Logistic Regression Computing Hypothesis Computing Cost Function Evaluation Higher Implementation Logistic Regression Hypothesis $${H(X) = \frac{1}{1 + e^{-W^TX}}}$$ Cost $${cost(W) = -\frac{1}{m}\sum ylog(H(x)) + (1-y)(log(1-H(x)))}$$ if ${y \simeq H(x)}$, cost is near 0 if ${y \ne H(x)}$, cost is high ${P(x = 1) = 1- P(X = 0)}$ X : ${m\times d}$ 차원, W : ${d\times 1}$ 차원 sigmoid 함수를 이용하여 0과 1에 ..