Paper Title
Combining Softmax and Maxout Activation Functions to Improve Accuracy in EEG Emotion Prediction

Abstract
An electroencephalogram (EEG) is a check used to evaluate the electric activity in the mind. Mind cells talk with every other cells via electrical impulses. An EEG can be used to help detect potential problems associated with this activity..An EEG tracks the statistics of mind wave patterns. Small flat metallic discs known as electrodes are attached to the scalp with wires. The electrodes analyze the electric impulses inside the mind and ship signals to a computer that analyse the data. Here , in this research we have improved accuracy in EEG emotion prediction by creating our own custom activation function. Activation functions are those functions that take real numbers as input, and output a binary value (either a 1 or a 0). If the output of the activation function is a zero, then the neuron is said to remain inactive. If the output of the activation function is a one, then the neuron is said to be firing (or active). So, the activation function is a way for us to mathematically mimic the firing of a biological neuron. Keywords - Electroencephalogram, Artificial Neural Networks, Activation Function, Classification Accuracy.