Skip to content

McKernel

Latest
Compare
Choose a tag to compare
@curto2 curto2 released this 06 Jun 19:09
· 24 commits to master since this release

McKernel introduces a framework to use kernel approximates in the mini-batch setting with Stochastic Gradient Descent (SGD) as an alternative to Deep Learning. McKernel establishes the foundation of a new architecture of learning that allows to obtain large-scale non-linear classification combining lightning kernel expansions and a linear classifier. It travails in the mini-batch setting working analogously to Neural Networks.