Tensor Data Imputation by PARAFAC with Updated Chaotic Biases by Adam Optimizer

The big data pattern analysis suffers from incorrect responses due to missing entries in the real world. Data collected for digital movie platforms like Netflix and intelligent transportation systems is Spatio-temporal data. Extracting latent explicit features this a challenge. We present high dimensional imputation problem as higher-order tensor decomposition. regularized biased PARAFAC decomposition proposed generate entries. biases are created updated by chaotic exponential factor Adam’s optimization, which reduces error. This perturbed exponentially update learning rate replaces fixed bias Adam optimization. idea has experimented with traffic datasets Guangzhou, China.