仓库源文，站点原文

layout: post title: "KBAI 笔记 10 Incremental Concept Learning" date: "2019-01-01 08:36:27" categories: 计算机科学 excerpt: "Preview Exercise: Identifying a Foo I background knowledge is important ..."

auth: conge

• content {:toc}

Preview

Exercise: Identifying a Foo I

• background knowledge is important to make the judgement whether the fourth graph shows the concept of foo.

Exercise: Identifying a Foo II

Exercise: Identifying a Foo III

• yes or no answer could be correct. yes is a generalization and no is a specification
• learning is incremental (learn from one example at a time)
• examples are labeled.
• examples come from specific order
• differ from K space reasoning
• the number of examples is small.
• what to learn is going to be a hard question( over generalization or over specification)

Incremental Concept Learning

Example of over generalization and over specification using children as example. what is a dog.

Variabilization

AI representation of an Arch.

Generalization to Ignore Features

Specialization to Require Features

Specialization to Exclude Features

Generalization to Abstract Features

Generalization with Background Knowledge

An Alternative Visualization

Heuristics for Concept Learning

Exercise: Re-Identifying a Foo I

Exercise: Re-Identifying Foo II

Exercise: Re-Identifying Foo III

The concept of block can be brick or Cylinder.

Exercise: Re-Identifying Foo VI

• the example is not a concept and the current COncept is already exclusive. we don't need to do anything or learn anything.

Final Concept of a Foo

• when there is limited number of examples, Agent has to use its background knowledge and use all the examples to incrementally learn the concept.

Assignment

Wrap Up

The Cognitive Connection

In real life, cognitive agent like humans are usually given one example after another. Incremental concept learning is the closed way of how human learn new concept.