Dramatic achievement in machine learning has resulted in a torrent of Artificial Intelligence (AI) applications. Continued improvements offer to create autonomous methods which will comprehend, understand, choose, and behave on their own. However, the potency of these methods is restricted by the machine's recent failure to explain their choices and activities to human users, and hence industries are experiencing problems that demand more intelligent, autonomous, and symbiotic systems. Explainable AI (XAI)—especially explainable machine learning—is going to be necessary if future methods are to understand, correctly trust, and efficiently control an emerging technology of artificially intelligent machine partners.

The complex nature of different XAI models and the tuning of multiple hyper-parameters to understand the underlying data makes it interesting to study. XAI models have been studied from different perspectives and different complex XAI models have been developed. Still, a lot of advancements need to be made to further investigate the structural and functional properties of complex XAI models in different domains.

This Special Issue aims to provide a platform for researchers to share cutting-edge solutions in the field. The objective is to evaluate various metaheuristic techniques which can be used to optimize the hyper-parameters of XAI models. Moreover, how we can use metaheuristics-based XAI models to solve many complex real-world problems. Both original research review articles are welcomed with a focus on development activities in complex XAI for multimodal data in this rapidly growing interdisciplinary field.

Potential topics include but are not limited to the following:

• Metaheuristics based complex explainable AI models
• Metaheuristics based deep XAI models
• Metaheuristics based XAI models for hardware design
• Metaheuristics based deep reinforcement XAI models
• Metaheuristics based XAI complex intelligent models
• Metaheuristics based XAI deep generative adversarial models
• Metaheuristics based explainable machine learning models
• Metaheuristics based XAI deep recurrent neural networks