Evaluation of Error Probability of Classification Based on the Analysis of the Bayes Code

11 Jan 2020 Saito Shota Matsushima Toshiyasu

Suppose that we have two training sequences generated by parametrized distributions $P_{\theta_1^*}$ and $P_{\theta_2^*}$, where $\theta_1^*$ and $\theta_2^*$ are unknown. Given training sequences, we study the problem of classifying whether a test sequence was generated according to $P_{\theta_1^*}$ or $P_{\theta_2^*}$... (read more)

PDF Abstract
No code implementations yet. Submit your code now

Categories


  • INFORMATION THEORY
  • INFORMATION THEORY