Cargando…
Analysis on Optimal Error Exponents of Binary Classification for Source with Multiple Subclasses
We consider a binary classification problem for a test sequence to determine from which source the sequence is generated. The system classifies the test sequence based on empirically observed (training) sequences obtained from unknown sources [Formula: see text] and [Formula: see text]. We analyze t...
Autores principales: | Kuramata, Hiroto, Yagi, Hideki |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9141706/ https://www.ncbi.nlm.nih.gov/pubmed/35626520 http://dx.doi.org/10.3390/e24050635 |
Ejemplares similares
-
On the Optimal Error Exponent of Type-Based Distributed Hypothesis Testing †
por: Tong, Xinyi, et al.
Publicado: (2023) -
Error Exponents and α-Mutual Information
por: Verdú, Sergio
Publicado: (2021) -
Trade-offs between Error Exponents and Excess-Rate Exponents of Typical Slepian–Wolf Codes
por: Tamir (Averbuch), Ran, et al.
Publicado: (2021) -
Error Exponents of LDPC Codes under Low-Complexity Decoding
por: Rybin, Pavel, et al.
Publicado: (2021) -
The role of vascular complexity on optimal junction exponents
por: Keelan, Jonathan, et al.
Publicado: (2021)