Artificial Intelligence

1607 Submissions

[5] viXra:1607.0484 [pdf] submitted on 2016-07-25 21:28:15

Active Appearance Model Construction: Implementation notes

Authors: Nikzad Babaii Rizvandi, Wilfried Philips, Aleksandra Pizurica
Comments: 7 Pages.

Active Appearance Model (AAM) is a powerful object modeling technique and one of the best available ones in computer vision and computer graphics. This approach is however quite complex and various parts of its implementation were addressed separately by different researchers in several recent works. In this paper, we present systematically a full implementation of the AAM model with pseudo codes for the crucial steps in the construction of this model.
Category: Artificial Intelligence

[4] viXra:1607.0483 [pdf] submitted on 2016-07-25 21:29:15

Active Appearance Model (Aam) from Theory to Implementation

Authors: Nikzad Babaii Rizvandi, Aleksandra Pizˇurica, Wilfried Philips
Comments: 4 Pages.

Active Appearance Model (AAM) is a kind of deformable shape descriptors which is widely used in computer vision and computer graphics. This approach utilizes statistical model obtained from some images in training set and gray-value information of the texture to fit on the boundaries of a new image. In this paper, we describe a brief implementation, apply the method on hand object and finally discuss its performance in compare to Active Shape Model(ASM). Our experiments shows this method is more sensitive to the initialization and slower than ASM.
Category: Artificial Intelligence

[3] viXra:1607.0459 [pdf] submitted on 2016-07-24 21:30:52

Pattern Recognition and Learning in Bistable Cam Networks

Authors: Vladimir Chinarov, Martin Dudziak, Yuri Kyrpach
Comments: 12 Pages.

The present study concerns the problem of learning, pattern recognition and computational abilities of a homogeneous network composed from coupled bistable units. New possibilities for pattern recognition may be realized due to the developed technique that permits a reconstruction of a dynamical system using the distributions of its attractors. In both cases the updating procedure for the coupling matrix uses the minimization of least-mean-square errors between the applied and desired patterns.
Category: Artificial Intelligence

[2] viXra:1607.0073 [pdf] replaced on 2016-07-08 06:55:14

Indian Buffet Process Deep Generative Models

Authors: Sotirios P. Chatzis
Comments: 16 Pages.

Deep generative models (DGMs) have brought about a major breakthrough, as well as renewed interest, in generative latent variable models. However, an issue current DGM formulations do not address concerns the data-driven inference of the number of latent features needed to represent the observed data. Traditional linear formulations allow for addressing this issue by resorting to tools from the field of nonparametric statistics: Indeed, nonparametric linear latent variable models, obtained by appropriate imposition of Indian Buffet Process (IBP) priors, have been extensively studied by the machine learning community; inference for such models can been performed either via exact sampling or via approximate variational techniques. Based on this inspiration, in this paper we examine whether similar ideas from the field of Bayesian nonparametrics can be utilized in the context of modern DGMs in order to address the latent variable dimensionality inference problem. To this end, we propose a novel DGM formulation, based on the imposition of an IBP prior. We devise an efficient Black-Box Variational inference algorithm for our model, and exhibit its efficacy in a number of semi-supervised classification experiments. In all cases, we use popular benchmark datasets, and compare to state-of-the-art DGMs.
Category: Artificial Intelligence

[1] viXra:1607.0014 [pdf] submitted on 2016-07-01 14:54:48

Interval-Valued Neutrosophic Oversets, Neutrosophic Undersets, and Neutrosophic Offsets

Authors: Florentin Smarandache
Comments: 4 Pages.

We have proposed since 1995 the existence of degrees of membership of an element with respect to a neutrosophic set to also be partially or totally above 1 (overmembership), and partially or totally below 0 (undermembership) in order to better describe our world problems [published in 2007].
Category: Artificial Intelligence