Cognitive Computing

Abstract

Huge popularity of cognitive computing in both academic and industry is as a result of rapid development of computer software, hardware technologies and artificial intelligence. Logical methods are used by cognitive computing in psychology, biology, signal processing, information theory, mathematics and statistics to build machines which have reasonable ability similar to human brain. An effective cognitive computing architecture can be constructed using 5G network, robotics, deep learning, cloud and IOT infrastructures. Voice recognition, computer vision, cognitive healthcare, smart city, and smart transportation are some of the application areas. Cognitive computing framework connects with big data analytics as it requires huge amount of data to assimilate critical thinking capability of human being. Reinforcement learning is one of the machine learning techniques that can be used in cognitive computing architecture. Deep learning algorithms, open source frameworks and computer vision are also used to build an effective cognitive computing architecture. The architecture will define resource, workload and computation process rules which regulate application performance, It also helps in information hiding, autonomic scaling, optimize reliability and mobility of data which promotes DL/ML systems.