This paper addresses the problem of motion synchronization (or averaging) and describes a simple, closed-form solution based on a spectral decomposition, which does not consider rotation and translation separately but works straight in SE(3), the manifold of rigid motions. Besides its theoretical interest, being the first closed form solution in SE(3), experimental results show that it compares favourably with the state of the art both in terms of precision and speed.
This paper presents an algorithm for efficient training of sparse linear models with elastic net regularization. Extending previous work on delayed updates, the new algorithm applies stochastic gradient updates to non-zero features only, bringing weights current as needed with closed-form updates. Closed-form delayed updates for the $\ell_1$, $\ell_{\infty}$, and rarely used $\ell_2$ regularizers have been described previously. This paper provides closed-form updates for the popular squared norm $\ell^2_2$ and elastic net regularizers. We provide dynamic programming algorithms that perform each delayed update in constant time. The new $\ell^2_2$ and elastic net methods handle both fixed and varying learning rates, and both standard {stochastic gradient descent} (SGD) and {forward backward splitting (FoBoS)}. Experimental results show that on a bag-of-words dataset with $260,941$ features, but only $88$ nonzero features on average per training example, the dynamic programming method trains a logistic regression classifier with elastic net regularization over $2000$ times faster than otherwise.
Computational neuroscience studies that have examined human visual system through functional magnetic resonance imaging (fMRI) have identified a model where the mammalian brain pursues two distinct pathways (for recognition of biological movement tasks). In the brain, dorsal stream analyzes the information of motion (optical flow), which is the fast features, and ventral stream (form pathway) analyzes form information (through active basis model based incremental slow feature analysis ) as slow features. The proposed approach suggests the motion perception of the human visual system composes of fast and slow feature interactions that identifies biological movements. Form features in the visual system biologically follows the application of active basis model with incremental slow feature analysis for the extraction of the slowest form features of human objects movements in the ventral stream. Applying incremental slow feature analysis provides an opportunity to use the action prototypes. To extract the slowest features episodic observation is required but the fast features updates the processing of motion information in every frames. Experimental results have shown promising accuracy for the proposed model and good performance with two datasets (KTH and Weizmann).
The Software Development Life Cycle (SDLC) starts with eliciting requirements of the customers in the form of Software Requirement Specification (SRS). SRS document needed for software development is mostly written in Natural Language(NL) convenient for the client. From the SRS document only, the class name, its attributes and the functions incorporated in the body of the class are traced based on pre-knowledge of analyst. The paper intends to present a review on Object Oriented (OO) analysis using Natural Language Processing (NLP) techniques. This analysis can be manual where domain expert helps to generate the required diagram or automated system, where the system generates the required diagram, from the input in the form of SRS.
Zipf's law appears in many application areas but does not have a closed form expression, which may make its use cumbersome. Since it coincides with the truncated version of the Zeta distribution, in this paper we propose three approximate closed form expressions for the truncated Zeta distribution, which may be employed for Zipf's law as well. The three approximations are based on the replacement of the sum occurring in Zipf's law with an integral, and are named respectively the integral approximation, the average integral approximation, and the trapezoidal approximation. While the first one is shown to be of little use, the trapezoidal approximation exhibits an error which is typically lower than 1\%, but is as low as 0.1\% for the range of values of the Zipf parameter below 1.
Today artificial neural networks are applied in various fields - engineering, data analysis, robotics. While they represent a successful tool for a variety of relevant applications, mathematically speaking they are still far from being conclusive. In particular, they suffer from being unable to find the best configuration possible during the training process (local minimum problem). In this paper, we focus on this issue and suggest a simple, but effective, post-learning strategy to allow the search for improved set of weights at a relatively small extra computational cost. Therefore, we introduce a novel technique based on analogy with quantum effects occurring in nature as a way to improve (and sometimes overcome) this problem. Several numerical experiments are presented to validate the approach.
We show that natural classes of regularized learning algorithms with a form of recency bias achieve faster convergence rates to approximate efficiency and to coarse correlated equilibria in multiplayer normal form games. When each player in a game uses an algorithm from our class, their individual regret decays at $O(T^{-3/4})$, while the sum of utilities converges to an approximate optimum at $O(T^{-1})$--an improvement upon the worst case $O(T^{-1/2})$ rates. We show a black-box reduction for any algorithm in the class to achieve $\tilde{O}(T^{-1/2})$ rates against an adversary, while maintaining the faster rates against algorithms in the class. Our results extend those of [Rakhlin and Shridharan 2013] and [Daskalakis et al. 2014], who only analyzed two-player zero-sum games for specific algorithms.
