The rapid increase of information and accessibility in recent years has activated a paradigm shift in algorithm design for artificial intelligence. Recently, deep learning (a surrogate of Machine Learning) have won several contests in pattern recognition and machine learning. This review comprehensively summarises relevant studies, much of it from prior state-of-the-art techniques. This paper also discusses the motivations and principles regarding learning algorithms for deep architectures.
Ghanaian universities have employed various marketing mix to stimulate demand for their services; particularly in recruitment and engagement of home and international students. This paper examines the relative influence of factors affecting the college choice decisions of students. It is based on a survey of 2,534 admitted students at a major university in Ghana, to which 39 percent of the sample responded. We used Factor analysis to rate 26 University borne attributes upon which student decisions are based. The outcome was used to build a five-scale preference measure, which were evaluated with a qualitative approach in analyzing gathered data using descriptive statistics, cross tabulation and chi square. The results revealed some marketing strategies that can be used in institutions of higher learning to boost students’ enrolment in their order of perceived effectiveness. The following were found to influence decisions: word of mouth (family and friends), proximity/nearness, accreditation/affiliation, affordability and lecturing Style.
Particle swarm optimization (PSO) is a heuristic global optimization method. PSO was motivated by the social behavior of organisms, such as bird flocking, fish schooling and human social relations. Its properties of low constraint on the continuity of objective function and the ability to adapt various dynamic environments, makes PSO one of the most important swarm intelligence algorithms and ostensibly the most commonly used optimization technique. This survey presents a comprehensive investigation of PSO and in particular, a proposed theoretical framework to improve its implementation. We hope that this survey would be beneficial to researchers studying PSO algorithms and would also serve as the substratum for future research in the study area, particularly those pursuing their career in artificial intelligence. In the end, some important conclusions and possible research directions of PSO that need to be studied in the future are proposed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.