May 6, 2019

3131 words 15 mins read

Paper Group ANR 235

Hierarchical Modeling of Multidimensional Data in Regularly Decomposed Spaces: Main Principles. Adaptive Neighborhood Graph Construction for Inference in Multi-Relational Networks. Fast, Robust, Continuous Monocular Egomotion Computation. Geometric-Algebra LMS Adaptive Filter and its Application to Rotation Estimation. Beyond Sharing Weights for De …

Hierarchical Modeling of Multidimensional Data in Regularly Decomposed Spaces: Main Principles


Title	Hierarchical Modeling of Multidimensional Data in Regularly Decomposed Spaces: Main Principles
Authors	Olivier Guye
Abstract	The described works have been carried out in the framework of a mid-term study initiated by the Centre Electronique de l’Armement and led by ADERSA, a French company of research under contract. The aim was to study the techniques of regular dividing of numerical data sets so as to provide tools for problem solving enabling to model multidimensional numerical objects and to be used in computer-aided design and manufacturing, in robotics, in image analysis and synthesis, in pattern recognition, in decision making, in cartography and numerical data base management. These tools are relying on the principle of regular hierarchical decomposition and led to the implementation of a multidimensional generalization of quaternary and octernary trees: the trees of order 2k or 2k-trees mapped in binary trees. This first tome, dedicated to the hierarchical modeling of multidimensional numerical data, describes the principles used for building, transforming, analyzing and recognizing patterns on which is relying the development of the associated algorithms. The whole so developed algorithms are detailed in pseudo-code at the end of this document. The present publication especially describes: - a building method adapted disordered and overcrowded data streams ; - its extension in inductive limits ; - the computation of the homographic transformation of a tree ; - the attribute calculus based on generalized moments and the provision of Eigen trees ; - perception procedures of objects without any covering in affine geometry ; - several supervised and unsupervised pattern recognition methods.
Tasks	Decision Making
Published	2016-05-03
URL	http://arxiv.org/abs/1605.00961v2
PDF	http://arxiv.org/pdf/1605.00961v2.pdf
PWC	https://paperswithcode.com/paper/hierarchical-modeling-of-multidimensional-1
Repo
Framework

Adaptive Neighborhood Graph Construction for Inference in Multi-Relational Networks


Title	Adaptive Neighborhood Graph Construction for Inference in Multi-Relational Networks
Authors	Shobeir Fakhraei, Dhanya Sridhar, Jay Pujara, Lise Getoor
Abstract	A neighborhood graph, which represents the instances as vertices and their relations as weighted edges, is the basis of many semi-supervised and relational models for node labeling and link prediction. Most methods employ a sequential process to construct the neighborhood graph. This process often consists of generating a candidate graph, pruning the candidate graph to make a neighborhood graph, and then performing inference on the variables (i.e., nodes) in the neighborhood graph. In this paper, we propose a framework that can dynamically adapt the neighborhood graph based on the states of variables from intermediate inference results, as well as structural properties of the relations connecting them. A key strength of our framework is its ability to handle multi-relational data and employ varying amounts of relations for each instance based on the intermediate inference results. We formulate the link prediction task as inference on neighborhood graphs, and include preliminary results illustrating the effects of different strategies in our proposed framework.
Tasks	graph construction, Link Prediction
Published	2016-07-02
URL	http://arxiv.org/abs/1607.00474v1
PDF	http://arxiv.org/pdf/1607.00474v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-neighborhood-graph-construction-for
Repo
Framework

