Problems in AI: Difference between revisions
Mr. MacKenty (talk | contribs) No edit summary |
Mr. MacKenty (talk | contribs) No edit summary |
||
Line 9: | Line 9: | ||
# World knowledge is dynamic but knowledge is limited | # World knowledge is dynamic but knowledge is limited | ||
# How can we get an AI agent to explain or justify it's decisions? | # How can we get an AI agent to explain or justify it's decisions? | ||
# Data arrives incrementally | |||
# Problems exhibit recurring patterns | |||
# Problems have multiple levels of granularity | |||
# Many problems are computationally intractable | |||
# The world is dynamic, but knowledge of the world is static | |||
# The world in open-ended, but knowledge is limited. | |||
Latest revision as of 19:51, 8 January 2018
I used this material from my course: knowledge-based AI:
- All intelligent agents have limited resources
- Computation is local, but problems have a global context
- Computational logic is deductive, but many problems are inductive
- World knowledge is dynamic but knowledge is limited
- How can we get an AI agent to explain or justify it's decisions?
- Data arrives incrementally
- Problems exhibit recurring patterns
- Problems have multiple levels of granularity
- Many problems are computationally intractable
- The world is dynamic, but knowledge of the world is static
- The world in open-ended, but knowledge is limited.