This study uses two meta-heuristics methodologies to introduce two novel quantum-inspired meta heuristic approaches: quantum-inspired genetic algorithm (QIGA1) and quantum-inspired genetic algorithm with dynamic approach (QIGA2). The two suggested methods combine a classical and quantum genetic algorithm approach. Both approaches use The correlation coefficient as an assessment function to identify the best (optimal) values for binary image. In quantum computing, they use simple ideas like qubits and state superposition. Due to these characteristics, parallelism which uses the time discreteness of quantum mechanical systems, is exhibited. For five distinct MNIST datasets, the performance of all participating algorithms has been assessed by comparing the suggested approaches first with their traditional approach counterparts and then with the proposed methods QIGA1 and QIGA2. Each method's ideal threshold value, associated fitness value (best and average), loss, and accuracy for each MNIST dataset have all been published. The outcomes demonstrate the superior efficiency of the suggested approaches over their traditional equivalents.
翻译:暂无翻译