Fast, Robust, Continuous Monocular Egomotion Computation


Title	Fast, Robust, Continuous Monocular Egomotion Computation
Authors	Andrew Jaegle, Stephen Phillips, Kostas Daniilidis
Abstract	We propose robust methods for estimating camera egomotion in noisy, real-world monocular image sequences in the general case of unknown observer rotation and translation with two views and a small baseline. This is a difficult problem because of the nonconvex cost function of the perspective camera motion equation and because of non-Gaussian noise arising from noisy optical flow estimates and scene non-rigidity. To address this problem, we introduce the expected residual likelihood method (ERL), which estimates confidence weights for noisy optical flow data using likelihood distributions of the residuals of the flow field under a range of counterfactual model parameters. We show that ERL is effective at identifying outliers and recovering appropriate confidence weights in many settings. We compare ERL to a novel formulation of the perspective camera motion equation using a lifted kernel, a recently proposed optimization framework for joint parameter and confidence weight estimation with good empirical properties. We incorporate these strategies into a motion estimation pipeline that avoids falling into local minima. We find that ERL outperforms the lifted kernel method and baseline monocular egomotion estimation strategies on the challenging KITTI dataset, while adding almost no runtime cost over baseline egomotion methods.
Tasks	Motion Estimation, Optical Flow Estimation
Published	2016-02-16
URL	http://arxiv.org/abs/1602.04886v1
PDF	http://arxiv.org/pdf/1602.04886v1.pdf
PWC	https://paperswithcode.com/paper/fast-robust-continuous-monocular-egomotion
Repo
Framework

Geometric-Algebra LMS Adaptive Filter and its Application to Rotation Estimation


Title	Geometric-Algebra LMS Adaptive Filter and its Application to Rotation Estimation
Authors	Wilder B. Lopes, Anas Al-Nuaimi, Cassio G. Lopes
Abstract	This paper exploits Geometric (Clifford) Algebra (GA) theory in order to devise and introduce a new adaptive filtering strategy. From a least-squares cost function, the gradient is calculated following results from Geometric Calculus (GC), the extension of GA to handle differential and integral calculus. The novel GA least-mean-squares (GA-LMS) adaptive filter, which inherits properties from standard adaptive filters and from GA, is developed to recursively estimate a rotor (multivector), a hypercomplex quantity able to describe rotations in any dimension. The adaptive filter (AF) performance is assessed via a 3D point-clouds registration problem, which contains a rotation estimation step. Calculating the AF computational complexity suggests that it can contribute to reduce the cost of a full-blown 3D registration algorithm, especially when the number of points to be processed grows. Moreover, the employed GA/GC framework allows for easily applying the resulting filter to estimating rotors in higher dimensions.
Tasks
Published	2016-01-22
URL	http://arxiv.org/abs/1601.06044v1
PDF	http://arxiv.org/pdf/1601.06044v1.pdf
PWC	https://paperswithcode.com/paper/geometric-algebra-lms-adaptive-filter-and-its
Repo
Framework


Title	Beyond Sharing Weights for Deep Domain Adaptation
Authors	Artem Rozantsev, Mathieu Salzmann, Pascal Fua
Abstract	The performance of a classifier trained on data coming from a specific domain typically degrades when applied to a related but different one. While annotating many samples from the new domain would address this issue, it is often too expensive or impractical. Domain Adaptation has therefore emerged as a solution to this problem; It leverages annotated data from a source domain, in which it is abundant, to train a classifier to operate in a target domain, in which it is either sparse or even lacking altogether. In this context, the recent trend consists of learning deep architectures whose weights are shared for both domains, which essentially amounts to learning domain invariant features. Here, we show that it is more effective to explicitly model the shift from one domain to the other. To this end, we introduce a two-stream architecture, where one operates in the source domain and the other in the target domain. In contrast to other approaches, the weights in corresponding layers are related but not shared. We demonstrate that this both yields higher accuracy than state-of-the-art methods on several object recognition and detection tasks and consistently outperforms networks with shared weights in both supervised and unsupervised settings.
Tasks	Domain Adaptation, Object Recognition
Published	2016-03-21
URL	http://arxiv.org/abs/1603.06432v2
PDF	http://arxiv.org/pdf/1603.06432v2.pdf
PWC	https://paperswithcode.com/paper/beyond-sharing-weights-for-deep-domain
Repo
Framework

