no code implementations • 18 May 2021 • Lorenz K. Muller
In this paper we propose to use HyperNetworks to break the fixed ratio of FLOPs to parameters of standard convolutions.
no code implementations • 22 Apr 2015 • Lorenz K. Muller, Giacomo Indiveri
We further use these methods to investigate the performance of three common neural network algorithms under fixed memory size of the weight matrix with different weight resolutions.