About this Research Topic
Inspired by how the human brain works, neurocomputing algorithms, including deep learning, reinforcement learning, and neurodynamic optimization, have achieved tremendous success in various applications across many domains, e.g., visual object tracking, speech recognition, human-level control, text understanding, and real-time optimization.
Various types of intelligent equipment and hardware devices are developed to implement the neurocomputing models for engineering systems. Deep learning has been employed for industrial robotic applications, including stereo reconstruction, object pose recognition, and product quality check. With the advent of Internet of Things and edge computing devices, predictive maintenance of engineering equipment is gaining popularity using deep reinforcement learning. Embedded convolutional neural networks are widely utilized for autonomous vehicle control. The success of applying neurocomputing approaches and related hardware implementations in different engineering domains, such as intelligent manufacturing, energy internet and smart healthcare, has proved the potential of employing neurocomputing for solving real problems in various engineering fields.
Nowadays, advances in sensor and data storage technologies have enabled cumulation of a large amount of data from engineering systems. Driven by big data generated from engineering systems, neurocomputing and its hardware implementation will continually transform engineering systems to more intelligent forms.
This research topic aims to provide a forum for researchers to present the latest research on applications of neurocomputing algorithms and neurocomputing-based hardware in engineering systems. The list of possible topics includes, but is not limited to:
• Wearable Equipment Driven by Neurocomputing Algorithms;
• Intelligent Edge Computing Devices of Implementing Neurocomputing Models;
• Novel Architecture of Neurocomputing Algorithms for Engineering Applications;
• Neurocomputing Simulation Software Environments and Emulation Hardware Architectures;
• Neurocomputers and Neurochips Suitable for Real Engineering Systems;
• New Applications of Neurocomputing under the Engineering Environment.
Keywords: Neural Networks, Deep Learning, Reinforcement Learning, Neurodynamic Optimization, Engineering Systems
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.