Paper Group ANR 206
Deep, Convolutional, and Recurrent Models for Human Activity Recognition using Wearables. Notes on a model for fuzzy computing. Depth from a Single Image by Harmonizing Overcomplete Local Network Predictions. Relations such as Hypernymy: Identifying and Exploiting Hearst Patterns in Distributional Vectors for Lexical Entailment. Who did What: A Lar …
Deep, Convolutional, and Recurrent Models for Human Activity Recognition using Wearables
| Title | Deep, Convolutional, and Recurrent Models for Human Activity Recognition using Wearables |
| Authors | Nils Y. Hammerla, Shane Halloran, Thomas Ploetz |
| Abstract | Human activity recognition (HAR) in ubiquitous computing is beginning to adopt deep learning to substitute for well-established analysis techniques that rely on hand-crafted feature extraction and classification techniques. From these isolated applications of custom deep architectures it is, however, difficult to gain an overview of their suitability for problems ranging from the recognition of manipulative gestures to the segmentation and identification of physical activities like running or ascending stairs. In this paper we rigorously explore deep, convolutional, and recurrent approaches across three representative datasets that contain movement data captured with wearable sensors. We describe how to train recurrent approaches in this setting, introduce a novel regularisation approach, and illustrate how they outperform the state-of-the-art on a large benchmark dataset. Across thousands of recognition experiments with randomly sampled model configurations we investigate the suitability of each model for different tasks in HAR, explore the impact of hyperparameters using the fANOVA framework, and provide guidelines for the practitioner who wants to apply deep learning in their problem setting. |
| Tasks | Activity Recognition, Human Activity Recognition |
| Published | 2016-04-29 |
| URL | http://arxiv.org/abs/1604.08880v1 |
| http://arxiv.org/pdf/1604.08880v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-convolutional-and-recurrent-models-for |
| Repo | |
| Framework | |
Notes on a model for fuzzy computing
| Title | Notes on a model for fuzzy computing |
| Authors | Vittorio Cafagna, Gianluca Caterina |
| Abstract | In these notes we propose a setting for fuzzy computing in a framework similar to that of well-established theories of computation: boolean, and quantum computing. Our efforts have been directed towards stressing the formal similarities: there is a common pattern underlying these three theories. We tried to conform our approach, as much as possible, to this pattern. This work was part of a project jointly with Professor Vittorio Cafagna. Professor Cafagna passed away unexpectedly in 2007. His intellectual breadth and inspiring passion for mathematics is still very well alive. |
| Tasks | |
| Published | 2016-05-04 |
| URL | http://arxiv.org/abs/1605.01596v1 |
| http://arxiv.org/pdf/1605.01596v1.pdf | |
| PWC | https://paperswithcode.com/paper/notes-on-a-model-for-fuzzy-computing |
| Repo | |
| Framework | |
Depth from a Single Image by Harmonizing Overcomplete Local Network Predictions
| Title | Depth from a Single Image by Harmonizing Overcomplete Local Network Predictions |
| Authors | Ayan Chakrabarti, Jingyu Shao, Gregory Shakhnarovich |
| Abstract | A single color image can contain many cues informative towards different aspects of local geometric structure. We approach the problem of monocular depth estimation by using a neural network to produce a mid-level representation that summarizes these cues. This network is trained to characterize local scene geometry by predicting, at every image location, depth derivatives of different orders, orientations and scales. However, instead of a single estimate for each derivative, the network outputs probability distributions that allow it to express confidence about some coefficients, and ambiguity about others. Scene depth is then estimated by harmonizing this overcomplete set of network predictions, using a globalization procedure that finds a single consistent depth map that best matches all the local derivative distributions. We demonstrate the efficacy of this approach through evaluation on the NYU v2 depth data set. |
| Tasks | Depth Estimation, Monocular Depth Estimation |
| Published | 2016-05-23 |
| URL | http://arxiv.org/abs/1605.07081v2 |
| http://arxiv.org/pdf/1605.07081v2.pdf | |
| PWC | https://paperswithcode.com/paper/depth-from-a-single-image-by-harmonizing |
| Repo | |
| Framework | |
Relations such as Hypernymy: Identifying and Exploiting Hearst Patterns in Distributional Vectors for Lexical Entailment
| Title | Relations such as Hypernymy: Identifying and Exploiting Hearst Patterns in Distributional Vectors for Lexical Entailment |
| Authors | Stephen Roller, Katrin Erk |
| Abstract | We consider the task of predicting lexical entailment using distributional vectors. We perform a novel qualitative analysis of one existing model which was previously shown to only measure the prototypicality of word pairs. We find that the model strongly learns to identify hypernyms using Hearst patterns, which are well known to be predictive of lexical relations. We present a novel model which exploits this behavior as a method of feature extraction in an iterative procedure similar to Principal Component Analysis. Our model combines the extracted features with the strengths of other proposed models in the literature, and matches or outperforms prior work on multiple data sets. |
