Randomization-Based Deep & Shallow Neural Networks

87 views
Download
  • Share
Create Account or Sign In to post comments
#IEEE #CIS #distinguished lecture #

This talk will first introduce the main randomization-based feedforward neural
networks with closed-form solutions. The popular instantiation of the
feedforward type called random vector functional link neural network (RVFL)
originated in the early 1990s.

RVFL variants will be empirically evaluated. Subsequently, deep versions of RVFL will be presented as a single and ensemble classifiers. The talk will also present extensive benchmarking studies using classification and forecasting datasets. If time permits, oblique random forest and kernel ridge regression will also be briefly discussed.

 

Acknowledgment: Sponsored by the Computational Intelligence Society under its
Distinguished Lecturer Program. Prof. Suganthan is a CIS Distinguished
Lecturer.

This talk will first introduce the main randomization-based feedforward neural
networks with closed-form solutions. The popular instantiation of the
feedforward type called random vector functional link neural network (RVFL)
originated in the early 1990s.

RVFL variants will be empirically evaluated. Subsequently, deep versions of RVFL will be presented as a single and ensemble classifiers.

Advertisment

Advertisment