INFOH419 Data Warehousing - Week 11

Small Summary

  • Data mining
    • high-level overview of clustering, classification, pattern mining
    • common errors: causality vs correlation, multi-hypotheses testing
  • Data stream processing
    • epsilon-delta approximations
    • maintaining a uniform sample
    • counting the number of distinct elements

Supporting material

Exercises

No Exercises this week

 
teaching/infoh419_-_week_11_lecture.txt · Last modified: 2012/11/29 15:33 by tcalders