| Tasks | |
| Published | 2016-05-18 |
| URL | http://arxiv.org/abs/1605.05433v2 |
| http://arxiv.org/pdf/1605.05433v2.pdf | |
| PWC | https://paperswithcode.com/paper/relations-such-as-hypernymy-identifying-and |
| Repo | |
| Framework | |
Who did What: A Large-Scale Person-Centered Cloze Dataset
| Title | Who did What: A Large-Scale Person-Centered Cloze Dataset |
| Authors | Takeshi Onishi, Hai Wang, Mohit Bansal, Kevin Gimpel, David McAllester |
| Abstract | We have constructed a new “Who-did-What” dataset of over 200,000 fill-in-the-gap (cloze) multiple choice reading comprehension problems constructed from the LDC English Gigaword newswire corpus. The WDW dataset has a variety of novel features. First, in contrast with the CNN and Daily Mail datasets (Hermann et al., 2015) we avoid using article summaries for question formation. Instead, each problem is formed from two independent articles — an article given as the passage to be read and a separate article on the same events used to form the question. Second, we avoid anonymization — each choice is a person named entity. Third, the problems have been filtered to remove a fraction that are easily solved by simple baselines, while remaining 84% solvable by humans. We report performance benchmarks of standard systems and propose the WDW dataset as a challenge task for the community. |
| Tasks | Reading Comprehension |
| Published | 2016-08-19 |
| URL | http://arxiv.org/abs/1608.05457v1 |
| http://arxiv.org/pdf/1608.05457v1.pdf | |
| PWC | https://paperswithcode.com/paper/who-did-what-a-large-scale-person-centered |
| Repo | |
| Framework | |
Implicit Tubular Surface Generation Guided by Centerline
| Title | Implicit Tubular Surface Generation Guided by Centerline |
| Authors | Haoyin Zhou, James K. Min, Guanglei Xiong |
| Abstract | Most machine learning-based coronary artery segmentation methods represent the vascular lumen surface in an implicit way by the centerline and the associated lumen radii, which makes the subsequent modeling process to generate a whole piece of watertight coronary artery tree model difficult. To solve this problem, in this paper, we propose a modeling method with the learning-based segmentation results by (1) considering mesh vertices as physical particles and using interaction force model and particle expansion model to generate uniformly distributed point cloud on the implicit lumen surface and; (2) doing incremental Delaunay-based triangulation. Our method has the advantage of being able to consider the complex shape of the coronary artery tree as a whole piece; hence no extra stitching or intersection removal algorithm is needed to generate a watertight model. Experiment results demonstrate that our method is capable of generating high quality mesh model which is highly consistent with the given implicit vascular lumen surface, with an average error of 0.08 mm. |
| Tasks | |
| Published | 2016-06-09 |
| URL | http://arxiv.org/abs/1606.03014v1 |
| http://arxiv.org/pdf/1606.03014v1.pdf | |
| PWC | https://paperswithcode.com/paper/implicit-tubular-surface-generation-guided-by |
| Repo | |
| Framework | |
Unsupervised Image Segmentation using the Deffuant-Weisbuch Model from Social Dynamics
| Title | Unsupervised Image Segmentation using the Deffuant-Weisbuch Model from Social Dynamics |
| Authors | Subhradeep Kayal |
| Abstract | Unsupervised image segmentation algorithms aim at identifying disjoint homogeneous regions in an image, and have been subject to considerable attention in the machine vision community. In this paper, a popular theoretical model with it’s origins in statistical physics and social dynamics, known as the Deffuant-Weisbuch model, is applied to the image segmentation problem. The Deffuant-Weisbuch model has been found to be useful in modelling the evolution of a closed system of interacting agents characterised by their opinions or beliefs, leading to the formation of clusters of agents who share a similar opinion or belief at steady state. In the context of image segmentation, this paper considers a pixel as an agent and it’s colour property as it’s opinion, with opinion updates as per the Deffuant-Weisbuch model. Apart from applying the basic model to image segmentation, this paper incorporates adjacency and neighbourhood information in the model, which factors in the local similarity and smoothness properties of images. Convergence is reached when the number of unique pixel opinions, i.e., the number of colour centres, matches the pre-specified number of clusters. Experiments are performed on a set of images from the Berkeley Image Segmentation Dataset and the results are analysed both qualitatively and quantitatively, which indicate that this simple and intuitive method is promising for image segmentation. To the best of the knowledge of the author, this is the first work where a theoretical model from statistical physics and social dynamics has been successfully applied to image processing. |
