# Goldilocks Neural Networks

arXiv: https://arxiv.org/abs/2002.05059 · HTML: https://mlsanity.com/paper/2002.05059/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Feb 2020.

## Built on by (most cited first, 1 of 1)

- [Neuronal architecture extracts statistical temporal patterns](https://mlsanity.com/paper/2301.10203/) (2023)

## Abstract (arXiv)

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.