.png){kind=icon}
Return
On ψ-learning
.png){kind=icon}
PRE
AI
DOI：10.1198/016214503000000639.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The concept of large margins have been recognized as an important principle in analyzing learning methodologies, including boosting, neural networks, and support vector machines (SVMs). However, this concept alone is not adequate for learning in nonseparable cases. We propose a learning methodology, called psi-learning, that is derived from a direct consideration of generalization errors. We provide a theory for psi-learning and show that it essentially attains the optimal rates of convergence in two learning examples. Finally, results from simulation studies and from breast cancer classification confirm the ability of psi-learning to outperform SVM in generalization.
Keywords:
classification
generalization error
margins
machine learning
metric entropy
support vector machine
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
J
IF:
3
Papers:
5.2K
Citations:
4.8W
Organization
No organization information available
Cited Papers
No cited papers available