Sparsity through evolutionary pruning prevents neuronal networks from overfitting

DOI10.1016/J.NEUNET.2020.05.007OpenAlexW3021119228WikidataQ95850337 ScholiaQ95850337MaRDI QIDQ1982444

Richard C. Gerum, André Erpenbeck, Patrick Krauss, Achim Schilling

Publication date: 8 September 2021

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1911.10988

zbMATH Keywords

evolutionartificial neural networksevolutionary algorithmoverfittingbiological plausibilitymaze task

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Problems related to evolution (92D15) Neural networks for/in biological studies, artificial life and related topics (92B20)

Related Items (1)

The digital asset value and currency supervision under deep learning and blockchain technology

Uses Software

• NumPy
• Matplotlib
• pylustrator

Cites Work

• An experimental unification of reservoir computing methods
• A neural algorithm for a fundamental computing problem
• Real-Time Computation at the Edge of Chaos in Recurrent Neural Networks
• The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions
• Collective dynamics of ‘small-world’ networks
• Unnamed Item

This page was built for publication: Sparsity through evolutionary pruning prevents neuronal networks from overfitting