We are very excited to join forces with MLCommons and OctoML.ai! Contact Grigori Fursin for more details!

Goldilocks Neural Networks

lib:c518d43fa96285af (v1.0.0)

Authors: Jan Rosenzweig,Zoran Cvetkovic,Ivana Roenzweig
ArXiv: 2002.05059
Document:  PDF  DOI 
Abstract URL: https://arxiv.org/abs/2002.05059v2

We introduce the new "Goldilocks" class of activation functions, which non-linearly deform the input signal only locally when the input signal is in the appropriate range. The small local deformation of the signal enables better understanding of how and why the signal is transformed through the layers. Numerical results on CIFAR-10 and CIFAR-100 data sets show that Goldilocks networks perform better than, or comparably to SELU and RELU, while introducing tractability of data deformation through the layers.

Relevant initiatives  

Related knowledge about this paper Reproduced results (crowd-benchmarking and competitions) Artifact and reproducibility checklists Common formats for research projects and shared artifacts Reproducibility initiatives


Please log in to add your comments!
If you notice any inapropriate content that should not be here, please report us as soon as possible and we will try to remove it within 48 hours!