liveBook · Manning

Artificial intelligence

As explained in AI-Powered Search

Artificial intelligence is the capability of a computer program to perform tasks that previously required human intelligence.

Artificial intelligence is the capability of a computer program to perform a task that previously required human intelligence. In software, the term includes machine-learning systems and rules-based systems that produce human-like feedback. section 1.1

AI-powered search applies this broad definition to the pipeline for finding and ordering information:

  • Matching finds documents that correspond to a query. section 1.1
  • Ranking orders matched documents by relevance. section 1.1
  • Preprocessing can improve query understanding, while postprocessing can extract answers or summarize results. section 1.1
Figure 1.1 AI-powered search includes all the technologies and techniques at the intersection of the fields of search and AI. These overlap heavily with and use the fields of data science, machine learning, and deep learning.
figure

Use the figure to locate AI-powered search at the intersection of search, data science, machine learning, and deep learning. section 1.1

How AI-Powered Search covers it

How deep it goes
Defines AI broadly and distinguishes machine-learning from rules-based systems, but stops short of detailed algorithmic implementation.
Examples
Uses self-driving cars, autonomous robots, human-like feedback, web search, product search, enterprise search, and generative AI context retrieval.
How it connects
Connects artificial intelligence to machine learning, deep learning, data science, search, matching, ranking, and generative AI.

Also explained in

Compare how 23 books explain artificial intelligence →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of AI-Powered Search. The section links point to the parts of the book it draws on.