DMCA
Unsupervised learning of invariant feature hierarchies with application to object recognition.” CVPR, 2007. 1 Data Driven HMC Algorithm. DDHMC (motion-based proposals) 1: Initialize chain with τo 2: for i = 1 to nsamples do 3: // 1. Data-Driven: Get Propo
Cached
Download Links
| Venue: | Initialize the Acceptance, H(qo, po), and the Proposal, H ′ (qo, po ) Hamiltonians , τq) 14: po = DMotion(τ ′ i , τq) 15: qo = DF orm(τ ′ i , τq) 16: draw po ∼ N (0, 1) 17: // 2. Perturbation on H ′ using Leapfrog 18: for j=1 to l do 13: qo = DF orm(τ ′ i |
| Citations: | 194 - 17 self |
BibTeX
@INPROCEEDINGS{Huang_unsupervisedlearning,
author = {Fu-jie Huang and Y-lan Boureau and Yann Lecun},
title = {Unsupervised learning of invariant feature hierarchies with application to object recognition.” CVPR, 2007. 1 Data Driven HMC Algorithm. DDHMC (motion-based proposals) 1: Initialize chain with τo 2: for i = 1 to nsamples do 3: // 1. Data-Driven: Get Propo},
booktitle = {Initialize the Acceptance, H(qo, po), and the Proposal, H ′ (qo, po ) Hamiltonians , τq) 14: po = DMotion(τ ′ i , τq) 15: qo = DF orm(τ ′ i , τq) 16: draw po ∼ N (0, 1) 17: // 2. Perturbation on H ′ using Leapfrog 18: for j=1 to l do 13: qo = DF orm(τ ′ i},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We present an unsupervised method for learning a hierarchy of sparse feature detectors that are invariant to small shifts and distortions. The resulting feature extractor consists of multiple convolution filters, followed by a pointwise sigmoid non-linearity, and a feature-pooling layer that computes the max of each filter output within adjacent windows. A second level of larger and more invariant features is obtained by training the same algorithm on patches of features from the first level. Training a supervised classifier on these features yields 0.64 % error on MNIST, and 54 % average recognition rate on Caltech 101
Keyphrases
data driven hmc algorithm invariant feature hierarchy initialize chain motion-based proposal get propo feature yield second level sparse feature detector resulting feature extractor adjacent window invariant feature pointwise sigmoid non-linearity first level small shift feature-pooling layer filter output multiple convolution filter average recognition rate unsupervised method
