본문 바로가기

분류 전체보기63

[강의]시즌1 딥러닝의기본 - Linear Regression의 cost 최소화 알고리즘 How to minimize cost Hypothesis and CostSimplified hypothesisH(x) = Wx ( b=0) What cost(W) looks like? * W=1, cost(W) = 0 * W=0, cost(W) = 4.67 * W=2, cost(W) = 4.67W에 대한 cost(W) 값을 그려보자 . 가운데 값 찾아내는 것! Gradient descent algorithm(경사 ) (감소)* Minimize cost function* Gradient descent is used many minimization problems* For a given cost function, cost(W,b), it will find W,b to minimize cost* It can .. 2017. 1. 20.
[강의]시즌1 딥러닝의기본 - Linear Regression의Hypothesis와 cost Predicting exam score : regressionx(hours) y(score)training data set. 을 통해서 learning.labeled data. y is range. After learning , put x . Then get y. (Linear) Hypothesis 는 어떤 1차원의 선이 존재할 것이다. 라고 가정하는것.H(x) = Wx + b 어떤 선이 우리가 찾던 선인가.?Which hypothesis is better ? hypothesis 와 data point 와 비교한다 ( 거리를 측정 =cost function,loss function) Cost function * How fit the line to our (training) dataH(x) - y ->no.. 2017. 1. 20.
[강의]시즌1 딥러닝의기본 - 기본적인 Machine Learning의 용어와 개념 Basic concepts* What is ML?* what is learning?-supervised-unsupervised* what is regression?* what is classification? Matching Learning* Limitations of explicit programming(개발자가 이런환경에서는 이렇게 작동하라. 라고 explicit 하게 한 경우)(spam필터 기능들은 explicit 하지 않으므로 동작하기 어렵다.) - spam filter : many rules - Automatic driving : too many rules * Machine learning : "Field of study that gives computers the ability to learn.. 2017. 1. 20.
[강의]시즌1 딥러닝의기본 - 수업의 개요 Audience* Want to understand basic machine learning(ML)* No/weak math/computer science background- y = Wx + b(y = ax+b) 이 정도의 수준으로 가능.* Want to use ML as black-box with basic understanding* Want to use Tensorflow and Python(optional) GoalsBasic understanding of machine learning algorithms * Linear regression, Lgistic regression ( classification) * Neural networks, Convolutional Neural Network,Re.. 2017. 1. 20.