A Perceptual Machine Model Based Approach to Recommending Online Learning Resources

Abstract

Abstract The bias values of various learning resources are computed using neuron excitation functions based on the perceptual machine model in this paper. Each learning sample is calculated using the weight vector value of each layer in the learning resources. The difference between the output result of the network and the expected value is calculated and converted into the minimum value of the loss function for solving the normalized processing of the weight matrix of the learning resources. It is found that the average square root error in the online learning resources is 0.0897, the decreasing rate is 35.28% compared with the empirical mixing method, and the bias of the online resource recommendation model is 0.2453, which indicates that the proposed model can learn the mixing weight matrix more quickly and obtain a better mixing analysis field for more accurate and personalized learning resource recommendation.