Learnability of Interestingness with Semantic Similarity and Reasoning in the Knowledge Base of Decision Support Systems

Abstract

The evolution of deep learning blended with GPU/TPU has elicited faster computation and assimilation of Big Data at a rapid pace with the exponential learning rate of models. Mobile technologies and cloud-based services are yielding massive data irrespective of geographic location at a rapid pace. Integrating the available plethora of data to find a semantic similarity while providing a rapid response without compromising on the quantity and quality of data is a prime concern. Learning from semantic similarity, utility algorithms turn this data into machine perceivable information, through learnability and utilization of Senticnet. The retainability of knowledge still has its own set of specific needs in terms of different machine learning and artificial intelligence algorithms. Utilization of the semantic similarity for ontology-based learning with interoperability helps preserve privacy for decoding the control attributes. The aspect of learning may further extend for rapidly generated sensor data through things and mobile devices.