# Tucker Decomposition Network: Expressive Power and Comparison

Source: [Tucker Decomposition Network: Expressive Power and Comparison](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c418>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:34:37.515Z

Authors: Ye Liu, Junjun Pan, Michael Ng

Published: 2019-05-23T13:12:15.000Z

## Abstract

Deep neural networks have achieved a great success in solving many machine learning and computer vision problems. The main contribution of this paper is to develop a deep network based on Tucker tensor decomposition, and analyze its expressive power. It is shown that the expressiveness of Tucker network is more powerful than that of shallow network. In general, it is required to use an exponential number of nodes in a shallow network in order to represent a Tucker network. Experimental results are also given to compare the performance of the proposed Tucker network with hierarchical tensor network and shallow network, and demonstrate the usefulness of Tucker network in image classification problems.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1905.09635>)

[PDF](<https://arxiv.org/pdf/1905.09635.pdf>)