理学 随机梯度下降 释 stochastic gradient descent; SGD 随机梯度下降 依据损失函数的梯度，在一次迭代中对每一个训练实例进行预测，并重复迭代该过程到一定的次数，从而最小化一个函数的过程。在机器学习中，可以利用该方法来最小化训练模型中的误差，即每次迭代时完成一次评估和更新。
人工智能 神经网络 释文 stochastic gradient descent 随机梯度下降法
- history of libraries in modern western countries
- history of library science in modern China
- History of Literature in Vernacular Chinese
- History of Liu Song Dynasty
- History of Logic
- History of Logic in the West
- history of Lutjanus sanguineus fishing in China
- history of Marburg virus
- history of Marshall Islands
- history of Marxist philosophy
- history of mathematics
- History of Mathematics Handout
- history of mathematics in China
- history of mechanical engineering education in China
- history of mechanical measurements
- history of mechanics in China
- history of mechanics in the world
- history of medical education
- history of medicinal crops cultivation
- History of Medicine
- history of medicine
- history of medicine in Korea
- history of memory
- history of mentalities
- history of metallurgy