What is AI?
The development of programs to simulate human behaviour. Including:
- Image recognition: identifies objects or people in an image
- Speech recognition: identifies words spoken and stores them
- Natural language: receives commands or instructions that are not in a set format and performs the required response
- Computer games: move elements or characters independently based on the environment
- Diagnosis systems: used to diagnose certain conditions, eg. using a patient's symptoms to detect the illness and suggest actions to cure
Components of AI
- Collection of data
- A set of programmed rules
- The ability to reason
- The ability to learn and adapt
Describe the characteristics of AI
- Collects data; stores rules for using the data
- Has the ability to reason
- Has the ability to learn by using machine learning
- …by adapting what it does
- …for example from mistakes previously made, to not make them again
- …by changing its own rules
- …by changing its own data
- …by being trained
- Makes one or more predictions (to make a decision)
- Find/analyse patterns
Machine Learning
What is machine learning?
- Is when a program has the ability to automatically adapt its own processes and/or data
Explain how a program can use AI to help a robot solve different puzzles
- Use machine learning algorithms
- Collects data about where it has been
- Collects data about obstacles
- Stores successful actions; stores unsuccessful actions
- Identifies and stores patterns
- …make sure it does not repeat incorrect route
- …so it knows how to react to obstacles next time
- …so it knows what is most likely to work next time
Expert Systems
What is an expert system?
- A special type of system that attempts to emulate the expertise of a human.
- Achieved by asking questions to determine the solution to the answer
- Depending on the choices the system will ask a different question
Expert System Key Features/Components
Knowledge base:
- A repository of facts
- A collection of objects and their attributes
Rule base:
- A collection of inference rules used to draw conclusions
- Inference rules are used by the inference engine to draw conclusions
Inference engine:
- A kind of search engine used in an expert system which examines the knowledge base for information that matches the queries
- The inference engine is the problem-solving part of the expert system that makes use of inference rules in the rules base
Interface:
- Used to allow the user to interact with the expert system
- Interaction can be through dialogue boxes, command prompts or other input methods
Why does an expert system need a knowledge base?
- It needs facts…
- …to generate the rules
- …to make the decisions // The data it contains is essential to the decision making process
Advantages of Expert Systems
- They offer a high level of expertise
- They offer high accuracy
- The results are consistent
- They have the ability to store vast amounts of ideas and facts
- They can make traceable logical solutions and diagnostics
- It is possible for an expert system to have multiple expertise
- They have very fast response times (much quicker than a human expert)
- They provide unbiased reporting and analysis of the facts
- They indicate the probability of any suggested solution being correct.
Disadvantages of Expert Systems
- Users of the expert system need considerable training in its use to ensure the system is being used correctly
- The set up and maintenance costs are very high
- They tend to give very “cold” responses that may not be appropriate in certain medical situations
- They are only as good as the information/facts entered into the system
- Users sometimes make the very dangerous assumption that they are infallible.