Efficient Method for Optimizing Artificial Neural Network Using „Quantum-Based Algorithm‟

This paper presents competent Method for Optimizing Artificial Neural Network Using Quantum Based Algorithm. In the evolutionary process, the Quantum bits refined so that the probability of finding the optimal network is increased. The probability representation reduced the non positive impact of the permutation problem and the risk of the potential network. To finds near-optimal connection weights, the technique of subspace search using quantum bits is proposed. The algorithm thus performed a division-by-division exploration in the beginning and, as the candidate subspaces are identified, a randomized search in good subspaces is employed for exploitation. This is helpful to provide a set of appropriate weights when evolving the network structure and to alleviate the noisy fitness evaluation problem. The Propose model Improved QNN performance better than standard QNN based on some bench test function. Application examples on iris and breast cancer are shown the Improved QNN performance better than standard QNN based.