Promoting Infrastructure Development through Experimental Learning in Law School Curriculum using Deep Learning Techniques to Improve Academic Performance

Abstract

Academic performance improvements in law schools rely on theoretical and practical knowledge implications and assessments. The curriculum-based knowledge transfer and performance assessment are scrutinized to meet the societal factors in improving the student's knowledge. This article introduces an Experimental Learning Assessment Approach (ELAA) using deep learning for student academic performance improvements. The student's skills and assessments are performed using mock training and law sessions periodically with different stages. The assessments are carried forward using different sessions and integrated curriculum verification is performed. Based on this theoretical and mock practice assessment, the deep learning recommendation is used for performance amendments. The learning induces multiple assessment constraints considering the different stages and their difficulty levels. In this assessment, the individuals' output and the curriculum impact are used for framing different constraints toward performance validation. In this learning process, recurrent assessments for different stages and (new) constraints are exploited to improve the recommendations. Based on the recommendations, the curriculum implication, modification, or assessment frequency is persuaded.