BioGD: Bio-inspired robust gradient descent.
PLoS One
; 14(7): e0219004, 2019.
Article
em En
| MEDLINE
| ID: mdl-31276469
ABSTRACT
Recent research in machine learning pointed to the core problem of state-of-the-art models which impedes their widespread adoption in different domains. The models' inability to differentiate between noise and subtle, yet significant variation in data leads to their vulnerability to adversarial perturbations that cause wrong predictions with high confidence. The study is aimed at identifying whether the algorithms inspired by biological evolution may achieve better results in cases where brittle robustness properties are highly sensitive to the slight noise. To answer this question, we introduce the new robust gradient descent inspired by the stability and adaptability of biological systems to unknown and changing environments. The proposed optimization technique involves an open-ended adaptation process with regard to two hyperparameters inherited from the generalized Verhulst population growth equation. The hyperparameters increase robustness to adversarial noise by penalizing the degree to which hardly visible changes in gradients impact prediction. The empirical evidence on synthetic and experimental datasets confirmed the viability of the bio-inspired gradient descent and suggested promising directions for future research. The code used for computational experiments is provided in a repository at https//github.com/yukinoi/bio_gradient_descent.
Texto completo:
1
Bases de dados:
MEDLINE
Assunto principal:
Aprendizado de Máquina
Tipo de estudo:
Prognostic_studies
Idioma:
En
Revista:
PLoS One
Assunto da revista:
CIENCIA
/
MEDICINA
Ano de publicação:
2019
Tipo de documento:
Article
País de afiliação:
Federação Russa