May 6, 2019

2666 words 13 mins read

Paper Group ANR 341

Microstructure Representation and Reconstruction of Heterogeneous Materials via Deep Belief Network for Computational Material Design. Automatic and Manual Segmentation of Hippocampus in Epileptic Patients MRI. Towards information based spatiotemporal patterns as a foundation for agent representation in dynamical systems. Batched Lazy Decision Tree …

Microstructure Representation and Reconstruction of Heterogeneous Materials via Deep Belief Network for Computational Material Design


Title	Microstructure Representation and Reconstruction of Heterogeneous Materials via Deep Belief Network for Computational Material Design
Authors	Ruijin Cang, Yaopengxiao Xu, Shaohua Chen, Yongming Liu, Yang Jiao, Max Yi Ren
Abstract	Integrated Computational Materials Engineering (ICME) aims to accelerate optimal design of complex material systems by integrating material science and design automation. For tractable ICME, it is required that (1) a structural feature space be identified to allow reconstruction of new designs, and (2) the reconstruction process be property-preserving. The majority of existing structural presentation schemes rely on the designer’s understanding of specific material systems to identify geometric and statistical features, which could be biased and insufficient for reconstructing physically meaningful microstructures of complex material systems. In this paper, we develop a feature learning mechanism based on convolutional deep belief network to automate a two-way conversion between microstructures and their lower-dimensional feature representations, and to achieves a 1000-fold dimension reduction from the microstructure space. The proposed model is applied to a wide spectrum of heterogeneous material systems with distinct microstructural features including Ti-6Al-4V alloy, Pb63-Sn37 alloy, Fontainebleau sandstone, and Spherical colloids, to produce material reconstructions that are close to the original samples with respect to 2-point correlation functions and mean critical fracture strength. This capability is not achieved by existing synthesis methods that rely on the Markovian assumption of material microstructures.
Tasks	Dimensionality Reduction
Published	2016-12-22
URL	http://arxiv.org/abs/1612.07401v3
PDF	http://arxiv.org/pdf/1612.07401v3.pdf
PWC	https://paperswithcode.com/paper/microstructure-representation-and
Repo
Framework

Automatic and Manual Segmentation of Hippocampus in Epileptic Patients MRI


Title	Automatic and Manual Segmentation of Hippocampus in Epileptic Patients MRI
Authors	Mohammad-Parsa Hosseini, Mohammad-Reza Nazem-Zadeh, Dario Pompili, Kourosh Jafari-Khouzani, Kost Elisevich, Hamid Soltanian-Zadeh
Abstract	The hippocampus is a seminal structure in the most common surgically-treated form of epilepsy. Accurate segmentation of the hippocampus aids in establishing asymmetry regarding size and signal characteristics in order to disclose the likely site of epileptogenicity. With sufficient refinement, it may ultimately aid in the avoidance of invasive monitoring with its expense and risk for the patient. To this end, a reliable and consistent method for segmentation of the hippocampus from magnetic resonance imaging (MRI) is needed. In this work, we present a systematic and statistical analysis approach for evaluation of automated segmentation methods in order to establish one that reliably approximates the results achieved by manual tracing of the hippocampus.
Tasks
Published	2016-10-24
URL	http://arxiv.org/abs/1610.07557v2
PDF	http://arxiv.org/pdf/1610.07557v2.pdf
PWC	https://paperswithcode.com/paper/automatic-and-manual-segmentation-of
Repo
Framework

Towards information based spatiotemporal patterns as a foundation for agent representation in dynamical systems


Title	Towards information based spatiotemporal patterns as a foundation for agent representation in dynamical systems
Authors	Martin Biehl, Takashi Ikegami, Daniel Polani
Abstract	We present some arguments why existing methods for representing agents fall short in applications crucial to artificial life. Using a thought experiment involving a fictitious dynamical systems model of the biosphere we argue that the metabolism, motility, and the concept of counterfactual variation should be compatible with any agent representation in dynamical systems. We then propose an information-theoretic notion of \emph{integrated spatiotemporal patterns} which we believe can serve as the basic building block of an agent definition. We argue that these patterns are capable of solving the problems mentioned before. We also test this in some preliminary experiments.
Tasks	Artificial Life
Published	2016-05-18
URL	http://arxiv.org/abs/1605.05676v1
PDF	http://arxiv.org/pdf/1605.05676v1.pdf
PWC	https://paperswithcode.com/paper/towards-information-based-spatiotemporal
Repo
Framework

