Learning Record

A Learning Record is a data record (with learning record attributes) that is intended as task input to a learning task.

• AKA: Exemplar, Example for Learning.
• Context:
  • It can (typically) be a Feature Vectors.
  • It can (typically) be a member of a Learning Record Set.
  • It can range from being a Training Record to being a Testing Record.
  • It can range from being a High-Dimensional Learning Record to being a Low-Dimensional Learning Record.
  • It can range from being a Labeled Learning Record to being an Unlabeled Learning Record, if it has a Target Attribute.
• Example(s):
  • a Tuple Learning Record.
  • a Vector Learning Record, e.g. a fixed-length feature vector.
  • ...
• Counter-Example(s):
  • a Transactional Database Record.
• See: Random Experiment Outcome.

References

2005

• (Wong et al., 2005) ⇒ Ke Wong Wang, Senqiang Zhou, Qiang Yang, and Jack Man Shun Yeung. (2005). "Mining Customer Value: From Association Rules to Direct Marketing." Data Mining and Knowledge Discovery, 11(1).
  • QUOTE: ... Despite many efficient algorithms for mining association rules (see (Agrawal et al., 1993, 1996; Agrawal and Srikant ... any association rule mining algorithm such as Agrawal et al. ... Let profit(r, t) denote the profit generated by the prediction of r on a learning record t. The observed ...

1998

• (Kohavi & Provost, 1998) ⇒ Ron Kohavi, and Foster Provost. (1998). "Glossary of Terms." In: Machine Leanring 30(2-3).
  • Example: See Instance.

• Concept