Evolutionary Neural Architecture Search and Its Applications in Healthcare
Authors:
Open Access
- 1 January 2024
- journal article
- review article
- Published by Tech Science Press in Computer Modeling in Engineering & Sciences
- Vol. 139 (1) , 143-185
Abstract
Most of the neural network architectures are based on human experience, which requires a long and tedious trial-and-error process. Neural architecture search (NAS) attempts to detect effective architectures without human intervention. Evolutionary algorithms (EAs) for NAS can find better solutions than human-designed architectures by exploring a large search space for possible architectures. Using multiobjective EAs for NAS, optimal neural architectures that meet various performance criteria can be explored and discovered efficiently. Furthermore, hardware-accelerated NAS methods can improve the efficiency of the NAS. While existing reviews have mainly focused on different strategies to complete NAS, a few studies have explored the use of EAs for NAS. In this paper, we summarize and explore the use of EAs for NAS, as well as large-scale multiobjective optimization strategies and hardware-accelerated NAS methods. NAS performs well in healthcare applications, such as medical image analysis, classification of disease diagnosis, and health monitoring. EAs for NAS can automate the search process and optimize multiple objectives simultaneously in a given healthcare task. Deep neural network has been successfully used in healthcare, but it lacks interpretability. Medical data is highly sensitive, and privacy leaks are frequently reported in the healthcare industry. To solve these problems, in healthcare, we propose an interpretable neuroevolution framework based on federated learning to address search efficiency and privacy protection. Moreover, we also point out future research directions for evolutionary NAS. Overall, for researchers who want to use EAs to optimize NNs in healthcare, we analyze the advantages and disadvantages of doing so to provide detailed guidance, and propose an interpretable privacy-preserving framework for healthcare applications.Keywords
This publication has 185 references indexed in Scilit:
- CIDE: Chaotically Initialized Differential EvolutionExpert Systems with Applications, 2010
- A Hypercube-Based Encoding for Evolving Large-Scale Neural NetworksArtificial Life, 2009
- Large scale evolutionary optimization using cooperative coevolutionInformation Sciences, 2008
- SMS-EMOA: Multiobjective selection based on dominated hypervolumeEuropean Journal of Operational Research, 2007
- A fast and elitist multiobjective genetic algorithm: NSGA-IIIEEE Transactions on Evolutionary Computation, 2002
- Evolving Neural Networks through Augmenting TopologiesEvolutionary Computation, 2002
- Fuzzy-rough and rough-fuzzy serial combinations in neurocomputingNeurocomputing, 2001
- A new evolutionary system for evolving artificial neural networksIEEE Transactions on Neural Networks, 1997
- An evolutionary algorithm that constructs recurrent neural networksIEEE Transactions on Neural Networks, 1994
- Learning representations by back-propagating errorsNature, 1986