← Search

Mate Lengyel

2 accepted papers

2018

Exact natural gradient in deep linear networks and its application to the nonlinear case

NeurIPS 2018poster

Stochastic gradient descent (SGD) remains the method of choice for deep learning, despite the limitations arising for ill-behaved objective functions. In cases where it could be estimated, the natural gradient has proven very effective at mitigating the catastrophic effects of pathological curvature…

Cited by 65SourcePDFScholar
2016

Efficient state-space modularization for planning: theory, behavioral and neural signatures

NeurIPS 2016poster

Even in state-spaces of modest size, planning is plagued by the “curse of dimensionality”. This problem is particularly acute in human and animal cognition given the limited capacity of working memory, and the time pressures under which planning often occurs in the natural environment. Hierarchicall…

Cited by 28SourcePDFScholar