官术网_书友最值得收藏!

Rectified linear unit (ReLU)

The output of a ReLU is linear when the total input to the neuron is greater than zero, and the output is zero when the total input to the neuron is negative. This simple activation function provides nonlinearity to a neural network, and, at the same time, it provides a constant gradient of one with respect to the total input. This constant gradient helps to keep the neural network from developing saturating or vanishing gradient problems, as seen in activation functions, such as sigmoid and tanh activation units. The ReLU function output (as shown in Figure 1.8) can be expressed as follows:

The ReLU activation function can be plotted as follows:

Figure 1.8: ReLU activation function

One of the constraints for ReLU is its zero gradients for negative values of input. This may slow down the training, especially at the initial phase. Leaky ReLU activation functions (as shown in Figure 1.9) can be useful in this scenario, where the output and gradients are nonzero, even for negative values of the input. A leaky ReLU output function can be expressed as follows:

       

The  parameter is to be provided for leaky ReLU activation functions, whereas for a parametric ReLU,  is a parameter that the neural network will learn through training. The following graph shows the output of the leaky ReLU activation function:

Figure 1.9: Leaky ReLU activation function
主站蜘蛛池模板: 泗洪县| 大方县| 德庆县| 凤阳县| 农安县| 祁东县| 临汾市| 如东县| 湖州市| 从江县| 苏尼特左旗| 奉贤区| 佛教| 故城县| 邹平县| 法库县| 杨浦区| 秭归县| 湖南省| 祥云县| 宝兴县| 西宁市| 泗洪县| 手游| 常宁市| 昌都县| 仪征市| 临泽县| 齐齐哈尔市| 大余县| 清原| 屯门区| 绥宁县| 四川省| 林口县| 饶平县| 双牌县| 抚宁县| 汪清县| 蕉岭县| 白朗县|