July 28, 2019

2775 words 14 mins read

Paper Group ANR 269

Learning Belief Network Structure From Data under Causal Insufficiency. Neural network identification of people hidden from view with a single-pixel, single-photon detector. Classification of Major Depressive Disorder via Multi-Site Weighted LASSO Model. Octopus: A Framework for Cost-Quality-Time Optimization in Crowdsourcing. Value Directed Explor …

Learning Belief Network Structure From Data under Causal Insufficiency


Title	Learning Belief Network Structure From Data under Causal Insufficiency
Authors	Mieczysław Kłopotek
Abstract	Though a belief network (a representation of the joint probability distribution, see [3]) and a causal network (a representation of causal relationships [14]) are intended to mean different things, they are closely related. Both assume an underlying dag (directed acyclic graph) structure of relations among variables and if Markov condition and faithfulness condition [15] are met, then a causal network is in fact a belief network. The difference comes to appearance when we recover belief network and causal network structure from data. A causal network structure may be impossible to recover completely from data as not all directions of causal links may be uniquely determined [15]. Fortunately, if we deal with causally sufficient sets of variables (that is whenever significant influence variables are not omitted from observation), then there exists the possibility to identify the family of belief networks a causal network belongs to [16]. Regrettably, to our knowledge, a similar result is not directly known for causally insufficient sets of variables. Spirtes, Glymour and Scheines developed a CI algorithm to handle this situation, but it leaves some important questions open. The big open question is whether or not the bidirectional edges (that is indications of a common cause) are the only ones necessary to develop a belief network out of the product of CI, or must there be some other hidden variables added (e.g. by guessing). This paper is devoted to settling this question.
Tasks
Published	2017-05-29
URL	http://arxiv.org/abs/1705.10308v1
PDF	http://arxiv.org/pdf/1705.10308v1.pdf
PWC	https://paperswithcode.com/paper/learning-belief-network-structure-from-data
Repo
Framework

Neural network identification of people hidden from view with a single-pixel, single-photon detector


Title	Neural network identification of people hidden from view with a single-pixel, single-photon detector
Authors	Piergiorgio Caramazza, Alessandro Boccolini, Daniel Buschek, Matthias Hullin, Catherine Higham, Robert Henderson, Roderick Murray-Smith, Daniele Faccio
Abstract	Light scattered from multiple surfaces can be used to retrieve information of hidden environments. However, full three-dimensional retrieval of an object hidden from view by a wall has only been achieved with scanning systems and requires intensive computational processing of the retrieved data. Here we use a non-scanning, single-photon single-pixel detector in combination with an artificial neural network: this allows us to locate the position and to also simultaneously provide the actual identity of a hidden person, chosen from a database of people (N=3). Artificial neural networks applied to specific computational imaging problems can therefore enable novel imaging capabilities with hugely simplified hardware and processing times
Tasks
Published	2017-09-21
URL	http://arxiv.org/abs/1709.07244v1
PDF	http://arxiv.org/pdf/1709.07244v1.pdf
PWC	https://paperswithcode.com/paper/neural-network-identification-of-people
Repo
Framework