Batched Lazy Decision Trees


Title	Batched Lazy Decision Trees
Authors	Mathieu Guillame-Bert, Artur Dubrawski
Abstract	We introduce a batched lazy algorithm for supervised classification using decision trees. It avoids unnecessary visits to irrelevant nodes when it is used to make predictions with either eagerly or lazily trained decision trees. A set of experiments demonstrate that the proposed algorithm can outperform both the conventional and lazy decision tree algorithms in terms of computation time as well as memory consumption, without compromising accuracy.
Tasks
Published	2016-03-08
URL	http://arxiv.org/abs/1603.02578v1
PDF	http://arxiv.org/pdf/1603.02578v1.pdf
PWC	https://paperswithcode.com/paper/batched-lazy-decision-trees
Repo
Framework

Temporal Convolutional Networks: A Unified Approach to Action Segmentation


Title	Temporal Convolutional Networks: A Unified Approach to Action Segmentation
Authors	Colin Lea, Rene Vidal, Austin Reiter, Gregory D. Hager
Abstract	The dominant paradigm for video-based action segmentation is composed of two steps: first, for each frame, compute low-level features using Dense Trajectories or a Convolutional Neural Network that encode spatiotemporal information locally, and second, input these features into a classifier that captures high-level temporal relationships, such as a Recurrent Neural Network (RNN). While often effective, this decoupling requires specifying two separate models, each with their own complexities, and prevents capturing more nuanced long-range spatiotemporal relationships. We propose a unified approach, as demonstrated by our Temporal Convolutional Network (TCN), that hierarchically captures relationships at low-, intermediate-, and high-level time-scales. Our model achieves superior or competitive performance using video or sensor data on three public action segmentation datasets and can be trained in a fraction of the time it takes to train an RNN.
Tasks	action segmentation
Published	2016-08-29
URL	http://arxiv.org/abs/1608.08242v1
PDF	http://arxiv.org/pdf/1608.08242v1.pdf
PWC	https://paperswithcode.com/paper/temporal-convolutional-networks-a-unified
Repo
Framework

Segmental Spatiotemporal CNNs for Fine-grained Action Segmentation


Title	Segmental Spatiotemporal CNNs for Fine-grained Action Segmentation
Authors	Colin Lea, Austin Reiter, Rene Vidal, Gregory D. Hager
Abstract	Joint segmentation and classification of fine-grained actions is important for applications of human-robot interaction, video surveillance, and human skill evaluation. However, despite substantial recent progress in large-scale action classification, the performance of state-of-the-art fine-grained action recognition approaches remains low. We propose a model for action segmentation which combines low-level spatiotemporal features with a high-level segmental classifier. Our spatiotemporal CNN is comprised of a spatial component that uses convolutional filters to capture information about objects and their relationships, and a temporal component that uses large 1D convolutional filters to capture information about how object relationships change across time. These features are used in tandem with a semi-Markov model that models transitions from one action to another. We introduce an efficient constrained segmental inference algorithm for this model that is orders of magnitude faster than the current approach. We highlight the effectiveness of our Segmental Spatiotemporal CNN on cooking and surgical action datasets for which we observe substantially improved performance relative to recent baseline methods.
Tasks	Action Classification, action segmentation, Temporal Action Localization
Published	2016-02-09
URL	http://arxiv.org/abs/1602.02995v4
PDF	http://arxiv.org/pdf/1602.02995v4.pdf
PWC	https://paperswithcode.com/paper/segmental-spatiotemporal-cnns-for-fine
Repo
Framework

Conformalized Kernel Ridge Regression


Title	Conformalized Kernel Ridge Regression
Authors	Evgeny Burnaev, Ivan Nazarov
Abstract	General predictive models do not provide a measure of confidence in predictions without Bayesian assumptions. A way to circumvent potential restrictions is to use conformal methods for constructing non-parametric confidence regions, that offer guarantees regarding validity. In this paper we provide a detailed description of a computationally efficient conformal procedure for Kernel Ridge Regression (KRR), and conduct a comparative numerical study to see how well conformal regions perform against the Bayesian confidence sets. The results suggest that conformalized KRR can yield predictive confidence regions with specified coverage rate, which is essential in constructing anomaly detection systems based on predictive models.
Tasks	Anomaly Detection
Published	2016-09-19
URL	http://arxiv.org/abs/1609.05959v1
PDF	http://arxiv.org/pdf/1609.05959v1.pdf
PWC	https://paperswithcode.com/paper/conformalized-kernel-ridge-regression
Repo
Framework

Detecting Context Dependent Messages in a Conversational Environment


Title	Detecting Context Dependent Messages in a Conversational Environment
Authors	Chaozhuo Li, Yu Wu, Wei Wu, Chen Xing, Zhoujun Li, Ming Zhou
Abstract	While automatic response generation for building chatbot systems has drawn a lot of attention recently, there is limited understanding on when we need to consider the linguistic context of an input text in the generation process. The task is challenging, as messages in a conversational environment are short and informal, and evidence that can indicate a message is context dependent is scarce. After a study of social conversation data crawled from the web, we observed that some characteristics estimated from the responses of messages are discriminative for identifying context dependent messages. With the characteristics as weak supervision, we propose using a Long Short Term Memory (LSTM) network to learn a classifier. Our method carries out text representation and classifier learning in a unified framework. Experimental results show that the proposed method can significantly outperform baseline methods on accuracy of classification.
Tasks	Chatbot
Published	2016-11-02
URL	http://arxiv.org/abs/1611.00483v2
PDF	http://arxiv.org/pdf/1611.00483v2.pdf
PWC	https://paperswithcode.com/paper/detecting-context-dependent-messages-in-a
Repo
Framework

