<ul><li>This paper introduces Factor Augmented Tensor-on-Tensor Neural Networks (FATTNN) for tensor-on-tensor regression.</li><li>FATTNN integrates tensor factor models into deep neural networks to handle nonlinearity between complex data structures.</li><li>The proposed methods offer improved prediction accuracy and computational efficiency compared to traditional statistical models and conventional deep learning approaches.</li><li>Empirical results from simulation studies and real-world applications show the superiority of FATTNN over benchmark methods.</li></ul>

Factor Augmented Tensor-on-Tensor Neural Networks

Discover more