This paper proposes an improved softmax layer algorithm and hardware implementation, which is applicable to an effective convolutional neural network of EEG-based real-time human emotion recognition. Compared with the general softmax layer, this hardware design adds threshold layers to accelerate the training speed and replace the Euler's base value with a dynamic base value to improve the network accuracy. This work also shows a hardware-friendly way to implement batch normalization layer on chip. Using the EEG emotion DEAP database, the maximum and mean classification accuracy were achieved as 96.03% and 83.88% respectively. In this work, the usage of improved softmax layer can save up to 15% of training model convergence time and also increase by 3 to 5% the average accuracy.