Text authorship identified using the dynamics of word co-occurrence networks


Title	Text authorship identified using the dynamics of word co-occurrence networks
Authors	Camilo Akimushkin, Diego R. Amancio, Osvaldo N. Oliveira Jr
Abstract	The identification of authorship in disputed documents still requires human expertise, which is now unfeasible for many tasks owing to the large volumes of text and authors in practical applications. In this study, we introduce a methodology based on the dynamics of word co-occurrence networks representing written texts to classify a corpus of 80 texts by 8 authors. The texts were divided into sections with equal number of linguistic tokens, from which time series were created for 12 topological metrics. The series were proven to be stationary (p-value>0.05), which permits to use distribution moments as learning attributes. With an optimized supervised learning procedure using a Radial Basis Function Network, 68 out of 80 texts were correctly classified, i.e. a remarkable 85% author matching success rate. Therefore, fluctuations in purely dynamic network metrics were found to characterize authorship, thus opening the way for the description of texts in terms of small evolving networks. Moreover, the approach introduced allows for comparison of texts with diverse characteristics in a simple, fast fashion.
Tasks	Time Series
Published	2016-07-29
URL	http://arxiv.org/abs/1608.01965v1
PDF	http://arxiv.org/pdf/1608.01965v1.pdf
PWC	https://paperswithcode.com/paper/text-authorship-identified-using-the-dynamics
Repo
Framework

DeepVO: A Deep Learning approach for Monocular Visual Odometry


Title	DeepVO: A Deep Learning approach for Monocular Visual Odometry
Authors	Vikram Mohanty, Shubh Agrawal, Shaswat Datta, Arna Ghosh, Vishnu Dutt Sharma, Debashish Chakravarty
Abstract	Deep Learning based techniques have been adopted with precision to solve a lot of standard computer vision problems, some of which are image classification, object detection and segmentation. Despite the widespread success of these approaches, they have not yet been exploited largely for solving the standard perception related problems encountered in autonomous navigation such as Visual Odometry (VO), Structure from Motion (SfM) and Simultaneous Localization and Mapping (SLAM). This paper analyzes the problem of Monocular Visual Odometry using a Deep Learning-based framework, instead of the regular ‘feature detection and tracking’ pipeline approaches. Several experiments were performed to understand the influence of a known/unknown environment, a conventional trackable feature and pre-trained activations tuned for object classification on the network’s ability to accurately estimate the motion trajectory of the camera (or the vehicle). Based on these observations, we propose a Convolutional Neural Network architecture, best suited for estimating the object’s pose under known environment conditions, and displays promising results when it comes to inferring the actual scale using just a single camera in real-time.
Tasks	Autonomous Navigation, Image Classification, Monocular Visual Odometry, Object Classification, Object Detection, Simultaneous Localization and Mapping, Visual Odometry
Published	2016-11-18
URL	http://arxiv.org/abs/1611.06069v1
PDF	http://arxiv.org/pdf/1611.06069v1.pdf
PWC	https://paperswithcode.com/paper/deepvo-a-deep-learning-approach-for-monocular
Repo
Framework

Investigating practical linear temporal difference learning


Title	Investigating practical linear temporal difference learning
Authors	Adam White, Martha White
Abstract	Off-policy reinforcement learning has many applications including: learning from demonstration, learning multiple goal seeking policies in parallel, and representing predictive knowledge. Recently there has been an proliferation of new policy-evaluation algorithms that fill a longstanding algorithmic void in reinforcement learning: combining robustness to off-policy sampling, function approximation, linear complexity, and temporal difference (TD) updates. This paper contains two main contributions. First, we derive two new hybrid TD policy-evaluation algorithms, which fill a gap in this collection of algorithms. Second, we perform an empirical comparison to elicit which of these new linear TD methods should be preferred in different situations, and make concrete suggestions about practical use.
Tasks
Published	2016-02-28
URL	http://arxiv.org/abs/1602.08771v2
PDF	http://arxiv.org/pdf/1602.08771v2.pdf
PWC	https://paperswithcode.com/paper/investigating-practical-linear-temporal
Repo
Framework

Preterm Birth Prediction: Deriving Stable and Interpretable Rules from High Dimensional Data


