Random Vector Functional Link Networks for Function Approximation on Manifolds

arXiv:2007.15776v3 Announce Type: replace-cross
Abstract: The learning speed of feed-forward neural networks is notoriously slow and has presented a bottleneck in deep learning applications for several decades. For instance, gradient-based learning algorithms, which are used extensively to train neural networks, tend to work slowly when all of the network parameters must be iteratively tuned. To counter this, both researchers and practitioners have tried introducing randomness to reduce the learning requirement. Based on the original construction of Igelnik and Pao, single …

abstract algorithms applications approximation arxiv cs.it cs.lg deep learning function functional gradient instance math.it math.pr network networks neural networks parameters random speed stat.ml train type vector work