| Tasks | Semantic Segmentation |
| Published | 2016-04-15 |
| URL | http://arxiv.org/abs/1604.04393v3 |
| http://arxiv.org/pdf/1604.04393v3.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-image-segmentation-using-the |
| Repo | |
| Framework | |
Diverse Neural Network Learns True Target Functions
| Title | Diverse Neural Network Learns True Target Functions |
| Authors | Bo Xie, Yingyu Liang, Le Song |
| Abstract | Neural networks are a powerful class of functions that can be trained with simple gradient descent to achieve state-of-the-art performance on a variety of applications. Despite their practical success, there is a paucity of results that provide theoretical guarantees on why they are so effective. Lying in the center of the problem is the difficulty of analyzing the non-convex loss function with potentially numerous local minima and saddle points. Can neural networks corresponding to the stationary points of the loss function learn the true target function? If yes, what are the key factors contributing to such nice optimization properties? In this paper, we answer these questions by analyzing one-hidden-layer neural networks with ReLU activation, and show that despite the non-convexity, neural networks with diverse units have no spurious local minima. We bypass the non-convexity issue by directly analyzing the first order optimality condition, and show that the loss can be made arbitrarily small if the minimum singular value of the “extended feature matrix” is large enough. We make novel use of techniques from kernel methods and geometric discrepancy, and identify a new relation linking the smallest singular value to the spectrum of a kernel function associated with the activation function and to the diversity of the units. Our results also suggest a novel regularization function to promote unit diversity for potentially better generalization. |
| Tasks | |
| Published | 2016-11-09 |
| URL | http://arxiv.org/abs/1611.03131v3 |
| http://arxiv.org/pdf/1611.03131v3.pdf | |
| PWC | https://paperswithcode.com/paper/diverse-neural-network-learns-true-target |
| Repo | |
| Framework | |
Distributed Generalized Cross-Validation for Divide-and-Conquer Kernel Ridge Regression and its Asymptotic Optimality
| Title | Distributed Generalized Cross-Validation for Divide-and-Conquer Kernel Ridge Regression and its Asymptotic Optimality |
| Authors | Ganggang Xu, Zuofeng Shang, Guang Cheng |
| Abstract | Tuning parameter selection is of critical importance for kernel ridge regression. To this date, data driven tuning method for divide-and-conquer kernel ridge regression (d-KRR) has been lacking in the literature, which limits the applicability of d-KRR for large data sets. In this paper, by modifying the Generalized Cross-validation (GCV, Wahba, 1990) score, we propose a distributed Generalized Cross-Validation (dGCV) as a data-driven tool for selecting the tuning parameters in d-KRR. Not only the proposed dGCV is computationally scalable for massive data sets, it is also shown, under mild conditions, to be asymptotically optimal in the sense that minimizing the dGCV score is equivalent to minimizing the true global conditional empirical loss of the averaged function estimator, extending the existing optimality results of GCV to the divide-and-conquer framework. |
| Tasks | |
| Published | 2016-12-18 |
| URL | http://arxiv.org/abs/1612.05907v2 |
| http://arxiv.org/pdf/1612.05907v2.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-generalized-cross-validation-for |
| Repo | |
| Framework | |
The ND-IRIS-0405 Iris Image Dataset
| Title | The ND-IRIS-0405 Iris Image Dataset |
| Authors | Kevin W. Bowyer, Patrick J. Flynn |
| Abstract | The Computer Vision Research Lab at the University of Notre Dame began collecting iris images in the spring semester of 2004. The initial data collections used an LG 2200 iris imaging system for image acquisition. Image datasets acquired in 2004-2005 at Notre Dame with this LG 2200 have been used in the ICE 2005 and ICE 2006 iris biometric evaluations. The ICE 2005 iris image dataset has been distributed to over 100 research groups around the world. The purpose of this document is to describe the content of the ND-IRIS-0405 iris image dataset. This dataset is a superset of the iris image datasets used in ICE 2005 and ICE 2006. The ND 2004-2005 iris image dataset contains 64,980 images corresponding to 356 unique subjects, and 712 unique irises. The age range of the subjects is 18 to 75 years old. 158 of the subjects are female, and 198 are male. 250 of the subjects are Caucasian, 82 are Asian, and 24 are other ethnicities. |
| Tasks | |
| Published | 2016-06-15 |
| URL | http://arxiv.org/abs/1606.04853v1 |
| http://arxiv.org/pdf/1606.04853v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-nd-iris-0405-iris-image-dataset |
| Repo | |
| Framework | |
Domain specialization: a post-training domain adaptation for Neural Machine Translation
| Title | Domain specialization: a post-training domain adaptation for Neural Machine Translation |
| Authors | Christophe Servan, Josep Crego, Jean Senellart |
