Advances in Neural Networks and Hybrid-Metaheuristics: Theory, Algorithms, and Novel Engineering Applications
1Instituto Politécnico Nacional, Ciudad de México, Mexico
2Oklahoma State University-Stillwater, Stillwater, USA
3Universidad de Málaga, Málaga, Spain
4Cinvestav, Ciudad de México, Mexico
5Universidad Nacional de San Luis, San Luis, Argentina
Advances in Neural Networks and Hybrid-Metaheuristics: Theory, Algorithms, and Novel Engineering Applications
Description
Neural networks are a family of statistical learning models inspired by biological neural networks which are mainly used to estimate functions; they also have been used to solve a wide variety of tasks that are hard to solve using ordinary rule-based programming, including computer vision and speech recognition. On the other hand, a metaheuristic is a higher-level procedure designed to find, generate, or select a heuristic (partial search algorithm) that may provide a sufficiently good solution to an optimization problem.
Recently, the neural networks area has once again become a hot topic, particularly using new architectures (spiking networks, deep networks), hybrid-schemes (with fuzzy logic and bioinspired algorithms), and stability analysis of mixed architectures (with fuzzy or sliding modes). Hybrid-metaheuristics aim to cover novel modifications on well-established metaheuristics algorithms looking to undertake the problem at hand.
Particularly, there are few published results on applications in engineering, bioengineering, and neurolinguistics using these two key subjects in computational intelligence.
This special issue focuses on research communities with high experience in evolutionary systems, neural networks, fuzzy logic, natural language processing, and multidisciplinary research teams with the aim to obtain novel solutions for real world applications.
Potential topics include, but are not limited to:
- Neural networks and neurocontrol
- Hybrid neural networks
- Analysis of neural networks dynamics
- Hybrid-metaheuristics
- Metaheuristics for multiobjective optimization and natural language processing
- Deep learning in computational linguistics
- Parallel metaheuristics
- Dynamic problems and dynamic metaheuristics