Labeled Training Record

A labeled training record is a labeled learning record in the role of being a training record (with a known training record value)

• AKA: Labeled Training Case, Labeled Training Instance, Training Pair.
• Context:
  • It can be a member of a Labeled Training Record Set.
  • It can be a task output to a Learning Record Labeling Task.
  • It can range from being a Strongly Labeled Training Record to being a Weakly Labeled Training Record.
  • It can be:
    • a Binary Training Record (such as a Positive Training Record)
    • a Multi-Valued Training Record.
    • a Real-Valued Training Record.
• Example(s):
  • (Name=N/A, Gender=Male, Age=54, BankruptcyInPast5Years=Yes, CreditRisk=High); Target_Class=CreditRisk
  • any Labeled Training Document.
  • …
• Counter-Example(s):
  • an Unlabeled Training Record.
  • a Labeled Testing Record.
• See: Concept Instance, Classifier Training Algorithm, Statistical Modeling Task.

---

---

References

• http://www.google.ca/search?q=%22a+labeled+training%22
• http://scholar.google.ca/scholar?q=%22a+labeled+training%22

2004

• (Hastie et al., 2004) ⇒ Trevor Hastie, Saharon Rosset, Robert Tibshirani, and Ji Zhu. (2004). “The Entire Regularization Path for the Support Vector Machine.” In: The Journal of Machine Learning Research, 5.
  • QUOTE: In this paper we study the support vector machine (SVM)(Vapnik, 1996; Schölkopf and Smola, 2001) for two-class classification. We have a set of [math]\displaystyle{ n }[/math] training pairs x_i, y_i, where x_i in R^p is a p-vector of real-valued predictors (attributes) for the i^th observation, and y_i in {−1,+1} codes its binary response. …

---