عنوان مقاله فارسی: نمودار هولوگرافیک نورون: یک معماری الهامگرفته از بیوتین برای پردازش الگو
عنوان مقاله لاتین: Holographic Graph Neuron: A Bioinspired Architecture for Pattern Processing
نویسندگان: Denis Kleyko; Evgeny Osipov; Alexander Senior; Asad I. Khan; Yaşar Ahmet Şekerciogğlu
تعداد صفحات: 12
سال انتشار: 2017
زبان: لاتین
Abstract:
In this paper, we propose a new approach to implementing hierarchical graph neuron (HGN), an architecture for memorizing patterns of generic sensor stimuli, through the use of vector symbolic architectures. The adoption of a vector symbolic representation ensures a single-layer design while retaining the existing performance characteristics of HGN. This approach significantly improves the noise resistance of the HGN architecture, and enables a linear (with respect to the number of stored entries) time search for an arbitrary subpattern.
holographic graph neuron a bioinspired architecture for pattern processing_1622969535_48866_4145_1116.zip1.97 MB |