About this document

AT-ELM: Enhanced Learning with Affine Transform by aayad.educ is a document available to read on EtoBox.

This paper introduces an improved Extreme Learning Machine (ELM) algorithm, referred to as AT-ELM, which incorporates an affine transformation in its activation function to enhance generalization performance. By optimizing the scaling and translation parameters based on the maximum entropy principle, the AT-ELM ensures that hidden layer outputs are approximately uniformly distributed, addressing the limitations of traditional ELMs. Experimental results demonstrate that AT-ELM outperforms the original ELM an

Author

aayad.educ

Language

EN