Authors:
Gustavo Assunção
1
;
2
;
Miguel Castelo-Branco
3
and
Paulo Menezes
1
;
2
Affiliations:
1
Institute of Systems and Robotics, Coimbra, Portugal
;
2
University of Coimbra, Department of Electrical and Computer Engineering, Coimbra, Portugal
;
3
Coimbra Institute for Biomedical Imaging and Translational Research (CIBIT), Coimbra, Portugal
Keyword(s):
Machine Learning, Overfitting, Data Augmentation, ANN, Artificial Sleep.
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 alg
orithm, following the mentioned hypothesis, for tackling overfitting in ANNs using autonomous data augmentation and interpretation based on a network’s current state of knowledge.
(More)