Building a world model with structure-sensitive sparse binary distributed representations

Rachkovskij, Dmitri A.; Kussul, Ernst; Baidyk, Tatiana

doi:10.1016/j.bica.2012.09.004

Cited by 32 publications

(42 citation statements)

References 93 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is also worth to note that the methods proposed in [31][32][33] could significantly accelerate the computation of the algorithm as well as the whole segmentation model. Thus, the proposed algorithm solves some intermediate task within the complex image segmentation problem.…”

Section: Discussionmentioning

confidence: 99%

Finding the Texture Features Characterizing the Most Homogeneous Texture Segment in the Image

Goltsev

Гриценко

Kussul

et al. 2015

Advances in Computational Intelligence

View full text Add to dashboard Cite

Abstract.We propose an algorithm for finding a set of texture features characterizing the most homogeneous texture area of an input image. The found set of features is intended for extraction of this segment. The algorithm processes any input images in the absence of any preliminary information about the images and, accordingly, without any learning. The essence of the algorithm is as follows. The image is covered with a number of test windows. In each of them, a degree of texture homogeneity is measured. The test window with maximal degree of homogeneity is determined and a representative patch of pixels is detected. The texture features extracted from the detected representative patch is considered as those that best characterize the most homogeneous texture segment. So, the proposed algorithm facilitates solution of the texture segmentation task by providing a segmentation technique with helpful additional information about the analyzed image. A computer program simulating the algorithm has been created. The program is tested on natural grayscale images.

show abstract

Section: Discussionmentioning

confidence: 99%

Finding the Texture Features Characterizing the Most Homogeneous Texture Segment in the Image

Goltsev

Гриценко

Kussul

et al. 2015

Advances in Computational Intelligence

View full text Add to dashboard Cite

show abstract

“…The SDM is based on the same idea as VSAs that similar or related concepts are represented by nearby points in a high-dimensional space (Kanerva, 1988;Kanerva, 1993). The SDM have been successfully used in numerous applications since the 1990s, e.g., pattern recognition (Hely, Willshaw, & Hayes, 1997;Meng et al, 2009), predictive analytics (Rogers, 1989;Rogers, 1990), robot navigation (Rao & Fuentes, 1998;Jockel, Mendes, Zhang, Coimbra, & Crisostomo, 2009), approximation of Bayesian inference in a fashion similar to Monte Carlo importance sampling (Anderson, 1989;Abbott, Hamrick, & Griffiths, 2013), and biologically inspired cognitive architectures (Rachkovskij, Kussul, & Baidyk, 2013;Franklin, Madl, D'Mello, & Snaider, 2014).…”

Section: Long-term Memorymentioning

confidence: 98%

Vector space architecture for emergent interoperability of systems by learning from demonstration

Emruli

Sandin

Delsing

2015

Biologically Inspired Cognitive Architectures

View full text Add to dashboard Cite

The rapid integration of physical systems with cyberspace infrastructure, the so-called Internet of Things, is likely to have a significant effect on how people interact with the physical environment and design information and communication systems. Internet-connected systems are expected to vastly outnumber people on the planet in the near future, leading to grand challenges in software engineering and automation in application domains involving complex and evolving systems. Several decades of artificial intelligence research suggests that conventional approaches to making such systems automatically interoperable using handcrafted ''semantic'' descriptions of services and information are difficult to apply. In this paper we outline a bioinspired learning approach to creating interoperable systems, which does not require handcrafted semantic descriptions and rules. Instead, the idea is that a functioning system (of systems) can emerge from an initial pseudorandom state through learning from examples, provided that each component conforms to a set of information coding rules. We combine a binary vector symbolic architecture (VSA) with an associative memory known as sparse distributed memory (SDM) to model context-dependent prediction by learning from examples. We present simulation results demonstrating that the proposed architecture can enable system interoperability by learning, for example by human demonstration. ª 2015 Published by Elsevier B.V.

show abstract

“…Distributed representations can also be formed in inner layers of multilayer networks in the course of training [46][47][48]. Distributed representations are used to represent semantic similarity [18,42,[49][50][51], sequences [29-31, 43, 51-54], complex hierarchically structured objects [1, 2, 4-11, 30, 31, 35, 36, 42-45, 55-57] required for models and systems of artificial intelligence [3,31,35,36,[57][58][59].…”

Section: Experimental Analysismentioning

confidence: 99%

“…Some approaches and methods require specialized algorithms for storage and handling of vector data in a certain format (representation). Sparse [28,29] (with a small share of nonzero components) binary vectors are used, for example, in associative-projective neural networks [30,31] and in the efficient binary version [32][33][34] of distributed associative memory [10,11,[35][36][37][38].…”

Section: Introductionmentioning

confidence: 99%

Estimation of Vectors Similarity by Their Randomized Binary Projections

Rachkovskij

2015

Cybern Syst Anal

View full text Add to dashboard Cite

We analyze the estimation of the angle, scalar product, and the Euclidean distance of real-valued vectors using binary vectors with controlled sparsity. Transformation is carried out by projection using a binary random matrix with elements { } 0 1 , and the output threshold transformation. We also provide a comparative analysis of the error obtained while estimating the similarity measures of input vectors by some similarity measures of output binary vectors based on their scalar product.Keywords: binary random projections, sparse binary representations, estimate of vector similarity.

show abstract

Building a world model with structure-sensitive sparse binary distributed representations

Cited by 32 publications

References 93 publications

Finding the Texture Features Characterizing the Most Homogeneous Texture Segment in the Image

Finding the Texture Features Characterizing the Most Homogeneous Texture Segment in the Image

Vector space architecture for emergent interoperability of systems by learning from demonstration

Estimation of Vectors Similarity by Their Randomized Binary Projections

Contact Info

Product

Resources

About