Non-Binary Dataset
Jump to navigation
Jump to search
A Non-Binary Dataset is a numeric dataset that is composed of non-binary records.
- Example(s):
- Counter-Example(s):
- See: Non-Negative Data, Positive-Valued Data.
References
2000
- (Baldi et al., 2000) ⇒ Pierre Baldi, Søren Brunak, Yves Chauvin, Claus AF Andersen, and Henrik Nielsen. (2000). “Assessing the Accuracy of Prediction Algorithms for Classification: An Overview." Bioinformatics 16, no. 5
- QUOTE: … [math]\displaystyle{ H (D, M) = N ∑_{i=1} [ d_i \log d_i m_i + (1 − d_i) \log (1 − d_i) (1 − m_i) ] }[/math]. (16) This is just the sum of the relative entropies at each position i. This form, of course, works perfectly well on non-binary data (for example binding affinities), or when D alone is binary. ...