ANNs Dream of Augmented Sheep: An Artificial Dreaming Algorithm

Gustavo Assunção, Gustavo Assunção, Miguel Castelo-Branco, Paulo Menezes, Paulo Menezes

2022

Abstract

Sleep is a fundamental daily process of several species, during which the brain cycles through critical stages for both resting and learning. A phenomenon known as dreaming may occur during that cycle, whose purpose and functioning have yet to be agreed upon by the research community. Despite the controversy, some have hypothesized dreaming to be an overfitting prevention mechanism, which enables the brain to corrupt its small amount of statistically similar observations and experiences. This leads to better cognition through non-rigid consolidation of knowledge and memory without requiring external generalization. Although this may occur in numerous ways depending on the basis theory, some appear more adequate for homologous methodology in machine learning. Overfitting is a recurrent problem of artificial neural network (ANN) training, caused by data homogeneity/reduced size and which is often resolved by manual alteration of data. In this paper we propose an artificial dreaming algorithm, following the mentioned hypothesis, for tackling overfitting in ANNs using autonomous data augmentation and interpretation based on a network’s current state of knowledge.

Download


Paper Citation


in Harvard Style

Assunção G., Castelo-Branco M. and Menezes P. (2022). ANNs Dream of Augmented Sheep: An Artificial Dreaming Algorithm. In Proceedings of the 2nd International Conference on Image Processing and Vision Engineering - Volume 1: IMPROVE, ISBN 978-989-758-563-0, pages 135-141. DOI: 10.5220/0011055700003209


in Bibtex Style

@conference{improve22,
author={Gustavo Assunção and Miguel Castelo-Branco and Paulo Menezes},
title={ANNs Dream of Augmented Sheep: An Artificial Dreaming Algorithm},
booktitle={Proceedings of the 2nd International Conference on Image Processing and Vision Engineering - Volume 1: IMPROVE,},
year={2022},
pages={135-141},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011055700003209},
isbn={978-989-758-563-0},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Image Processing and Vision Engineering - Volume 1: IMPROVE,
TI - ANNs Dream of Augmented Sheep: An Artificial Dreaming Algorithm
SN - 978-989-758-563-0
AU - Assunção G.
AU - Castelo-Branco M.
AU - Menezes P.
PY - 2022
SP - 135
EP - 141
DO - 10.5220/0011055700003209