题目描述：1.Generate n = 2,000 points uniformly at random in the two-dimensional unit square.Which point do you expect the centroid to be?2.What objective does the centroid of the points optimize?3.Apply g...

问题描述：禁止使用深度学习与梯度下降相关的库实现下列问题。Several exercises will make use of the following three-dimensional data sampledfrom three categories, denoted ωi .1. Consider a 2-2-1 network with bias, where the activati...

这里将自己做的一个PPT纪录一下，根据斯坦福大学CS234 lecture 5 整理而来Some of the content for this lecture is borrowed from Hugo Larochelle 神经网络相对于训练集：太小（欠拟合），找到的规律模型未能够很好的捕捉数据特征，不能很好的拟合数据；太大（过拟合），记住的规律太多，太具体死板地记住训练集，不够抽象。单个神经...