Evaluating the Performance of Deep Learning Techniques on Classification Using Tensor Flow Application

Abstract

In Deep Learning, Artificial intelligence is the overall bigger domain, in which machines given the capability to learn new instances of data and then adapt to the basic domain of Machine Learning. Deep Learning is a subset of it, which goes into further accuracy that uses neural networking technology to go in and enable more complex situational data to come in and make more precise decisions. The objective of this research is to find out the details like Ratio of training data, Noise, Batch Size, Properties of features, learning rate, Type of Activation function, Level of Regularization, Rate of Regularization in constructing Neural Network on four different Classification Datasets after directly manipulating design providing in Tensor flow playground application. The Evaluation parameters consider in our experiments are Test loss and Training lose. The findings in our research is to specify that, how many hidden layers and number of neurons in each hidden layer are needed, for each type of classification problem. These findings help the researchers to fix the Maximum number of neurons and hidden layers needed in solving the four different types of classification problems by achieving test loss less than 0.005.