A New Learning Algorithm: SinAdaMax

Artificial Neural Networks are clearly influencing the field of machine learning since the age of the ‘Deep Learning’, roughly starting after the first 10 years of the 21st century. The neural network training success highly depends on the optimizers which modify the network weights, and these learning algorithms affect the success of the training of the networks significantly. In this work, different optimizers are employed in different problems like sentiment analysis and image classification for comparing and figuring out the successful ones. To show the success of the new optimizer SinAdaMax we proposed previously, recurrent and convolutional neural networks on different datasets are used with other well-known learning algorithms in this research.