Classification of Major Depressive Disorder via Multi-Site Weighted LASSO Model


Title	Classification of Major Depressive Disorder via Multi-Site Weighted LASSO Model
Authors	Dajiang Zhu, Brandalyn C. Riedel, Neda Jahanshad, Nynke A. Groenewold, Dan J. Stein, Ian H. Gotlib, Matthew D. Sacchet, Danai Dima, James H. Cole, Cynthia H. Y. Fu, Henrik Walter, Ilya M. Veer, Thomas Frodl, Lianne Schmaal, Dick J. Veltman, Paul M. Thompson
Abstract	Large-scale collaborative analysis of brain imaging data, in psychiatry and neu-rology, offers a new source of statistical power to discover features that boost ac-curacy in disease classification, differential diagnosis, and outcome prediction. However, due to data privacy regulations or limited accessibility to large datasets across the world, it is challenging to efficiently integrate distributed information. Here we propose a novel classification framework through multi-site weighted LASSO: each site performs an iterative weighted LASSO for feature selection separately. Within each iteration, the classification result and the selected features are collected to update the weighting parameters for each feature. This new weight is used to guide the LASSO process at the next iteration. Only the fea-tures that help to improve the classification accuracy are preserved. In tests on da-ta from five sites (299 patients with major depressive disorder (MDD) and 258 normal controls), our method boosted classification accuracy for MDD by 4.9% on average. This result shows the potential of the proposed new strategy as an ef-fective and practical collaborative platform for machine learning on large scale distributed imaging and biobank data.
Tasks	Feature Selection
Published	2017-05-26
URL	http://arxiv.org/abs/1705.10312v2
PDF	http://arxiv.org/pdf/1705.10312v2.pdf
PWC	https://paperswithcode.com/paper/classification-of-major-depressive-disorder
Repo
Framework

Octopus: A Framework for Cost-Quality-Time Optimization in Crowdsourcing


Title	Octopus: A Framework for Cost-Quality-Time Optimization in Crowdsourcing
Authors	Karan Goel, Shreya Rajpal, Mausam
Abstract	We present Octopus, an AI agent to jointly balance three conflicting task objectives on a micro-crowdsourcing marketplace - the quality of work, total cost incurred, and time to completion. Previous control agents have mostly focused on cost-quality, or cost-time tradeoffs, but not on directly controlling all three in concert. A naive formulation of three-objective optimization is intractable; Octopus takes a hierarchical POMDP approach, with three different components responsible for setting the pay per task, selecting the next task, and controlling task-level quality. We demonstrate that Octopus significantly outperforms existing state-of-the-art approaches on real experiments. We also deploy Octopus on Amazon Mechanical Turk, showing its ability to manage tasks in a real-world dynamic setting.
Tasks
Published	2017-02-12
URL	http://arxiv.org/abs/1702.03488v2
PDF	http://arxiv.org/pdf/1702.03488v2.pdf
PWC	https://paperswithcode.com/paper/octopus-a-framework-for-cost-quality-time
Repo
Framework

Value Directed Exploration in Multi-Armed Bandits with Structured Priors


Title	Value Directed Exploration in Multi-Armed Bandits with Structured Priors
Authors	Bence Cserna, Marek Petrik, Reazul Hasan Russel, Wheeler Ruml
Abstract	Multi-armed bandits are a quintessential machine learning problem requiring the balancing of exploration and exploitation. While there has been progress in developing algorithms with strong theoretical guarantees, there has been less focus on practical near-optimal finite-time performance. In this paper, we propose an algorithm for Bayesian multi-armed bandits that utilizes value-function-driven online planning techniques. Building on previous work on UCB and Gittins index, we introduce linearly-separable value functions that take both the expected return and the benefit of exploration into consideration to perform n-step lookahead. The algorithm enjoys a sub-linear performance guarantee and we present simulation results that confirm its strength in problems with structured priors. The simplicity and generality of our approach makes it a strong candidate for analyzing more complex multi-armed bandit problems.
Tasks	Multi-Armed Bandits
Published	2017-04-12
URL	http://arxiv.org/abs/1704.03926v2
PDF	http://arxiv.org/pdf/1704.03926v2.pdf
PWC	https://paperswithcode.com/paper/value-directed-exploration-in-multi-armed
Repo
Framework

Computational Machines in a Coexistence with Concrete Universals and Data Streams


