Scribd
Upload
75 views

3 - Intelligent System

The document discusses artificial intelligence and intelligent systems. It defines intelligent systems as systems that incorporate intelligence into machine applications using techniques like machine learning. It provides examples of intelligent systems like expert systems and intelligent agents. It then describes key characteristics of intelligent systems such as being self-explaining, robust, fault-tolerant, adaptive, self-optimizing, deductive, learning, cooperative, autonomous and agile. Finally, it outlines the main steps to build AI systems, including identifying problems, preprocessing data, choosing algorithms, training models, selecting platforms and languages, testing, and deploying.

Uploaded by

PARLAPALLI HEMANTH -2019BCSIIITK
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
75 views

3 - Intelligent System

The document discusses artificial intelligence and intelligent systems. It defines intelligent systems as systems that incorporate intelligence into machine applications using techniques like machine learning. It provides examples of intelligent systems like expert systems and intelligent agents. It then describes key characteristics of intelligent systems such as being self-explaining, robust, fault-tolerant, adaptive, self-optimizing, deductive, learning, cooperative, autonomous and agile. Finally, it outlines the main steps to build AI systems, including identifying problems, preprocessing data, choosing algorithms, training models, selecting platforms and languages, testing, and deploying.

Uploaded by

PARLAPALLI HEMANTH -2019BCSIIITK
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 7

Artificial Intelligence

Intelligent systems
Intelligent systems
 the system that incorporates intelligence into applications being
handled by machines
 perform search and optimization along with learning capabilities.
 different types of machine learning such as supervised,
unsupervised and reinforcement learning can be modeled in
designing intelligent systems.
 Expert systems, intelligent agents and knowledge-based systems
are examples of intelligent systems
 from automated vacuums such as the Roomba to facial
recognition programs to Amazon's personalized shopping
suggestions
Characteristics
 Self-explaining
 the system can explain how it came to a certain decision
 Robust
 property of a system means that the system behaves well
and adequate not only under ordinary conditions, but also under
unusual conditions
 fault tolerant
 continue to adequately perform even if one or more of its internal
system components fail or break.
 Adaptive
 react to changes, in particular to changes in the environment or the
context of the system
 self-optimizing
 organize their internal components and capabilities in new
structures without a central or an external authority in place
Characteristics
 Deductive
 based on a set of axioms and rules, they can deduct new insights by
applying the rules to the axioms as well as to the resulting new
facts.
 using an underlying inference engine; deductive systems can
discover new facts that they can use for their decision process
 deductive systems can discover new facts that they can use for their
decision process
 Learning
 observe the achieved results and compare them with the desired
outcome.
 Cooperative
 expose social capabilities; interact with other systems – and
potentially humans as well
 Autonomous
Characteristics
 Autonomous
 performs the desired tasks and behaves well and adequate
even in unstructured environments without continuous human
guidance.
 Agile
 able to manage and apply knowledge effectively so that they
behave well and adequate in continuously changing and
unpredicted environments.
Steps to build AI systems
 Identify the problem
 What are you trying to solve?
 Which result is desired?
 Preparation of the data (preprocessing)
 structured and unstructured data
 80% of their time cleaning , moving, reviewing, and organizing
 Choice of algorithms (model)
 Supervised learning
 Unsupervised learning & reinforcing learning
 Training the algorithms
 Choosing the most suitable programming language
 Platform selection
 Test the Model
 Deployment
The End…

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy