一个小demo,用softmax实现数据分类，数据有4类，均服从高斯分布-A little demo, a classifier with softmax softmax is implemented to classify 4 classes of datas which are generated by gaussian distribution

去掉神经元类，把功能合并入NetLayer类中，使用矩阵计算加快速度 调整代码实现批量训练方法。 优化程序中numpy库运算顺序，避免产生中间变量(Remove neuron classes, merge functions into NetLayer classes, and use matrix to calculate speed.)