Study/CSC-4220 - Data Mining Machine Learning
2023.02.15
1. Supervised Learning Linear Regression > 1-1. Linear Regression - Summary Model $ f_\theta = \theta_0 + \theta_1;x $ $x$ → $f_\theta(x)$ → $\hat{y}$ Model Parameters : $\theta_0$ = Bias , $\theta_1$ = Weight Finding Model Parameters find $\Theta_0$ and $\Theta_1$ that minimize the loss/cost function (MSE) solve : $$ \min_{ \theta_0 , \theta_1} \frac{1}{2M}(\sum_{m=1}^{M}(y - f_\theta(x))^2) $$..
Study/CSC-4220 - Data Mining Machine Learning
2023.02.15
0. Intro > 0-3. Introduction Supervised Learning 지도학습 ← labeled data Regression 변수간의 관계 Predict continuous valued output ex) Predict housing prices : price vs house size Classification Predict discrete valued output (class) ex) Breast Cancer (malignant 악성 or benign 양성) : class vs tumor size Unsupervised Learning 비지도학습 ← unlabeled data Clustering Find some structure in the data ex) Google News, S..
Study/CSC-4220 - Data Mining Machine Learning
2023.02.15
0. Intro > 0-2. Introduction - Summary What? Performance ↑ improves with Experience ↑ E : Experience T : Task P : Performance Why? Exact method unknown Exact method expensive Dynamic System : Task change over time Automate process Replace humans How? Supervised Learning Unsupervised Learning Reinforcement Learning ← labeled data (x,y) ← unlabeled data Penalty training dataset just input dataset ..
Study/CSC-4220 - Data Mining Machine Learning
2023.02.15
0. Intro > 0-1. Intro Course Time Lectures: Monday and Wednesday 2:30 – 3:45 pm , Room: Bruner 228 Course Schedule Topics covered in the course: Introduction What, Why, and How? Python Part 1: Supervised Learning Basic Algorithms: Linear regression, logistic regression, support vector machine (SVM), Neural Networks (NNs) Anatomy of a learning algorithm Basic practice: datasets, underfitting & ov..
