官术网_书友最值得收藏!

Algorithm

The algorithm of the prototypical networks is shown here:

  1. Let's say we have the dataset, D, comprising {(x1, y1), (x2, y2), ... (xn, yn)} where x is the feature and y is the class label.
  2. Since we perform episodic training, we randomly sample n number of data points per each class from our dataset, D, and prepare our support set, S.
  3. Similarly, we select n number of data points and prepare our query set, Q.
  4. We learn the embeddings of the data points in our support set using our embedding function, f? (). The embedding function can be any feature extractor—say, a convolutional network for images and an LSTM network for text.
  5. Once we have the embeddings for each data point, we compute the prototype of each class by taking the mean embeddings of the data points under each class:
  1. Similarly, we learn the query set embeddings.
  2. We calculate the Euclidean distance, d, between query set embeddings and the class prototype.
  3. We predict the probability, p?(y = k|x), of the class of a query set by applying softmax over the distance d:
  1. We compute the loss function, J(?), as a negative log probability, J(?) = -logp?(y=k|x), and we try to minimize the loss using stochastic gradient descent.
主站蜘蛛池模板: 晋宁县| 定襄县| 尉犁县| 安丘市| 宿松县| 左云县| 会宁县| 威远县| 顺昌县| 清镇市| 赣榆县| 裕民县| 灵石县| 武胜县| 西乌珠穆沁旗| 蒲城县| 辽源市| 达州市| 巴青县| 灌云县| 双鸭山市| 西林县| 黎平县| 瑞安市| 寻乌县| 建阳市| 大庆市| 景泰县| 松桃| 阿城市| 神池县| 芮城县| 灵台县| 哈密市| 卢龙县| 隆尧县| 丽江市| 克东县| 扎兰屯市| 屏东市| 广宁县|