An Novel Approach on the Number of Hidden Nodes Optimizing in Artificial Neural Network

Forecasting, classification, and data analysis may all gain from improved pattern recognition results. Neural Networks are very effective and adaptable for pattern recognition and a variety of other real-world problems, such as signal processing and classification concerns. Providing improved pattern recognition results for predicting, categorizing, and data analysis. To provide correct results, neural networks need sufficient data pre-processing, architecture selection, and network training; nevertheless, the performance of a neural network is reliant on the size of its network. The correct preparation of data, selection of architecture, and training of the network are all required for ANN to provide satisfactory results; yet, the efficacy of a neural network still depends on its size. Fundamental to the field of artificial neural networks is the detection of hidden neurons in neural networks. The random selection of hidden neurons may result in either under fitting or over fitting. Over fitting happens when the network's ability to expand beyond the test data is hindered as a result of an abnormally close fit between the data and the network. After training the ANN with real-world data, the proposed method calculates the approximately optimal number of hidden nodes. The number of hidden nodes is determined depending on the similarity of the input data, as per the specified method