Title	Preterm Birth Prediction: Deriving Stable and Interpretable Rules from High Dimensional Data
Authors	Truyen Tran, Wei Luo, Dinh Phung, Jonathan Morris, Kristen Rickard, Svetha Venkatesh
Abstract	Preterm births occur at an alarming rate of 10-15%. Preemies have a higher risk of infant mortality, developmental retardation and long-term disabilities. Predicting preterm birth is difficult, even for the most experienced clinicians. The most well-designed clinical study thus far reaches a modest sensitivity of 18.2-24.2% at specificity of 28.6-33.3%. We take a different approach by exploiting databases of normal hospital operations. We aims are twofold: (i) to derive an easy-to-use, interpretable prediction rule with quantified uncertainties, and (ii) to construct accurate classifiers for preterm birth prediction. Our approach is to automatically generate and select from hundreds (if not thousands) of possible predictors using stability-aware techniques. Derived from a large database of 15,814 women, our simplified prediction rule with only 10 items has sensitivity of 62.3% at specificity of 81.5%.
Tasks
Published	2016-07-28
URL	http://arxiv.org/abs/1607.08310v1
PDF	http://arxiv.org/pdf/1607.08310v1.pdf
PWC	https://paperswithcode.com/paper/preterm-birth-prediction-deriving-stable-and
Repo
Framework

On the Difficulty of Selecting Ising Models with Approximate Recovery


Title	On the Difficulty of Selecting Ising Models with Approximate Recovery
Authors	Jonathan Scarlett, Volkan Cevher
Abstract	In this paper, we consider the problem of estimating the underlying graph associated with an Ising model given a number of independent and identically distributed samples. We adopt an \emph{approximate recovery} criterion that allows for a number of missed edges or incorrectly-included edges, in contrast with the widely-studied exact recovery problem. Our main results provide information-theoretic lower bounds on the sample complexity for graph classes imposing constraints on the number of edges, maximal degree, and other properties. We identify a broad range of scenarios where, either up to constant factors or logarithmic factors, our lower bounds match the best known lower bounds for the exact recovery criterion, several of which are known to be tight or near-tight. Hence, in these cases, approximate recovery has a similar difficulty to exact recovery in the minimax sense. Our bounds are obtained via a modification of Fano’s inequality for handling the approximate recovery criterion, along with suitably-designed ensembles of graphs that can broadly be classed into two categories: (i) Those containing graphs that contain several isolated edges or cliques and are thus difficult to distinguish from the empty graph; (ii) Those containing graphs for which certain groups of nodes are highly correlated, thus making it difficult to determine precisely which edges connect them. We support our theoretical results on these ensembles with numerical experiments.
Tasks
Published	2016-02-11
URL	http://arxiv.org/abs/1602.03647v2
PDF	http://arxiv.org/pdf/1602.03647v2.pdf
PWC	https://paperswithcode.com/paper/on-the-difficulty-of-selecting-ising-models
Repo
Framework

Mode-Seeking on Hypergraphs for Robust Geometric Model Fitting


Title	Mode-Seeking on Hypergraphs for Robust Geometric Model Fitting
Authors	Hanzi Wang, Guobao Xiao, Yan Yan, David Suter
Abstract	In this paper, we propose a novel geometric model fitting method, called Mode-Seeking on Hypergraphs (MSH),to deal with multi-structure data even in the presence of severe outliers. The proposed method formulates geometric model fitting as a mode seeking problem on a hypergraph in which vertices represent model hypotheses and hyperedges denote data points. MSH intuitively detects model instances by a simple and effective mode seeking algorithm. In addition to the mode seeking algorithm, MSH includes a similarity measure between vertices on the hypergraph and a weight-aware sampling technique. The proposed method not only alleviates sensitivity to the data distribution, but also is scalable to large scale problems. Experimental results further demonstrate that the proposed method has significant superiority over the state-of-the-art fitting methods on both synthetic data and real images.
Tasks
Published	2016-03-25
URL	http://arxiv.org/abs/1603.07807v1
PDF	http://arxiv.org/pdf/1603.07807v1.pdf
PWC	https://paperswithcode.com/paper/mode-seeking-on-hypergraphs-for-robust
Repo
Framework

Image and Information


Title	Image and Information
Authors	Frank Nielsen
Abstract	A well-known old adage says that {\em “A picture is worth a thousand words!"} (attributed to the Chinese philosopher Confucius ca 500 years BC). But more precisely, what do we mean by information in images? And how can it be retrieved effectively by machines? We briefly highlight these puzzling questions in this column. But first of all, let us start by defining more precisely what is meant by an “Image.”
Tasks
Published	2016-02-03
URL	http://arxiv.org/abs/1602.01228v1
PDF	http://arxiv.org/pdf/1602.01228v1.pdf
PWC	https://paperswithcode.com/paper/image-and-information
Repo
Framework