Memory Organization
Memory is central to common sense behavior and also the basis for learning. Human memory is still not fully understood however psychologists have proposed several ideas,
Short Term Memory (STM): Only a few items at a time can be held here. Perceptual information stored directly here.
Long Term Memory (LTM): Capacity for storage is very large and fairly permanent.
LTM is often divided up further.
Episodic Memory: Contains information about personal experiences.
Semantic Memory: General facts with no personal meaning. Example, Birds fly. Useful in natural language understanding.
In terms of AI research work started by Quillian on semantic memory led to semantic networks and frames and other slot and filler structures. Work on episodic memory grew out of scripts. Production systems are an example of STM-LTM computer models.
Memory in Problem Solving:
Memory is employed in problem solving. We have seen that many problems are solved by analogy. Computer systems that perform this task are sometimes called case based reasoning (CBR) systems. CBR systems employ large case libraries rather than descriptions from first principles. Therefore they rely heavily on memory organization and retrieval.
- A rich indexing system must be employed - when reasoning with a problem only relevant past experience should be recalled.
- Index by features present in problem.
- Require some measure of relevance of retrieved information.
- Some features only important in a certain context.
- Inductive and explanation based learning suitable here.
- The data structures used will be important as the number of cases represented will be large.
- Do we retrieve all information about a case or fragment of it?
- A number of cases are usually retrieved. We need to select the best one using some heuristic which may include,
- i) Goal directed preference: Cases that include same goal as current problem.
- ii) Salient Feature Preference: Cases that include the most important (or largest number of) features.
- iii) Specificity Preference: Certain match features identified.
- iv) Frequency Preference: Select frequently matched cases.
- v) Recency Preference: Select recently matched cases.
- vi) Ease of Adaptation Preference: Cases whose features easily modified for new problem.
