NEURAL ENTROPY ENHANCED MACHINE LEARNING
    3.
    发明申请

    公开(公告)号:US20190197406A1

    公开(公告)日:2019-06-27

    申请号:US15853458

    申请日:2017-12-22

    IPC分类号: G06N3/08 G06F15/18

    CPC分类号: G06N3/082 G06N3/063 G06N20/00

    摘要: A computer implemented method of optimizing a neural network includes obtaining a deep neural network (DNN) trained with a training dataset, determining a spreading signal between neurons in multiple adjacent layers of the DNN wherein the spreading signal is an element-wise multiplication of input activations between the neurons in a first layer to neurons in a second next layer with a corresponding weight matrix of connections between such neurons, and determining neural entropies of respective connections between neurons by calculating an exponent of a volume of an area covered by the spreading signal. The DNN may be optimized based on the determined neural entropies between the neurons in the multiple adjacent layers.