id: 29682
Назва: Design and simulation of neuron-equivalentors array for creation of self-learning equivalent-convolutional neural structures (slecns).
Автори: Krasilenko Vladimir, Yurchuk Nataliya, Nikitovich Diana.
Ключові слова: Neuron-Equivalentor, Hardware Accelerator, Self-Learning Equivalent-Convolutional Neural Structures, continuous logic, current mirror
Дата публікації: 2021-11-16 14:17:13
Останні зміни: 2021-11-16 14:17:13
Рік видання: 2021
Аннотація: In the paper, we consider the urgent need to create highly efficient hardware accelerators for machine learning
algorithms, including convolutional and deep neural networks (CNN and DNNS), for associative memory models, clustering,
and pattern recognition. We show a brief overview of our related works the advantages of the equivalent models (EM) for
describing and designing bio-inspired systems. The capacity of NN on the basis of EM and of its modifications is in several
times quantity of neurons. Such neural paradigms are very perspective for processing, clustering, recognition, storing large
size, strongly correlated, highly noised images and creating of uncontrolled learning machine. And since the basic
operational functional nodes of EM are such vector-matrix or matrix-tensor procedures with continuous-logical operations
as: normalized vector operations "equivalence", "nonequivalence", and etc. , we consider in this paper new conceptual
approaches to the design of full-scale arrays of such neuron-equivalentors (NEs) with extended functionality, including
different activation functions. Our approach is based on the use of analog and mixed (with special coding) methods for
implementing the required operations, building NEs (with number of synapsis from 8 up to 128 and more) and their base
cells, nodes based on photosensitive elements and CMOS current mirrors. Simulation results show that the efficiency of NEs
relative to the energy intensity is estimated at a value of not less than 1012 an. op. / sec on W and can be increased. The
results confirm the correctness of the concept and the possibility of creating NE and MIMO structures on their basis.
URI: http://81.30.162.23/repository/getfile.php/29682.pdf
Тип виданя: Статті у наукових фахових виданнях України (Copernicus та інші)
Видавництво: Вісник Хмельницького національного університету. Серія: Технічні науки. 2021. № 3 (297). C. 58-70.
Розташовується в колекціях :
Ким внесений: Адміністратор
Файл : 29682.pdf Розмір : 2626266 байт Формат : Adobe PDF Доступ : Загально доступний
| |
|
|