Title	Computational Machines in a Coexistence with Concrete Universals and Data Streams
Authors	Vahid Moosavi
Abstract	We discuss that how the majority of traditional modeling approaches are following the idealism point of view in scientific modeling, which follow the set theoretical notions of models based on abstract universals. We show that while successful in many classical modeling domains, there are fundamental limits to the application of set theoretical models in dealing with complex systems with many potential aspects or properties depending on the perspectives. As an alternative to abstract universals, we propose a conceptual modeling framework based on concrete universals that can be interpreted as a category theoretical approach to modeling. We call this modeling framework pre-specific modeling. We further, discuss how a certain group of mathematical and computational methods, along with ever-growing data streams are able to operationalize the concept of pre-specific modeling.
Tasks
Published	2017-09-10
URL	http://arxiv.org/abs/1709.03136v1
PDF	http://arxiv.org/pdf/1709.03136v1.pdf
PWC	https://paperswithcode.com/paper/computational-machines-in-a-coexistence-with
Repo
Framework

A Study of Deep Learning Robustness Against Computation Failures


Title	A Study of Deep Learning Robustness Against Computation Failures
Authors	Jean-Charles Vialatte, François Leduc-Primeau
Abstract	For many types of integrated circuits, accepting larger failure rates in computations can be used to improve energy efficiency. We study the performance of faulty implementations of certain deep neural networks based on pessimistic and optimistic models of the effect of hardware faults. After identifying the impact of hyperparameters such as the number of layers on robustness, we study the ability of the network to compensate for computational failures through an increase of the network size. We show that some networks can achieve equivalent performance under faulty implementations, and quantify the required increase in computational complexity.
Tasks
Published	2017-04-18
URL	http://arxiv.org/abs/1704.05396v1
PDF	http://arxiv.org/pdf/1704.05396v1.pdf
PWC	https://paperswithcode.com/paper/a-study-of-deep-learning-robustness-against
Repo
Framework

von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification


Title	von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification
Authors	Md. Abul Hasnat, Julien Bohné, Jonathan Milgram, Stéphane Gentric, Liming Chen
Abstract	A number of pattern recognition tasks, \textit{e.g.}, face verification, can be boiled down to classification or clustering of unit length directional feature vectors whose distance can be simply computed by their angle. In this paper, we propose the von Mises-Fisher (vMF) mixture model as the theoretical foundation for an effective deep-learning of such directional features and derive a novel vMF Mixture Loss and its corresponding vMF deep features. The proposed vMF feature learning achieves the characteristics of discriminative learning, \textit{i.e.}, compacting the instances of the same class while increasing the distance of instances from different classes. Moreover, it subsumes a number of popular loss functions as well as an effective method in deep learning, namely normalization. We conduct extensive experiments on face verification using 4 different challenging face datasets, \textit{i.e.}, LFW, YouTube faces, CACD and IJB-A. Results show the effectiveness and excellent generalization ability of the proposed approach as it achieves state-of-the-art results on the LFW, YouTube faces and CACD datasets and competitive results on the IJB-A dataset.
Tasks	Face Verification
Published	2017-06-13
URL	http://arxiv.org/abs/1706.04264v2
PDF	http://arxiv.org/pdf/1706.04264v2.pdf
PWC	https://paperswithcode.com/paper/von-mises-fisher-mixture-model-based-deep
Repo
Framework

Deep neural networks on graph signals for brain imaging analysis


Title	Deep neural networks on graph signals for brain imaging analysis
Authors	Yiluan Guo, Hossein Nejati, Ngai-Man Cheung
Abstract	Brain imaging data such as EEG or MEG are high-dimensional spatiotemporal data often degraded by complex, non-Gaussian noise. For reliable analysis of brain imaging data, it is important to extract discriminative, low-dimensional intrinsic representation of the recorded data. This work proposes a new method to learn the low-dimensional representations from the noise-degraded measurements. In particular, our work proposes a new deep neural network design that integrates graph information such as brain connectivity with fully-connected layers. Our work leverages efficient graph filter design using Chebyshev polynomial and recent work on convolutional nets on graph-structured data. Our approach exploits graph structure as the prior side information, localized graph filter for feature extraction and neural networks for high capacity learning. Experiments on real MEG datasets show that our approach can extract more discriminative representations, leading to improved accuracy in a supervised classification task.
Tasks	EEG
Published	2017-05-13
URL	http://arxiv.org/abs/1705.04828v1
PDF	http://arxiv.org/pdf/1705.04828v1.pdf
PWC	https://paperswithcode.com/paper/deep-neural-networks-on-graph-signals-for
Repo
Framework

