Tensor Networks

Read:
Tensor Networks for Big Data Analytics and Large-Scale Optimization Problems

Good way to represent tensor contraction in higher dimensional tensors
Roger Penrose’s phd thesis was on tensors

Introduction to tensors (with cool graphcs):
https://www.tensors.net/

Many related resource links available at:
https://tensornetwork.org/

tensor train technique

One can reduce an N-order tensor (containing exponentially many trainable parameters) to a chain of N tensors of order 2 or 3, which gives us a polynomial number of parametersone can reduce an N-order tensor (containing exponentially many trainable parameters) to a chain of N tensors of order 2 or 3, which gives us a polynomial number of parameters

Also see penrose_notation