| Abstract | Domain adaptation is a key feature in Machine Translation. It generally encompasses terminology, domain and style adaptation, especially for human post-editing workflows in Computer Assisted Translation (CAT). With Neural Machine Translation (NMT), we introduce a new notion of domain adaptation that we call “specialization” and which is showing promising results both in the learning speed and in adaptation accuracy. In this paper, we propose to explore this approach under several perspectives. |
| Tasks | Domain Adaptation, Machine Translation |
| Published | 2016-12-19 |
| URL | http://arxiv.org/abs/1612.06141v1 |
| http://arxiv.org/pdf/1612.06141v1.pdf | |
| PWC | https://paperswithcode.com/paper/domain-specialization-a-post-training-domain |
| Repo | |
| Framework | |
A Cross-Entropy-based Method to Perform Information-based Feature Selection
| Title | A Cross-Entropy-based Method to Perform Information-based Feature Selection |
| Authors | Pietro Cassara, Alessandro Rozza, Mirco Nanni |
| Abstract | From a machine learning point of view, identifying a subset of relevant features from a real data set can be useful to improve the results achieved by classification methods and to reduce their time and space complexity. To achieve this goal, feature selection methods are usually employed. These approaches assume that the data contains redundant or irrelevant attributes that can be eliminated. In this work, we propose a novel algorithm to manage the optimization problem that is at the foundation of the Mutual Information feature selection methods. Furthermore, our novel approach is able to estimate automatically the number of dimensions to retain. The quality of our method is confirmed by the promising results achieved on standard real data sets. |
| Tasks | Feature Selection |
| Published | 2016-07-25 |
| URL | http://arxiv.org/abs/1607.07186v2 |
| http://arxiv.org/pdf/1607.07186v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-cross-entropy-based-method-to-perform |
| Repo | |
| Framework | |
An optimal algorithm for the Thresholding Bandit Problem
| Title | An optimal algorithm for the Thresholding Bandit Problem |
| Authors | Andrea Locatelli, Maurilio Gutzeit, Alexandra Carpentier |
| Abstract | We study a specific \textit{combinatorial pure exploration stochastic bandit problem} where the learner aims at finding the set of arms whose means are above a given threshold, up to a given precision, and \textit{for a fixed time horizon}. We propose a parameter-free algorithm based on an original heuristic, and prove that it is optimal for this problem by deriving matching upper and lower bounds. To the best of our knowledge, this is the first non-trivial pure exploration setting with \textit{fixed budget} for which optimal strategies are constructed. |
| Tasks | |
| Published | 2016-05-27 |
| URL | http://arxiv.org/abs/1605.08671v1 |
| http://arxiv.org/pdf/1605.08671v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-optimal-algorithm-for-the-thresholding |
| Repo | |
| Framework | |
A Joint Model for Word Embedding and Word Morphology
| Title | A Joint Model for Word Embedding and Word Morphology |
| Authors | Kris Cao, Marek Rei |
| Abstract | This paper presents a joint model for performing unsupervised morphological analysis on words, and learning a character-level composition function from morphemes to word embeddings. Our model splits individual words into segments, and weights each segment according to its ability to predict context words. Our morphological analysis is comparable to dedicated morphological analyzers at the task of morpheme boundary recovery, and also performs better than word-based embedding models at the task of syntactic analogy answering. Finally, we show that incorporating morphology explicitly into character-level models help them produce embeddings for unseen words which correlate better with human judgments. |
| Tasks | Morphological Analysis, Word Embeddings |
| Published | 2016-06-08 |
| URL | http://arxiv.org/abs/1606.02601v1 |
| http://arxiv.org/pdf/1606.02601v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-joint-model-for-word-embedding-and-word |
| Repo | |
| Framework | |
Visualizing textual models with in-text and word-as-pixel highlighting
| Title | Visualizing textual models with in-text and word-as-pixel highlighting |
| Authors | Abram Handler, Su Lin Blodgett, Brendan O’Connor |
| Abstract | We explore two techniques which use color to make sense of statistical text models. One method uses in-text annotations to illustrate a model’s view of particular tokens in particular documents. Another uses a high-level, “words-as-pixels” graphic to display an entire corpus. Together, these methods offer both zoomed-in and zoomed-out perspectives into a model’s understanding of text. We show how these interconnected methods help diagnose a classifier’s poor performance on Twitter slang, and make sense of a topic model on historical political texts. |
| Tasks | |
| Published | 2016-06-20 |
| URL | http://arxiv.org/abs/1606.06352v1 |
| http://arxiv.org/pdf/1606.06352v1.pdf | |
| PWC | https://paperswithcode.com/paper/visualizing-textual-models-with-in-text-and |
| Repo | |
| Framework | |
