머신러닝17 [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. [논문] Human-level control through deep reinforcement learning 인하대학교 이필규 교수님이 추천해주신 논문을 읽어보도록 하겠습니다.http://www.nature.com/nature/journal/v518/n7540/full/nature14236.html Human-level control through deep reinforcement learning 이라는 제목의 논문으로 nature 입니다.The theory of reinforcement learning provides a normative account , deeply rooted in psychological and neuroscientific perspectives on animal behavior, of how agents may optimize their control of an environment... 2017. 1. 20. 이전 1 2 3 4 5 다음
