[Knowledge-based AI] {ud409} Lesson 19: 19 - Version Spaces

Optional reading: Winston Chapter 20

Incremental Concept Learning Revisited

Abstract Version Spaces

Visualizing Version Spaces

converge

model is thre representation of the world

Example Food Allergies I

Identification Trees

decision tree learning

Optimal Identification Trees

decision tree lead to more optimal tree, but decision tree has a requirement: need all examples right up front

Discrimination tree (in case-base reasoning) may lead to suboptimal trees, bu you can learn incrementally

原文地址:https://www.cnblogs.com/ecoflex/p/10984442.html

时间: 2024-07-30 09:30:52

[Knowledge-based AI] {ud409} Lesson 19: 19 - Version Spaces的相关文章

[Knowledge-based AI] {ud409} Lesson 2: 02 - Introduction to CS7637

Optional Readings : Putting Online Learning and Learning Sciences Togetherhttps://www.youtube.com/watch?v=N56ghCGmWWQ Understanding the Natural and Artificial Worldshttp://courses.washington.edu/thesisd/documents/Kun_Herbert%20Simon_Sciences_of_the_A

[Knowledge-based AI] {ud409} Lesson 24: 24 - Meta-Reasoning

Mistakes in Reasoning and Learning Beyond Mistakes: Knowledge Gaps The Blurred Line Between Cognition and Metacognition Strategy Selection Strategy Integration Optional Reading: Metacognition in Computation: A selected research review by Michael T. C

[Knowledge-based AI] {ud409} Lesson 26: 26 - Wrap-Up

represent => reason => represent =>.... data => knowledge => data > ...... Current Research 原文地址:https://www.cnblogs.com/ecoflex/p/10987521.html

[Knowledge-based AI] {ud409} Lesson 12: 12 - Logic

Why do we need formal logic? Inferences About Birds Winston Chapter 13: Page 284 Exercise: Inferences About Foos Predicates Conjunctions and Disjunctions Implies Notation Equivalency Truth Tables 原文地址:https://www.cnblogs.com/ecoflex/p/10982993.html

[Knowledge-based AI] {ud409} Lesson 13: 13 - Planning

Block Problem Revisited Painting a Ceiling States Optional Reading: Winston Chapter 15, pages 323-336 Operators Planning and State Spaces plan: Planning Partial Planning Detecting Conflicts Open Preconditions Hierarchical Task Network Planning Hierar

[Knowledge-based AI] {ud409} Lesson 21: 21 - Configuration

Exercise: Designing a Basement Defining Configuration The Configuration Process left top: task right bottom: solution task v1 --- Configuration Space ---> solution v1 (search solution) solution v1 takes too long solution v1 --- Configuration Space --

[Knowledge-based AI] {ud409} Lesson 22: 22 - Diagnosis

Optional reading: Stefik, Chapter 9 diagnose as classification and abduction Exercise: Diagnosing Illness Defining Diagnosis Problems with Diagnosis as Classification Deduction, Induction, Abduction Optional Reading: Stefik, Diagnosis and Troubleshoo

[Knowledge-based AI] {ud409} Lesson 23: 23 - Learning by Correcting Mistakes

Optional Readings : Winston Chapter 18 http://courses.csail.mit.edu/6.034f/ai3/rest.pdf Questions for Correcting Mistakes Visualizing Error Detection Error Detection Algorithm Explanation-Free Repair Explaining the Mistake Correcting the Mistake Conn

【hadoop】第一个UDF小例子 此博文包含图片 (2013-09-23 19:19:13)

之前做过一个例子,但是有问题,中间因为其他事情给耽搁了,就忘记了,今天帮同事查数据,要写一个UDF,又发现了同一个问题,最终解决了.下边整理一下我的小例子,由于hive表中存放的时间是Long型的字符串,需要将其转化成时间: 1.首先创建一个java项目,根据需要命名. 2.导入hive需要的jar包: 3.在项目中创建一个类,extends UDF:package cn.hive.udf; import java.sql.Date;import java.text.SimpleDateForm