Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Greedy Deep Transform Learning

Abstract: 

We introduce deep transform learning – a new
tool for deep learning. Deeper representation is learnt by
stacking one transform after another. The learning proceeds in
a greedy way. The first layer learns the transform and features
from the input training samples. Subsequent layers use the
features (after activation) from the previous layers as training
input. Experiments have been carried out with other deep
representation learning tools – deep dictionary learning,
stacked denoising autoencoder, deep belief network and PCANet
(a version of convolutional neural network). Results show
that our proposed technique is better than all the said
techniques, at least on the benchmark datasets (MNIST,
CIFAR-10 and SVHN) compared on.

up
0 users have voted:

Paper Details

Authors:
Jyoti Maggu, Angshul Majumdar
Submitted On:
18 September 2017 - 1:57pm
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Jyoti
Paper Code:
1136
Document Year:
2017
Cite

Document Files

ICIP_greedyDTL.pdf

(49 downloads)

Subscribe

[1] Jyoti Maggu, Angshul Majumdar, "Greedy Deep Transform Learning", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2180. Accessed: Dec. 18, 2017.
@article{2180-17,
url = {http://sigport.org/2180},
author = {Jyoti Maggu; Angshul Majumdar },
publisher = {IEEE SigPort},
title = {Greedy Deep Transform Learning},
year = {2017} }
TY - EJOUR
T1 - Greedy Deep Transform Learning
AU - Jyoti Maggu; Angshul Majumdar
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2180
ER -
Jyoti Maggu, Angshul Majumdar. (2017). Greedy Deep Transform Learning. IEEE SigPort. http://sigport.org/2180
Jyoti Maggu, Angshul Majumdar, 2017. Greedy Deep Transform Learning. Available at: http://sigport.org/2180.
Jyoti Maggu, Angshul Majumdar. (2017). "Greedy Deep Transform Learning." Web.
1. Jyoti Maggu, Angshul Majumdar. Greedy Deep Transform Learning [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2180