Impacts of Darwinian Evolution on Pre-trained Deep Neural Networks
This work addresses the optimization of deep neural networks for visual recognition tasks, offering a novel approach that could benefit researchers in machine learning, though it appears incremental as it builds on existing evolutionary methods.
The paper tackles the problem of optimizing deep neural networks by proposing a framework based on Darwinian evolution, which reduces over-fitting and achieves an order of magnitude lower time complexity compared to back-propagation.
Darwinian evolution of the biological brain is documented through multiple lines of evidence, although the modes of evolutionary changes remain unclear. Drawing inspiration from the evolved neural systems (e.g., visual cortex), deep learning models have demonstrated superior performance in visual tasks, among others. While the success of training deep neural networks has been relying on back-propagation (BP) and its variants to learn representations from data, BP does not incorporate the evolutionary processes that govern biological neural systems. This work proposes a neural network optimization framework based on evolutionary theory. Specifically, BP-trained deep neural networks for visual recognition tasks obtained from the ending epochs are considered the primordial ancestors (initial population). Subsequently, the population evolved with differential evolution. Extensive experiments are carried out to examine the relationships between Darwinian evolution and neural network optimization, including the correspondence between datasets, environment, models, and living species. The empirical results show that the proposed framework has positive impacts on the network, with reduced over-fitting and an order of magnitude lower time complexity compared to BP. Moreover, the experiments show that the proposed framework performs well on deep neural networks and big datasets.