A Non-Revisiting Equilibrium Optimizer Algorithm
نویسندگان
چکیده
The equilibrium optimizer (EO) is a novel physics-based meta-heuristic optimization algorithm that inspired by estimating dynamics and states in controlled volume mass balance models. As stochastic algorithm, EO inevitably produces duplicated solutions, which wasteful of valuable evaluation opportunities. In addition, an excessive number solutions can increase the risk getting trapped local optima. this paper, improved with bis-population-based non-revisiting (BNR) mechanism proposed, namely BEO. It aims to eliminate duplicate generated population during iterations, thus avoiding wasted Furthermore, when revisited solution detected, BNR activates its unique archive learning assist generating high-quality using excellent genes historical information, not only improves algorithm's diversity but also helps get out optimum dilemma. Experimental findings IEEE CEC2017 benchmark demonstrate proposed BEO outperforms other seven representative techniques, including original algorithm.
منابع مشابه
Revisiting the Paxos Algorithm Revisiting the Paxos Algorithm
The paxos algorithm is an e cient and highly fault-tolerant algorithm, devised by Lamport, for reaching consensus in a distributed system. Although it appears to be practical, it seems to be not widely known or understood. This thesis contains a new presentation of the paxos algorithm, based on a formal decomposition into several interacting components. It also contains a correctness proof and ...
متن کاملRevisiting the Paxos Algorithm
The PAXOS algorithm is an efficient and highly fault-tolerant algorithm, devised by Lamport, for reaching consensus in a distributed system. Although it appears to be practical, it seems to be not widely known or understood. This thesis contains a new presentation of the PAXOS algorithm, based on a formal decomposition into several interacting components. It also contains a correctness proof an...
متن کاملNeumann Optimizer: A Practical Optimization Algorithm for Deep Neural Networks
Progress in deep learning is slowed by the days or weeks it takes to train large models. The natural solution of using more hardware is limited by diminishing returns, and leads to inefficient use of additional resources. In this paper, we present a large batch, stochastic optimization algorithm that is both faster than widely used algorithms for fixed amounts of computation, and also scales up...
متن کاملNeumann Optimizer: a Practical Optimization Algorithm for Deep Neural Networks
Progress in deep learning is slowed by the days or weeks it takes to train large models. The natural solution of using more hardware is limited by diminishing returns, and leads to inefficient use of additional resources. In this paper, we present a large batch, stochastic optimization algorithm that is both faster than widely used algorithms for fixed amounts of computation, and also scales up...
متن کاملNeumann Optimizer: a Practical Optimization Algorithm for Deep Neural Networks
Progress in deep learning is slowed by the days or weeks it takes to train large models. The natural solution of using more hardware is limited by diminishing returns, and leads to inefficient use of additional resources. In this paper, we present a large batch, stochastic optimization algorithm that is both faster than widely used algorithms for fixed amounts of computation, and also scales up...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEICE Transactions on Information and Systems
سال: 2023
ISSN: ['0916-8532', '1745-1361']
DOI: https://doi.org/10.1587/transinf.2022edp7119