (DNNs). However, it is highly data demanding, so unfeasible in physical systems for most applications. In this work, we approach an alternative Interactive Machine Learning (IML) strategy for training DNN policies based on human corrective feedback, with a method called Deep COACH (D-COACH). This approach not only takes advantage of the knowledge and insights of human teachers as well as the power of DNNs, but also has no need of a reward function (which sometimes implies the need of external perception for computing rewards). We combine Deep Learning with the COrrective Advice Communicated by Humans (COACH) framework, in which non-expert humans shape policies by correcting the agent’s actions during execution. The D-COACH framework has the potential to solve complex problems without much data or time required. Experimental results validated the efficiency of the framework in three different problems (two simulated, one with a real robot), with state spaces of low and high dimensions, showing the capacity to successfully learn policies for continuous action spaces like in the Car Racing and Cart-Pole problems faster than with DRL.
Tasks Car Racing, Decision Making
Published 2018-09-30
URL http://arxiv.org/abs/1810.00466v1
PDF http://arxiv.org/pdf/1810.00466v1.pdf
PWC https://paperswithcode.com/paper/interactive-learning-with-corrective-feedback
Repo
Framework

Correcting Length Bias in Neural Machine Translation

Title Correcting Length Bias in Neural Machine Translation
Authors Kenton Murray, David Chiang
Abstract We study two problems in neural machine translation (NMT). First, in beam search, whereas a wider beam should in principle help translation, it often hurts NMT. Second, NMT has a tendency to produce translations that are too short. Here, we argue that these problems are closely related and both rooted in label bias. We show that correcting the brevity problem almost eliminates the beam problem; we compare some commonly-used methods for doing this, finding that a simple per-word reward works well; and we introduce a simple and quick way to tune this reward using the perceptron algorithm.
Tasks Machine Translation
Published 2018-08-29
URL http://arxiv.org/abs/1808.10006v2
PDF http://arxiv.org/pdf/1808.10006v2.pdf
PWC https://paperswithcode.com/paper/correcting-length-bias-in-neural-machine
Repo
Framework

Learning Spectral-Spatial-Temporal Features via a Recurrent Convolutional Neural Network for Change Detection in Multispectral Imagery

Title Learning Spectral-Spatial-Temporal Features via a Recurrent Convolutional Neural Network for Change Detection in Multispectral Imagery
Authors Lichao Mou, Lorenzo Bruzzone, Xiao Xiang Zhu
Abstract Change detection is one of the central problems in earth observation and was extensively investigated over recent decades. In this paper, we propose a novel recurrent convolutional neural network (ReCNN) architecture, which is trained to learn a joint spectral-spatial-temporal feature representation in a unified framework for change detection in multispectral images. To this end, we bring together a convolutional neural network (CNN) and a recurrent neural network (RNN) into one end-to-end network. The former is able to generate rich spectral-spatial feature representations, while the latter effectively analyzes temporal dependency in bi-temporal images. In comparison with previous approaches to change detection, the proposed network architecture possesses three distinctive properties: 1) It is end-to-end trainable, in contrast to most existing methods whose components are separately trained or computed; 2) it naturally harnesses spatial information that has been proven to be beneficial to change detection task; 3) it is capable of adaptively learning the temporal dependency between multitemporal images, unlike most of algorithms that use fairly simple operation like image differencing or stacking. As far as we know, this is the first time that a recurrent convolutional network architecture has been proposed for multitemporal remote sensing image analysis. The proposed network is validated on real multispectral data sets. Both visual and quantitative analysis of experimental results demonstrates competitive performance in the proposed mode.
Tasks
Published 2018-03-07
URL http://arxiv.org/abs/1803.02642v1
PDF http://arxiv.org/pdf/1803.02642v1.pdf
PWC https://paperswithcode.com/paper/learning-spectral-spatial-temporal-features
Repo
Framework
comments powered by Disqus