Conclusions

Intelligent Agents
- problem-solving and search
- knowledge and reasoning
- planning
- uncertainty reasoning
- learning
- perception
  - natural language processing
  - vision
  - speech processing
- other functionality
  - taste
  - smell
  - touch
  - manipulation of environment
    - robotics
  - emotion
  - ethics
- computational constraints
  - rationality
  - bounded optimality
- consider example from first class
  - can we build an intelligent TAGER student?

Platform
- C, C++
  - need symbol processing
  - need inference engine
  - only procedural
  + low-level control
  + fast
- Lisp
  + symbol processing
  - still need inference engine
  - still only procedural
  + reasonably low-level control
  - slow
  + can be converted to C
- Prolog
  + symbol processing
  + built-in inference engine
  + declarative and procedural
  - low-level control difficult
  - slow
  + can be converted to C

Questions
- what goes into a general-purpose intelligent agent?
  - see above
- what is the ideal platform for the agent?
  - hardware/software
  - parallelism
- will the agent be intelligent, thinking or conscious?
  - see Chapter 26, Russell and Norvig
- what will happen if we succeed (rn26)
  - see Chapter 27, Russell and Norvig (rn27)