Special issue on deep learning and neural computing for intelligent sensing and control

Excerpt

Intelligent sensing, especially together with autonomous decision making and control, recently has gained wide attention, with successful showcases in different areas such as the autonomous flying droids, self-driving cars, and Amazon–Kiva systems. One primary ultimate goal is that via active sensing, the computer/machine can learn through either supervised or unsupervised information to perform different tasks. This fact renders learning a fundamental component for both sensing and control. Among many learning approaches, deep learning has obtained a series of success across various domains including image, speech, text as well as various user interaction data. The resulting increased sensing capability opens up new possibility for more intelligent decision making and control. On the other hand, emerging technology, e.g., deep reinforcement learning and big data, also spurs the research for new control paradigm. The continuously increasing interest in the intersection between intelligent sensing, big data, and deep learning motivates us to organize this special section to study the learning of feature representations for decision-making and control problems. …