Quanta Magazine

By using hypernetworks, researchers can now preemptively fine-tune artificial neural networks, saving some of the time and expense of training.

Related Keywords

Guelph ,Ontario ,Canada ,Toronto ,London ,City Of ,United Kingdom ,Amsterdam ,Noord Holland ,Netherlands ,Boris Knyazev ,Mengye Ren ,Raquel Urtasun ,Chris Zhang ,Thomas Kipf ,Petar Veli ,University Of Toronto ,Google Research Brain Team ,University Of Guelph ,Google Research ,Brain Team ,