Construction of Multi-Channel Teaching Effect Evaluation System Based on Deep Learning in the Era of Education Informatization

In information-based teaching, the use of multi-channel and all-round evaluation is conducive to mobilizing students’ interest in learning and promoting the realization of teaching objectives. In this paper, a new teaching effect evaluation model combining particle swarm optimization algorithm and RBF neural network is constructed with the help of deep learning method. Aiming at the problem of “early convergence” of particle swarm optimization algorithm, the inertia weight of the algorithm is adjusted and the learning factor is set, which not only optimizes the convergence performance of the algorithm, but also improves the search accuracy of the algorithm. Subsequently, the improved particle swarm algorithm is combined with the radial basis neural network, and the center of the base function of the hidden layer, the width and the connection weights of the output layer of the RBF neural network are particleized, so that the particles can be optimized and the appropriate network parameters can be selected. Applying the improved PSO-RBF neural network control algorithm in multi-channel teaching effect assessment, the accuracy of the algorithm is effectively improved, and the test RMSE value is only 7.0128. In the practice of teaching effect assessment of the course “Art Appreciation for College Students”, the assessment of the network reaches 94% correct rate. Its structure and method have a broad teaching application prospect.