Testing independence is of significant interest in many important areas of large-scale inference. Using extreme-value form statistics to test against sparse alternatives and using quadratic form statistics to test against dense alternatives are two important testing procedures for high-dimensional independence. However, quadratic form statistics suffer from low power against sparse alternatives, and extreme-value form statistics suffer from low power against dense alternatives with small disturbances and may have size distortions due to its slow convergence. For real-world applications, it is important to derive powerful testing procedures against more general alternatives. Based on intermediate limiting distributions, we derive (model-free) joint limiting laws of extreme-value form and quadratic form statistics, and surprisingly, we prove that they are asymptotically independent. Given such asymptotic independencies, we propose (model-free) testing procedures to boost the power against general alternatives and also retain the correct asymptotic size. Under the high-dimensional setting, we derive the closed-form limiting null distributions, and obtain their explicit rates of uniform convergence. We prove their consistent statistical powers against general alternatives. We demonstrate the performance of our proposed test statistics in simulation studies. Our work provides very helpful insights to high-dimensional independence tests, and fills an important gap.
This paper discusses the representation of ontologies in the first-order logical environment {\ttfamily FOLE}. An ontology defines the primitives with which to model the knowledge resources for a community of discourse. These primitives consist of classes, relationships and properties. An ontology uses formal axioms to constrain the interpretation of these primitives. In short, an ontology specifies a logical theory. This paper continues the discussion of the representation and interpretation of ontologies in the first-order logical environment {\ttfamily FOLE}. The formalism and semantics of (many-sorted) first-order logic can be developed in both a \emph{classification form} and an \emph{interpretation form}. Two papers, the current paper, defining the concept of a structure, and ``The {\ttfamily ERA} of {\ttfamily FOLE}: Superstructure'', defining the concept of a sound logic, represent the \emph{classification form}, corresponding to ideas discussed in the ``Information Flow Framework''. Two papers, ``The {\ttfamily FOLE} Table'', defining the concept of a relational table, and ``The {\ttfamily FOLE} Database'', defining the concept of a relational database, represent the \emph{interpretation form}, expanding on material found in the paper ``Database Semantics''. Although the classification form follows the entity-relationship-attribute data model of Chen, the interpretation form incorporates the relational data model of Codd. A fifth paper ``{\ttfamily FOLE} Equivalence'' proves that the classification form is equivalent to the interpretation form. In general, the {\ttfamily FOLE} representation uses a conceptual structures approach, that is completely compatible with the theory of institutions, formal concept analysis and information flow.
Mean field variational Bayes (MFVB) is a popular posterior approximation method due to its fast runtime on large-scale data sets. However, it is well known that a major failing of MFVB is that it underestimates the uncertainty of model variables (sometimes severely) and provides no information about model variable covariance. We generalize linear response methods from statistical physics to deliver accurate uncertainty estimates for model variables---both for individual variables and coherently across variables. We call our method linear response variational Bayes (LRVB). When the MFVB posterior approximation is in the exponential family, LRVB has a simple, analytic form, even for non-conjugate models. Indeed, we make no assumptions about the form of the true posterior. We demonstrate the accuracy and scalability of our method on a range of models for both simulated and real data.
We prove a closed-form solution to tensor voting (CFTV): given a point set in any dimensions, our closed-form solution provides an exact, continuous and efficient algorithm for computing a structure-aware tensor that simultaneously achieves salient structure detection and outlier attenuation. Using CFTV, we prove the convergence of tensor voting on a Markov random field (MRF), thus termed as MRFTV, where the structure-aware tensor at each input site reaches a stationary state upon convergence in structure propagation. We then embed structure-aware tensor into expectation maximization (EM) for optimizing a single linear structure to achieve efficient and robust parameter estimation. Specifically, our EMTV algorithm optimizes both the tensor and fitting parameters and does not require random sampling consensus typically used in existing robust statistical techniques. We performed quantitative evaluation on its accuracy and robustness, showing that EMTV performs better than the original TV and other state-of-the-art techniques in fundamental matrix estimation for multiview stereo matching. The extensions of CFTV and EMTV for extracting multiple and nonlinear structures are underway. An addendum is included in this arXiv version.
Recently, many methods have been proposed for face reconstruction from multiple images, most of which involve fundamental principles of Shape from Shading and Structure from motion. However, a majority of the methods just generate discrete surface model of face. In this paper, B-spline Shape from Motion and Shading (BsSfMS) is proposed to reconstruct continuous B-spline surface for multi-view face images, according to an assumption that shading and motion information in the images contain 1st- and 0th-order derivative of B-spline face respectively. Face surface is expressed as a B-spline surface that can be reconstructed by optimizing B-spline control points. Therefore, normals and 3D feature points computed from shading and motion of images respectively are used as the 1st- and 0th- order derivative information, to be jointly applied in optimizing the B-spline face. Additionally, an IMLS (iterative multi-least-square) algorithm is proposed to handle the difficult control point optimization. Furthermore, synthetic samples and LFW dataset are introduced and conducted to verify the proposed approach, and the experimental results demonstrate the effectiveness with different poses, illuminations, expressions etc., even with wild images.
