Machine-translated by Google. Questions are authored in English.
Top

Discussion

What is the risk of a widely used benchmark?

  • A.The benchmark data becomes corrupted through repeated use
  • B.Methods become tuned to it and generalise less well elsewhere
  • C.Benchmarks become too easy as computers become faster
  • D.Only large organisations can afford to run the evaluation

Answer: B

Repeated evaluation on the same data amounts to fitting the test set through the accumulated choices of the community, so reported gains overstate what would be seen on fresh data. Held out challenge sets and periodic replacement are the usual responses. Hardware, cost and data integrity are practical issues rather than the fundamental one. Selection pressure applied to a fixed target eventually optimises for the target rather than for what it was meant to represent.

No comment is present. Be the first to comment.
Loading…

Post your comment

Please log in or register to post a comment.