Directed evolution algorithm drives neural prediction

TL;DR

This paper introduces the directed evolution model (DEM), a novel computational approach inspired by biological evolution, to improve neural prediction accuracy and generalization in personalized neurocognitive applications, especially under label scarcity.

Contribution

The paper presents DEM, a new evolutionary-inspired algorithm that enhances neural prediction models' generalization and robustness in personalized neurocognitive tasks, addressing domain shift and label scarcity issues.

Findings

DEM improves cross-domain neural prediction accuracy.

DEM enhances generalization in reinforcement learning.

DEM effectively handles label scarcity in target domains.

Abstract

Neural prediction offers a promising approach to forecasting the individual variability of neurocognitive functions and disorders and providing prognostic indicators for personalized invention. However, it is challenging to translate neural predictive models into medical artificial intelligent applications due to the limitations of domain shift and label scarcity. Here, we propose the directed evolution model (DEM), a novel computational model that mimics the trial-and-error processes of biological directed evolution to approximate optimal solutions for predictive modeling tasks. We demonstrated that the directed evolution algorithm is an effective strategy for uncertainty exploration, enhancing generalization in reinforcement learning. Furthermore, by incorporating replay buffer and continual backpropagate methods into DEM, we provide evidence of achieving better trade-off between exploitation and exploration in continuous learning settings. We conducted experiments on four different datasets for children with cochlear implants whose spoken language developmental outcomes vary considerably on the individual-child level. Preoperative neural MRI data has shown to accurately predict the post-operative outcome of these children within but not across datasets. Our results show that DEM can efficiently improve the performance of cross-domain pre-implantation neural predictions while addressing the challenge of label scarcity in target domain.