Three-dimensional models of craniofacial variation over the general population are useful for assessing pre- and post-operative head shape when treating various craniofacial conditions, such as craniosynostosis. We present a new method of automatically building both sagittal profile models and full 3D surface models of the human head using a range of techniques in 3D surface image analysis; in particular, automatic facial landmarking using supervised machine learning, global and local symmetry plane detection using a variant of trimmed iterative closest points, locally-affine template warping (for full 3D models) and a novel pose normalisation using robust iterative ellipse fitting. The PCA-based models built using the new pose normalisation are more compact than those using Generalised Procrustes Analysis and we demonstrate their utility in a clinical case study.
The successive projection algorithm (SPA) has been known to work well for separable nonnegative matrix factorization (NMF) problems arising in applications, such as topic extraction from documents and endmember detection in hyperspectral images. One of the reasons is in that the algorithm is robust to noise. Gillis and Vavasis showed in [SIAM J. Optim., 25(1), pp. 677-698, 2015] that a preconditioner can further enhance its noise robustness. The proof rested on the condition that the dimension $d$ and factorization rank $r$ in the separable NMF problem coincide with each other. However, it may be unrealistic to expect that the condition holds in separable NMF problems appearing in actual applications; in such problems, $d$ is usually greater than $r$. This paper shows, without the condition $d=r$, that the preconditioned SPA is robust to noise.
Utilizing the sample size of a dataset, the random cluster model is employed in order to derive an estimate of the mean number of K-Means clusters to form during classification of a dataset.
In this paper you can explore the application of some notable Boolean-derived methods, namely the Disjunctive Normal Form representation of logic table expansions, and extend them to a real-valued logic model which is able to utilize quantities on the range [0,1], [-1,1], [a,b], (x,y), (x,y,z), and etc. so as to produce a logical programming of arbitrary range, precision, and dimensionality, thereby enabling contemplation at a logical level in notions of arbitrary data, colors, and spatial constructs, with an example of the production of a game character's logic in mathematical form.
Regularized empirical risk minimization with constrained labels (in contrast to fixed labels) is a remarkably general abstraction of learning. For common loss and regularization functions, this optimization problem assumes the form of a mixed integer program (MIP) whose objective function is non-convex. In this form, the problem is resistant to standard optimization techniques. We construct MIPs with the same solutions whose objective functions are convex. Specifically, we characterize the tightest convex extension of the objective function, given by the Legendre-Fenchel biconjugate. Computing values of this tightest convex extension is NP-hard. However, by applying our characterization to every function in an additive decomposition of the objective function, we obtain a class of looser convex extensions that can be computed efficiently. For some decompositions, common loss and regularization functions, we derive a closed form.
Studies on computational neuroscience through functional magnetic resonance imaging (fMRI) and following biological inspired system stated that human action recognition in the brain of mammalian leads two distinct pathways in the model, which are specialized for analysis of motion (optic flow) and form information. Principally, we have defined a novel and robust form features applying active basis model as form extractor in form pathway in the biological inspired model. An unbalanced synergetic neural net-work classifies shapes and structures of human objects along with tuning its attention parameter by quantum particle swarm optimization (QPSO) via initiation of Centroidal Voronoi Tessellations. These tools utilized and justified as strong tools for following biological system model in form pathway. But the final decision has done by combination of ultimate outcomes of both pathways via fuzzy inference which increases novality of proposed model. Combination of these two brain pathways is done by considering each feature sets in Gaussian membership functions with fuzzy product inference method. Two configurations have been proposed for form pathway: applying multi-prototype human action templates using two time synergetic neural network for obtaining uniform template regarding each actions, and second scenario that it uses abstracting human action in four key-frames. Experimental results showed promising accuracy performance on different datasets (KTH and Weizmann).
This paper presents to the best of our knowledge the first end-to-end object tracking approach which directly maps from raw sensor input to object tracks in sensor space without requiring any feature engineering or system identification in the form of plant or sensor models. Specifically, our system accepts a stream of raw sensor data at one end and, in real-time, produces an estimate of the entire environment state at the output including even occluded objects. We achieve this by framing the problem as a deep learning task and exploit sequence models in the form of recurrent neural networks to learn a mapping from sensor measurements to object tracks. In particular, we propose a learning method based on a form of input dropout which allows learning in an unsupervised manner, only based on raw, occluded sensor data without access to ground-truth annotations. We demonstrate our approach using a synthetic dataset designed to mimic the task of tracking objects in 2D laser data -- as commonly encountered in robotics applications -- and show that it learns to track many dynamic objects despite occlusions and the presence of sensor noise.
In this paper, we propose a set theoretic approach for knowledge representation. While the syntax of an application domain is captured by set theoretic constructs including individuals, concepts and operators, knowledge is formalized by equality assertions. We first present a primitive form that uses minimal assumed knowledge and constructs. Then, assuming naive set theory, we extend it by definitions, which are special kinds of knowledge. Interestingly, we show that the primitive form is expressive enough to define logic operators, not only propositional connectives but also quantifiers.