.png){kind=icon}
.png){kind=icon}
Return
Model-based learning problem taxonomies
.png){kind=icon}
PRE
AI
DOI：10.1017/S0140525X97300028.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
A fundamental problem with the Clark & Thornton definition of a type-1 problem (requirement 2) is identified. An alternative classical statistical formulation is proposed where a type-1 (learnable) problem corresponds to the case where the learning machine is capable of representing its statistical environment.
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
13.7
Papers:
1.6W
Citations:
1.2W
Organization
No organization information available