Bayesian nonparametrics for Sparse Dynamic Networks


Title	Bayesian nonparametrics for Sparse Dynamic Networks
Authors	Konstantina Palla, Francois Caron, Yee Whye Teh
Abstract	We propose a Bayesian nonparametric prior for time-varying networks. To each node of the network is associated a positive parameter, modeling the sociability of that node. Sociabilities are assumed to evolve over time, and are modeled via a dynamic point process model. The model is able to (a) capture smooth evolution of the interaction between nodes, allowing edges to appear/disappear over time (b) capture long term evolution of the sociabilities of the nodes (c) and yield sparse graphs, where the number of edges grows subquadratically with the number of nodes. The evolution of the sociabilities is described by a tractable time-varying gamma process. We provide some theoretical insights into the model and apply it to three real world datasets.
Tasks
Published	2016-07-06
URL	http://arxiv.org/abs/1607.01624v1
PDF	http://arxiv.org/pdf/1607.01624v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-nonparametrics-for-sparse-dynamic
Repo
Framework

Clustering with Same-Cluster Queries


Title	Clustering with Same-Cluster Queries
Authors	Hassan Ashtiani, Shrinu Kushagra, Shai Ben-David
Abstract	We propose a framework for Semi-Supervised Active Clustering framework (SSAC), where the learner is allowed to interact with a domain expert, asking whether two given instances belong to the same cluster or not. We study the query and computational complexity of clustering in this framework. We consider a setting where the expert conforms to a center-based clustering with a notion of margin. We show that there is a trade off between computational complexity and query complexity; We prove that for the case of $k$-means clustering (i.e., when the expert conforms to a solution of $k$-means), having access to relatively few such queries allows efficient solutions to otherwise NP hard problems. In particular, we provide a probabilistic polynomial-time (BPP) algorithm for clustering in this setting that asks $O\big(k^2\log k + k\log n)$ same-cluster queries and runs with time complexity $O\big(kn\log n)$ (where $k$ is the number of clusters and $n$ is the number of instances). The algorithm succeeds with high probability for data satisfying margin conditions under which, without queries, we show that the problem is NP hard. We also prove a lower bound on the number of queries needed to have a computationally efficient clustering algorithm in this setting.
Tasks
Published	2016-06-08
URL	http://arxiv.org/abs/1606.02404v2
PDF	http://arxiv.org/pdf/1606.02404v2.pdf
PWC	https://paperswithcode.com/paper/clustering-with-same-cluster-queries
Repo
Framework

Extracting Biological Pathway Models From NLP Event Representations


Title	Extracting Biological Pathway Models From NLP Event Representations
Authors	Michael Spranger, Sucheendra K. Palaniappan, Samik Ghosh
Abstract	This paper describes an an open-source software system for the automatic conversion of NLP event representations to system biology structured data interchange formats such as SBML and BioPAX. It is part of a larger effort to make results of the NLP community available for system biology pathway modelers.
Tasks
Published	2016-08-12
URL	http://arxiv.org/abs/1608.03764v1
PDF	http://arxiv.org/pdf/1608.03764v1.pdf
PWC	https://paperswithcode.com/paper/extracting-biological-pathway-models-from-nlp
Repo
Framework

Parametric Object Motion from Blur


Title	Parametric Object Motion from Blur
Authors	Jochen Gast, Anita Sellent, Stefan Roth
Abstract	Motion blur can adversely affect a number of vision tasks, hence it is generally considered a nuisance. We instead treat motion blur as a useful signal that allows to compute the motion of objects from a single image. Drawing on the success of joint segmentation and parametric motion models in the context of optical flow estimation, we propose a parametric object motion model combined with a segmentation mask to exploit localized, non-uniform motion blur. Our parametric image formation model is differentiable w.r.t. the motion parameters, which enables us to generalize marginal-likelihood techniques from uniform blind deblurring to localized, non-uniform blur. A two-stage pipeline, first in derivative space and then in image space, allows to estimate both parametric object motion as well as a motion segmentation from a single image alone. Our experiments demonstrate its ability to cope with very challenging cases of object motion blur.
Tasks	Deblurring, Motion Segmentation, Optical Flow Estimation
Published	2016-04-20
URL	http://arxiv.org/abs/1604.05933v1
PDF	http://arxiv.org/pdf/1604.05933v1.pdf
PWC	https://paperswithcode.com/paper/parametric-object-motion-from-blur
Repo
Framework

