其实质是采用梯度下降法使权值的改变总是朝着误差变小的方向改进,最终达到最小误差。
The essence of back propagation networks is that make the change of weights become little by gradient descent method and finally attain the minimal error.
从单极性输出改为双极性输出。 (3)改变能量函数使权值修正根据输出误差的大小而改变。
The single-extreme output is replaced by the double-extreme output(3) Changing the energy function updatesweights according to output errors.
作为传感器的性能,采用不同的权值测量燃着的手指和相应的阻力是改变传统的电阻测量来衡量。
The performance as a sensor is measured by applying different weights to the tip of a finger and the corresponding change of resistance is measured by a conventional resistance measurement.
应用推荐