Multiscale Hierarchical Convolutional Networks

03/12/2017
by   Jörn-Henrik Jacobsen, et al.
0

Deep neural network algorithms are difficult to analyze because they lack structure allowing to understand the properties of underlying transforms and invariants. Multiscale hierarchical convolutional networks are structured deep convolutional networks where layers are indexed by progressively higher dimensional attributes, which are learned from training data. Each new layer is computed with multidimensional convolutions along spatial and attribute variables. We introduce an efficient implementation of such networks where the dimensionality is progressively reduced by averaging intermediate layers along attribute indices. Hierarchical networks are tested on CIFAR image data bases where they obtain comparable precisions to state of the art networks, with much fewer parameters. We study some properties of the attributes learned from these databases.

READ FULL TEXT

page 7

page 8

research
01/19/2016

Understanding Deep Convolutional Networks

Deep convolutional networks provide state of the art classifications and...
research
05/21/2019

Geometry of Deep Convolutional Networks

We give a formal procedure for computing preimages of convolutional netw...
research
11/25/2017

CondenseNet: An Efficient DenseNet using Learned Group Convolutions

Deep neural networks are increasingly used on mobile devices, where comp...
research
06/06/2016

Very Deep Convolutional Networks for Text Classification

The dominant approach for many NLP tasks are recurrent neural networks, ...
research
07/07/2020

Hierarchical nucleation in deep neural networks

Deep convolutional networks (DCNs) learn meaningful representations wher...
research
10/19/2018

Understanding Deep Convolutional Networks through Gestalt Theory

The superior performance of deep convolutional networks over high-dimens...
research
08/22/2017

A Spatiotemporal Oriented Energy Network for Dynamic Texture Recognition

This paper presents a novel hierarchical spatiotemporal orientation repr...

Please sign up or login with your details

Forgot password? Click here to reset