tensor-networks

This paper introduces a tensor network model to capture the influence of emotional valence on the order-dependent structure of children's recognition memory, achieving 77.98% accuracy and demonstrating the value of quantum-inspired methods for modelling cognitive phenomena.

Introduces Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) for compressing deep neural network layers via small core tensors, achieving high compression ratios while maintaining accuracy.