A plug-and-play mechanism that mixes genetic-algorithm evolution into RL training for neural routing solvers gives small benchmark gains, but its stability theorem is not valid as proven.
Design paradigms of intelligent control systems on a chip
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
This paper focuses on the Field Programmable Gate Array (FPGA) design and implementation of intelligent control system applications on a chip, specifically fuzzy logic and genetic algorithm processing units. Initially, an overview of the FPGA technology is presented, followed by design methodologies, development tools and the use of hardware description languages (HDL). Two FPGA design examples with the use of Hardware Description Languages (HDLs) of parameterized fuzzy logic controller cores are discussed. Thereinafter, a System-on-a-Chip (SoC) designed by the authors in previous work and realized on FPGA featuring a Digital Fuzzy Logic Controller (DFLC) and a soft processor core for the path tracking problem of mobile robots is discussed. Finally a Genetic Algorithm implementation (previously published by the authors) in FPGA chip for the Traveling Salesman Problem (TSP) is also discussed.
citation-role summary
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Synergizing Reinforcement Learning and Genetic Algorithms for Neural Combinatorial Optimization
A plug-and-play mechanism that mixes genetic-algorithm evolution into RL training for neural routing solvers gives small benchmark gains, but its stability theorem is not valid as proven.