Measuring accuracy of Dataset using Deep Learning Algorithm RMSProp Algorithm
Abstract: Over the last few years, there have been many significant improvements in the field of AI, machine learning, deep learning are being used in various industries and research. In order to train the deep learning models learning of parameters plays a major role, here the reduction of loss incurred during the training process is the main objective. In a supervised mode of learning, a model is given the data samples and their respective outcomes. When a model generates an output, it compares it with the desired output and then takes the difference of generated and desired outputs and then attempts to bring the generated output close to the desired output. This is achieved through optimization algorithms. Though many kinds of clinical methods have been employed to detect whether patients have heart disease or not by number of features from patients. but it’s still a challenging task due to the multitude of data elements involved. The motive of our project is to save human resources in medical centers and improve accuracy of diagnosis. In our project we used an RMS prop optimizer. The purpose is to decide how many hidden layers need to be selected and how many neurons need to be selected in each and every hidden layer by looking at the dataset and to give the application of deep learning to the health care sector so that we can minimize the costs of treatment and help in proactive actions. We want to show that we can increase the accuracy of the project by taking stability along with accuracy into consideration. Index Terms: RMS Prop, Machine Learning, Deep Learning, number of features, proactive actions