Object-oriented Neural Programming (OONP) for Document Understanding


Title	Object-oriented Neural Programming (OONP) for Document Understanding
Authors	Zhengdong Lu, Xianggen Liu, Haotian Cui, Yukun Yan, Daqi Zheng
Abstract	We propose Object-oriented Neural Programming (OONP), a framework for semantically parsing documents in specific domains. Basically, OONP reads a document and parses it into a predesigned object-oriented data structure (referred to as ontology in this paper) that reflects the domain-specific semantics of the document. An OONP parser models semantic parsing as a decision process: a neural net-based Reader sequentially goes through the document, and during the process it builds and updates an intermediate ontology to summarize its partial understanding of the text it covers. OONP supports a rich family of operations (both symbolic and differentiable) for composing the ontology, and a big variety of forms (both symbolic and differentiable) for representing the state and the document. An OONP parser can be trained with supervision of different forms and strength, including supervised learning (SL) , reinforcement learning (RL) and hybrid of the two. Our experiments on both synthetic and real-world document parsing tasks have shown that OONP can learn to handle fairly complicated ontology with training data of modest sizes.
Tasks	Semantic Parsing
Published	2017-09-26
URL	http://arxiv.org/abs/1709.08853v6
PDF	http://arxiv.org/pdf/1709.08853v6.pdf
PWC	https://paperswithcode.com/paper/object-oriented-neural-programming-oonp-for
Repo
Framework

Assumption-Based Approaches to Reasoning with Priorities


Title	Assumption-Based Approaches to Reasoning with Priorities
Authors	Jesse Heyninck, Christian Straßer, Pere Pardo
Abstract	This paper maps out the relation between different approaches for handling preferences in argumentation with strict rules and defeasible assumptions by offering translations between them. The systems we compare are: non-prioritized defeats i.e. attacks, preference-based defeats, and preference-based defeats extended with reverse defeat.
Tasks
Published	2017-09-21
URL	http://arxiv.org/abs/1709.07255v2
PDF	http://arxiv.org/pdf/1709.07255v2.pdf
PWC	https://paperswithcode.com/paper/assumption-based-approaches-to-reasoning-with
Repo
Framework

Model-based Classification and Novelty Detection For Point Pattern Data


Title	Model-based Classification and Novelty Detection For Point Pattern Data
Authors	Ba-Ngu Vo, Quang N. Tran, Dinh Phung, Ba-Tuong Vo
Abstract	Point patterns are sets or multi-sets of unordered elements that can be found in numerous data sources. However, in data analysis tasks such as classification and novelty detection, appropriate statistical models for point pattern data have not received much attention. This paper proposes the modelling of point pattern data via random finite sets (RFS). In particular, we propose appropriate likelihood functions, and a maximum likelihood estimator for learning a tractable family of RFS models. In novelty detection, we propose novel ranking functions based on RFS models, which substantially improve performance.
Tasks
Published	2017-01-30
URL	http://arxiv.org/abs/1701.08473v2
PDF	http://arxiv.org/pdf/1701.08473v2.pdf
PWC	https://paperswithcode.com/paper/model-based-classification-and-novelty
Repo
Framework

