Massive Open Online Courses (MOOCs) have become a popular choice fore-learning thanks to their flexibility . Bayesian deeplearning offers a critical uncertainty measure that is not supplied by traditional neural networks . This adds more explainability, trust andrust to AI, which is crucial in education-based applications . It can achieve similar or better performance compared tonon-probabilistic neural networks, as well as grant lower variance, according to the authors of the paper . The results suggest that Bayesian . deeplearning offer a critical . uncertainty measure not supplied . bytraditional neural networks – this adds more . explainability and trust and .robustness to AI-based . applications, which are crucial in . education- based applications, says the authors . The authors. The authors say. The results are based on their proposed methods with probabilistic models with probablistic models to its . baseline non-Bayesian models under similar circumstances, for similar circumstances of applying prediction, for different cases of . applying prediction .

Author(s) : Jialin Yu, Laila Alrajhi, Anoushka Harit, Zhongtian Sun, Alexandra I. Cristea, Lei Shi

Links : PDF - Abstract

Code :

https://github.com/oktantod/RoboND-DeepLearning-Project


Coursera

Keywords : based - authors - bayesian - models - similar -

Leave a Reply

Your email address will not be published. Required fields are marked *