Simple Tasks to Accomplish
Once you've worried for why you're performing AI, what has inspired you and how you're going to approach the job, then you can initialize to think for what operation it is that you want to automate. AI is so often portrayed as a groupe of problem-solving methodes, but we think the relentless shoe-horning of intelligent tasks into one problem formulation or another is holding AI back. That said, we have examined a number of problem solving process in AI - most of which have been hinted at previously - which can be used as a characterization. The categories overlap a little bit because of the generality of the process. For instance, planning could be found in many categories, as this is a fundamental part of solving many types of problem.
Simple Techniques Generated
In the pursuit of solutions to many problems in the above categories, many personal techniques have sprung up which have been shown to be useful for solving a domain of problems (often within the general problem category). These techniques are established sufficient now to have a name and given at least a partial characterisation of AI. The given list is not intended to be finshed, but rather to introduce some process you will study later in the course. See that some of those overlap in the general techniques above.
- Forward/backward chaining (reasoning)
- Resolution theorem proving (reasoning)
- Proof planning (reasoning)
- Constraint satisfaction (reasoning)
- Davis-Putnam method (reasoning)
- Minimax search (games)
- Alpha-Beta pruning (games)
- Case-based reasoning (expert systems)
- Knowledge elicitation (expert systems)
- Neural networks (learning)
- Bayesian methods (learning)
- Explanation based (learning)
- Inductive logic programming
- (learning)
- Reinforcement (learning)
- Genetic algorithms (learning)
- Genetic programming
- (learning)
- Strips (planning)
- N-grams (NLP)
- Parsing (NLP)
- Behavior based (robotics)
- Cell decomposition (robotics)