DeepAI AI Chat
Log In Sign Up

Deep tensor networks with matrix product operators

by   Bojan Žunkovič, et al.
University of Ljubljana

We introduce deep tensor networks, which are exponentially wide neural networks based on the tensor network representation of the weight matrices. We evaluate the proposed method on the image classification (MNIST, FashionMNIST) and sequence prediction (cellular automata) tasks. In the image classification case, deep tensor networks improve our matrix product state baselines and achieve 0.49 sequence prediction case, we demonstrate an exponential improvement in the number of parameters compared to the one-layer tensor network methods. In both cases, we discuss the non-uniform and the uniform tensor network models and show that the latter generalizes well to different input sizes.


page 1

page 2

page 3

page 4


TensorNetwork for Machine Learning

We demonstrate the use of tensor networks for image classification with ...

On the descriptive power of Neural-Networks as constrained Tensor Networks with exponentially large bond dimension

In many cases, neural networks can be mapped into tensor networks with a...

Tensor-based algorithms for image classification

The interest in machine learning with tensor networks has been growing r...

Tensor Networks for Medical Image Classification

With the increasing adoption of machine learning tools like neural netwo...

Multi-layered tensor networks for image classification

The recently introduced locally orderless tensor network (LoTeNet) for s...

Stable Tensor Neural Networks for Rapid Deep Learning

We propose a tensor neural network (t-NN) framework that offers an excit...

Interaction Decompositions for Tensor Network Regression

It is well known that tensor network regression models operate on an exp...