[null,null,["上次更新時間：2025-05-19 (世界標準時間)。"],[[["This module explains how to create embeddings, which are lower-dimensional representations of sparse data that address the problems of large input vectors and lack of meaningful relations between vectors in one-hot encoding."],["One-hot encoding creates large input vectors, leading to a huge number of weights in a neural network, requiring more data, computation, and memory."],["One-hot encoding vectors lack meaningful relationships, failing to capture semantic similarities between items, like the example of hot dogs and shawarmas being more similar than hot dogs and salads."],["Embeddings offer a solution by providing dense vector representations that capture semantic relationships and reduce the dimensionality of data, improving efficiency and performance in machine learning models."],["This module assumes familiarity with introductory machine learning concepts like linear regression, categorical data, and neural networks."]]],[]]
![圖 2. 頂端：羅宋湯 one-hot 編碼的圖表。向量 [1, 0, 0, 0, ..., 0] 顯示在六個方框上方，方框由左到右分別對應一個向量數值。方框由左至右分別包含下列圖片：羅宋湯、熱狗、沙拉、披薩、[空白]、沙威瑪。中間：熱狗 one-hot 編碼的圖表。向量 [0, 1, 0, 0, ..., 0] 顯示在六個方框上方，方框由左到右分別對應一個向量數值。方框由左至右分別顯示與上方羅宋湯圖表相同的圖片。底部：沙威瑪 one-hot 編碼的圖表。向量 [0, 0, 0, 0, ..., 1] 顯示在六個方框上方，方框由左到右分別對應一個向量數值。方框中由左至右分別顯示與羅宋湯和熱狗圖表相同的圖片。](https://developers.google.cn/static/machine-learning/crash-course/embeddings/images/food_images_one_hot_encodings.png?authuser=1&hl=zh-tw)