Distance Metric Ensemble Learning and the Andrews-Curtis Conjecture


Title	Distance Metric Ensemble Learning and the Andrews-Curtis Conjecture
Authors	Krzysztof Krawiec, Jerry Swan
Abstract	Motivated by the search for a counterexample to the Poincar'e conjecture in three and four dimensions, the Andrews-Curtis conjecture was proposed in 1965. It is now generally suspected that the Andrews-Curtis conjecture is false, but small potential counterexamples are not so numerous, and previous work has attempted to eliminate some via combinatorial search. Progress has however been limited, with the most successful approach (breadth-first-search using secondary storage) being neither scalable nor heuristically-informed. A previous empirical analysis of problem structure examined several heuristic measures of search progress and determined that none of them provided any useful guidance for search. In this article, we induce new quality measures directly from the problem structure and combine them to produce a more effective search driver via ensemble machine learning. By this means, we eliminate 19 potential counterexamples, the status of which had been unknown for some years.
Tasks
Published	2016-06-04
URL	http://arxiv.org/abs/1606.01412v1
PDF	http://arxiv.org/pdf/1606.01412v1.pdf
PWC	https://paperswithcode.com/paper/distance-metric-ensemble-learning-and-the
Repo
Framework

Error-Resilient Machine Learning in Near Threshold Voltage via Classifier Ensemble


Title	Error-Resilient Machine Learning in Near Threshold Voltage via Classifier Ensemble
Authors	Sai Zhang, Naresh Shanbhag
Abstract	In this paper, we present the design of error-resilient machine learning architectures by employing a distributed machine learning framework referred to as classifier ensemble (CE). CE combines several simple classifiers to obtain a strong one. In contrast, centralized machine learning employs a single complex block. We compare the random forest (RF) and the support vector machine (SVM), which are representative techniques from the CE and centralized frameworks, respectively. Employing the dataset from UCI machine learning repository and architectural-level error models in a commercial 45 nm CMOS process, it is demonstrated that RF-based architectures are significantly more robust than SVM architectures in presence of timing errors due to process variations in near-threshold voltage (NTV) regions (0.3 V - 0.7 V). In particular, the RF architecture exhibits a detection accuracy (P_{det}) that varies by 3.2% while maintaining a median P_{det} > 0.9 at a gate level delay variation of 28.9% . In comparison, SVM exhibits a P_{det} that varies by 16.8%. Additionally, we propose an error weighted voting technique that incorporates the timing error statistics of the NTV circuit fabric to further enhance robustness. Simulation results confirm that the error weighted voting achieves a P_{det} that varies by only 1.4%, which is 12X lower compared to SVM.
Tasks
Published	2016-07-03
URL	http://arxiv.org/abs/1607.07804v1
PDF	http://arxiv.org/pdf/1607.07804v1.pdf
PWC	https://paperswithcode.com/paper/error-resilient-machine-learning-in-near
Repo
Framework

Automated Correction for Syntax Errors in Programming Assignments using Recurrent Neural Networks


Title	Automated Correction for Syntax Errors in Programming Assignments using Recurrent Neural Networks
Authors	Sahil Bhatia, Rishabh Singh
Abstract	We present a method for automatically generating repair feedback for syntax errors for introductory programming problems. Syntax errors constitute one of the largest classes of errors (34%) in our dataset of student submissions obtained from a MOOC course on edX. The previous techniques for generating automated feed- back on programming assignments have focused on functional correctness and style considerations of student programs. These techniques analyze the program AST of the program and then perform some dynamic and symbolic analyses to compute repair feedback. Unfortunately, it is not possible to generate ASTs for student pro- grams with syntax errors and therefore the previous feedback techniques are not applicable in repairing syntax errors. We present a technique for providing feedback on syntax errors that uses Recurrent neural networks (RNNs) to model syntactically valid token sequences. Our approach is inspired from the recent work on learning language models from Big Code (large code corpus). For a given programming assignment, we first learn an RNN to model all valid token sequences using the set of syntactically correct student submissions. Then, for a student submission with syntax errors, we query the learnt RNN model with the prefix to- ken sequence to predict token sequences that can fix the error by either replacing or inserting the predicted token sequence at the error location. We evaluate our technique on over 14, 000 student submissions with syntax errors. Our technique can completely re- pair 31.69% (4501/14203) of submissions with syntax errors and in addition partially correct 6.39% (908/14203) of the submissions.
Tasks
Published	2016-03-19
URL	http://arxiv.org/abs/1603.06129v1
PDF	http://arxiv.org/pdf/1603.06129v1.pdf
PWC	https://paperswithcode.com/paper/automated-correction-for-syntax-errors-in
Repo
Framework

