In the domain of text processing, Vector Symbolic Architectures were used to search for the longest common substring and to recognize permuted words. In the domain of automation systems, Vector Symbolic Architectures were used for a data-driven fault isolation. In the domain of biomedical signal processing, Vector Symbolic Architectures were applied for three tasks: classification of a modality of medical images, gesture recognition, and assessment of synchronization of cardiovascular signals. All applications scenarios used novel methods of mapping data to Vector Symbolic Architectures proposed in the thesis. ![]() Specifically, such important applications as biomedical signal processing, automation systems, and text processing were considered. Therefore, it is important to look for new possibilities in the area via exploring biologically inspired approaches.Īll application scenarios, which are considered in the thesis, contribute to the development of the global strategy of creating an information society. In particular, one of the challenges is a large amount of training data required by conventional machine learning algorithms. Despite the success in many domains pattern recognition algorithms are still far from being close to their biological vis-a-vis – the brain. Applications of pattern recognition and machine learning can be found in many areas of the present day world including health-care, robotics, manufacturing, economics, automation, transportation, etc. Pattern recognition is the area constantly enlarging its theoretical and practical horizons. This thesis significantly extends the applicability of Vector Symbolic Architectures to an area of pattern recognition. Previously, Vector Symbolic Architectures have been used mainly in the area of cognitive computing for representing and reasoning upon semantically bound information, for example, for analogy-based reasoning. This thesis includes eleven scientific papers and extends the research area in three directions: theory of Vector Symbolic Architectures, their applications for pattern recognition, and unification of Vector Symbolic Architectures with other neural-like computational approaches. Representational units can be of different nature, however, the thesis concentrates on the case when units have either binary or integer values. ![]() Information in Vector Symbolic Architectures is evenly distributed across representational units, therefore, it is said that they operate with distributed representations. ![]() Vector Symbolic Architectures are a family of bio-inspired methods of representing and manipulating concepts and their meanings in a high-dimensional space (hence Hyperdimensional Computing). The most common ones are Vector Symbolic Architectures and Hyperdimensional Computing. The main focus of this thesis lies in a rather narrow subfield of Artificial Intelligence. Vektor symboliska Arkitekturer och deras tillämpningar : Beräkning med slumpmässiga vektorer i ett hyperdimensionellt utrymme (Swedish)
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |