公开(公告)号：EP3772709A1

公开(公告)日：2021-02-10

申请号：EP19190237.8

申请日：2019-08-06

申请人： Robert Bosch GmbH ,  Carnegie Mellon University

发明人： Bai, Shaojie ,  Kolter, Jeremy Zieg ,  Schober, Michael

IPC分类号： G06N3/08 ,  G06N3/04

摘要： A neural network may comprise an iterative function ( z [ i +1] = f ( z [ i ] , θ , c ( x )). Such an iterative function is known in the field of machine learning to be representable by a stack of layers which have mutually shared weights. As described in this specification, this stack of layers may during training be replaced by the use of a numerical root-finding algorithm to find an equilibrium of the iterative function in which a further execution of the iterative function would not substantially further change the output of the iterative function. Effectively, the stack of layers may be replaced by a numerical equilibrium solver 480. The use of the numerical root-finding algorithm is demonstrated to greatly reduce the memory footprint during training while achieving similar accuracy as state-of-the-art prior art models.