官术网_书友最值得收藏!

Calculating errors

The first thing in backpropagation is to calculate the errors from forward propagation for your target value. The input provides y as a test for the accuracy of the network’s output, so we compute the following vector:

This is written in code as follows: 

# define error, which is the difference between the activation function output from the last layer and the label
error = tf.sub(a_2, y)
主站蜘蛛池模板: 天峨县| 永和县| 沁源县| 淳安县| 泰来县| 美姑县| 乐清市| 嵊泗县| 云浮市| 新宁县| 且末县| 大邑县| 乌拉特后旗| 德昌县| 玉溪市| 阿鲁科尔沁旗| 安平县| 霍山县| 徐闻县| 定边县| 汽车| 原阳县| 高邮市| 高州市| 东乌珠穆沁旗| 嘉荫县| 通辽市| 石楼县| 凤阳县| 壤塘县| 太白县| 准格尔旗| 昭觉县| 眉山市| 涿州市| 海门市| 丁青县| 灵宝市| 吐鲁番市| 三门峡市| 金堂县|