logo资料库

deep learning-李宏毅(中文版).doc

第1页 / 共321页
第2页 / 共321页
第3页 / 共321页
第4页 / 共321页
第5页 / 共321页
第6页 / 共321页
第7页 / 共321页
第8页 / 共321页
资料共321页,剩余部分请下载后查看
Deep Learning Tutorial 李宏毅 Hung-yi Lee
Deep learning attracts lots of attention. • I believe you have seen lots of exciting results before. Deep learning trends at Google. Source: SIGMOD/Jeff Dean This talk focuses on the basic techniques.
Outline Lecture I: Introduction of Deep Learning Lecture II: Tips for Training Deep Neural Network Lecture III: Variants of Neural Network Lecture IV: Next Wave
Lecture I: Introduction of Deep Learning
Outline of Lecture I Introduction of Deep Learning Why Deep? Let’s start with general machine learning. “Hello World” for Deep Learning
Machine Learning ≈ Looking for a Function • Speech Recognition  “How are you” f  • Image Recognition • Playing Go f   f • Dialogue System f   “Cat”  “Hi” (what the user said) “5-5” (next move)  “Hello” (system response)
Framework Image Recognition: f   “cat” A set of function Model f1 , f2 f1  f1   “cat”  “dog” f2  f2   “money”    “snake”
Framework Image Recognition: f   “cat” A set of Model f 1 , f 2 function Better! Goodness of function f Training Data Supervised Learning function input: function output: “monkey” “cat” “dog”
分享到:
收藏