ݠन۞ (Machine Learning) • “The field of study that gives computers the ability to learn without being explicitly programmed.” - Arthur Samuel • “A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E.” - Tom Mitchell • : ߄قѱਸ فח ஹೊఠ - E = ߄قѱਸ فח ҃ - T = ߄قѱਸ فח ೯ਤ - P = ஹೊఠо ౸ ߄قਸ ӡ ഛܫ
Linear Regression • y = a * x + b - x: և(ಣ) - y: оѺ - h(x) ৬ э അೞӝب ೣ (hypothesis, оࢸ) - ৬ э അ • Training dataܳ learning algorithmী ਊ, h ܳ ҳೣ! • h ܳ ਊೞৈ x ী ೠ Ѿҗч (y) ܳ ஏ оמ
Linear Regression Gradient Descent (for fixed , this is a function of x) (function of the parameters ) (for fixed , this is a function of x) (function of the parameters ) (for fixed , this is a function of x) (function of the parameters ) (for fixed , this is a function of x) (function of the parameters )
Linear Regression Gradient Descent (for fixed , this is a function of x) (function of the parameters ) (for fixed , this is a function of x) (function of the parameters ) (for fixed , this is a function of x) (function of the parameters ) (for fixed , this is a function of x) (function of the parameters )
Neural Network - Back Propagation • Back propagation Layer 1 Layer 2 Layer 3 Layer 4 Intuition: “error” of node in layer . For each output unit (layer L = 4)