Open AccessA Heuristic Review on Analog Performance and Accomplishment of Activation Functions at RTL Level
Author(s) -
Sudhakar Jyothula
Publication year - 2021
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/1099/1/012028
Subject(s) - computer science , automation , latency (audio) , artificial neural network , field (mathematics) , heuristic , process (computing) , power (physics) , analog computer , computer engineering , artificial intelligence , engineering , electrical engineering , telecommunications , mechanical engineering , physics , mathematics , quantum mechanics , pure mathematics , operating system
In this article, the behavior of many functional activities used for Artificial Neural Networks (ANNs) study is demonstrated together with their similar performance under transistor conditions. ANN plays an important role in computer science, technology, machine learning, automation, speech and voice processing. The accuracy of any automated device largely depends on ANN training. Therefore, choosing an appropriate operating system affects the performance of the entire system. Performing operational movements at the transistor levels with low power, latency, and power requirements without adjusting their properties is a major challenge. Process actions are performed on an analog or digital one. Analog performance simulations are clearly demonstrated in this article, as the field and power limit for simulation applications is greater than for digital applications. The efficiency of the operating system relies on the % of errors between its manufacture and quality.