Tucker Decomposition Network: Expressive Power and Comparison

05/23/2019
by   Ye Liu, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/16/2017

Entanglement Entropy of Target Functions for Image Classification and Convolutional Neural Network

The success of deep convolutional neural network (CNN) in computer visio...
research
09/16/2015

On the Expressive Power of Deep Learning: A Tensor Analysis

It has long been conjectured that hypotheses spaces suitable for data th...
research
05/29/2020

Deep convolutional tensor network

Tensor networks are linear algebraic representations of quantum many-bod...
research
06/20/2018

Como funciona o Deep Learning

Deep Learning methods are currently the state-of-the-art in many problem...
research
07/17/2018

Expressive power of outer product manifolds on feed-forward neural networks

Hierarchical neural networks are exponentially more efficient than their...
research
12/18/2019

Tangent Space Separability in Feedforward Neural Networks

Hierarchical neural networks are exponentially more efficient than their...
research
10/31/2016

Tensor Switching Networks

We present a novel neural network algorithm, the Tensor Switching (TS) n...

Please sign up or login with your details

Forgot password? Click here to reset