HyperNetworks with statistical filtering for defending adversarial examples


Title	HyperNetworks with statistical filtering for defending adversarial examples
Authors	Zhun Sun, Mete Ozay, Takayuki Okatani
Abstract	Deep learning algorithms have been known to be vulnerable to adversarial perturbations in various tasks such as image classification. This problem was addressed by employing several defense methods for detection and rejection of particular types of attacks. However, training and manipulating networks according to particular defense schemes increases computational complexity of the learning algorithms. In this work, we propose a simple yet effective method to improve robustness of convolutional neural networks (CNNs) to adversarial attacks by using data dependent adaptive convolution kernels. To this end, we propose a new type of HyperNetwork in order to employ statistical properties of input data and features for computation of statistical adaptive maps. Then, we filter convolution weights of CNNs with the learned statistical maps to compute dynamic kernels. Thereby, weights and kernels are collectively optimized for learning of image classification models robust to adversarial attacks without employment of additional target detection and rejection algorithms. We empirically demonstrate that the proposed method enables CNNs to spontaneously defend against different types of attacks, e.g. attacks generated by Gaussian noise, fast gradient sign methods (Goodfellow et al., 2014) and a black-box attack(Narodytska & Kasiviswanathan, 2016).
Tasks	Image Classification
Published	2017-11-06
URL	http://arxiv.org/abs/1711.01791v1
PDF	http://arxiv.org/pdf/1711.01791v1.pdf
PWC	https://paperswithcode.com/paper/hypernetworks-with-statistical-filtering-for
Repo
Framework

Spatial-Temporal Union of Subspaces for Multi-body Non-rigid Structure-from-Motion


Title	Spatial-Temporal Union of Subspaces for Multi-body Non-rigid Structure-from-Motion
Authors	Suryansh Kumar, Yuchao Dai, Hongdong Li
Abstract	Non-rigid structure-from-motion (NRSfM) has so far been mostly studied for recovering 3D structure of a single non-rigid/deforming object. To handle the real world challenging multiple deforming objects scenarios, existing methods either pre-segment different objects in the scene or treat multiple non-rigid objects as a whole to obtain the 3D non-rigid reconstruction. However, these methods fail to exploit the inherent structure in the problem as the solution of segmentation and the solution of reconstruction could not benefit each other. In this paper, we propose a unified framework to jointly segment and reconstruct multiple non-rigid objects. To compactly represent complex multi-body non-rigid scenes, we propose to exploit the structure of the scenes along both temporal direction and spatial direction, thus achieving a spatio-temporal representation. Specifically, we represent the 3D non-rigid deformations as lying in a union of subspaces along the temporal direction and represent the 3D trajectories as lying in the union of subspaces along the spatial direction. This spatio-temporal representation not only provides competitive 3D reconstruction but also outputs robust segmentation of multiple non-rigid objects. The resultant optimization problem is solved efficiently using the Alternating Direction Method of Multipliers (ADMM). Extensive experimental results on both synthetic and real multi-body NRSfM datasets demonstrate the superior performance of our proposed framework compared with the state-of-the-art methods.
Tasks	3D Reconstruction
Published	2017-05-14
URL	http://arxiv.org/abs/1705.04916v1
PDF	http://arxiv.org/pdf/1705.04916v1.pdf
PWC	https://paperswithcode.com/paper/spatial-temporal-union-of-subspaces-for-multi
Repo
Framework

Deep Learning for Ontology Reasoning


Title	Deep Learning for Ontology Reasoning
Authors	Patrick Hohenecker, Thomas Lukasiewicz
Abstract	In this work, we present a novel approach to ontology reasoning that is based on deep learning rather than logic-based formal reasoning. To this end, we introduce a new model for statistical relational learning that is built upon deep recursive neural networks, and give experimental evidence that it can easily compete with, or even outperform, existing logic-based reasoners on the task of ontology reasoning. More precisely, we compared our implemented system with one of the best logic-based ontology reasoners at present, RDFox, on a number of large standard benchmark datasets, and found that our system attained high reasoning quality, while being up to two orders of magnitude faster.
Tasks	Relational Reasoning
Published	2017-05-29
URL	http://arxiv.org/abs/1705.10342v1
PDF	http://arxiv.org/pdf/1705.10342v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-ontology-reasoning
Repo
Framework