Compositional Distributional Cognition


Title	Compositional Distributional Cognition
Authors	Yaared Al-Mehairi, Bob Coecke, Martha Lewis
Abstract	We accommodate the Integrated Connectionist/Symbolic Architecture (ICS) of [32] within the categorical compositional semantics (CatCo) of [13], forming a model of categorical compositional cognition (CatCog). This resolves intrinsic problems with ICS such as the fact that representations inhabit an unbounded space and that sentences with differing tree structures cannot be directly compared. We do so in a way that makes the most of the grammatical structure available, in contrast to strategies like circular convolution. Using the CatCo model also allows us to make use of tools developed for CatCo such as the representation of ambiguity and logical reasoning via density matrices, structural meanings for words such as relative pronouns, and addressing over- and under-extension, all of which are present in cognitive processes. Moreover the CatCog framework is sufficiently flexible to allow for entirely different representations of meaning, such as conceptual spaces. Interestingly, since the CatCo model was largely inspired by categorical quantum mechanics, so is CatCog.
Tasks
Published	2016-08-12
URL	http://arxiv.org/abs/1608.03785v1
PDF	http://arxiv.org/pdf/1608.03785v1.pdf
PWC	https://paperswithcode.com/paper/compositional-distributional-cognition
Repo
Framework

Compressing Neural Language Models by Sparse Word Representations


Title	Compressing Neural Language Models by Sparse Word Representations
Authors	Yunchuan Chen, Lili Mou, Yan Xu, Ge Li, Zhi Jin
Abstract	Neural networks are among the state-of-the-art techniques for language modeling. Existing neural language models typically map discrete words to distributed, dense vector representations. After information processing of the preceding context words by hidden layers, an output layer estimates the probability of the next word. Such approaches are time- and memory-intensive because of the large numbers of parameters for word embeddings and the output layer. In this paper, we propose to compress neural language models by sparse word representations. In the experiments, the number of parameters in our model increases very slowly with the growth of the vocabulary size, which is almost imperceptible. Moreover, our approach not only reduces the parameter space to a large extent, but also improves the performance in terms of the perplexity measure.
Tasks	Language Modelling, Word Embeddings
Published	2016-10-13
URL	http://arxiv.org/abs/1610.03950v1
PDF	http://arxiv.org/pdf/1610.03950v1.pdf
PWC	https://paperswithcode.com/paper/compressing-neural-language-models-by-sparse
Repo
Framework

Navigational Instruction Generation as Inverse Reinforcement Learning with Neural Machine Translation


Title	Navigational Instruction Generation as Inverse Reinforcement Learning with Neural Machine Translation
Authors	Andrea F. Daniele, Mohit Bansal, Matthew R. Walter
Abstract	Modern robotics applications that involve human-robot interaction require robots to be able to communicate with humans seamlessly and effectively. Natural language provides a flexible and efficient medium through which robots can exchange information with their human partners. Significant advancements have been made in developing robots capable of interpreting free-form instructions, but less attention has been devoted to endowing robots with the ability to generate natural language. We propose a navigational guide model that enables robots to generate natural language instructions that allow humans to navigate a priori unknown environments. We first decide which information to share with the user according to their preferences, using a policy trained from human demonstrations via inverse reinforcement learning. We then “translate” this information into a natural language instruction using a neural sequence-to-sequence model that learns to generate free-form instructions from natural language corpora. We evaluate our method on a benchmark route instruction dataset and achieve a BLEU score of 72.18% when compared to human-generated reference instructions. We additionally conduct navigation experiments with human participants that demonstrate that our method generates instructions that people follow as accurately and easily as those produced by humans.
Tasks	Machine Translation
Published	2016-10-11
URL	http://arxiv.org/abs/1610.03164v1
PDF	http://arxiv.org/pdf/1610.03164v1.pdf
PWC	https://paperswithcode.com/paper/navigational-instruction-generation-as
Repo
Framework