本文共 740 字,大约阅读时间需要 2 分钟。
(Machine Learning Foundations)—Mathematical Foundations
,副教授 (Associate Professor),资讯工程学系 (Computer Science and Information Engineering)
circular separable 圆圈可分
feature transform
perceptrons in Z Z -space ⟺ ⟺ quadratic hypotheses in X X -space
The Nonlinear Transform Steps
linear model A A , not just binary classification
Q次多项式转换
d维数据,转换的Q次项有 CdQ+d C Q + d d 个
careful about your brain’s ‘model complexity’
human learning 加到模型上去,造成模型不错的错觉
structure: nested Hi H i
Structured Hypothesis Sets
safe route
linear model: simple, efficient, safe, and workable!