.png){kind=icon}
返回
Learning invariance manifolds
.png){kind=icon}
PRE
AI
DOI：10.1016/S0925-2312(99)00011-9.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
A new algorithm for learning invariance manifolds is introduced that allows a neuron to learn a non-linear input-output function to extract invariant or rather slowly varying features from a vectorial input sequence. This is demonstrated by a simple model of learning complex cell responses. The algorithm is generalized to a group of neurons, referred to as a Gibson-clique, to learn slowly varying features that are uncorrelated. Since the input-output functions are non-linear, this technique can be applied iteratively. This is demonstrated by a hierarchical network of Gibson-cliques learning translation invariance. (C) 1999 Published by Elsevier Science B.V. All rights reserved.
Keyword:
feed-forward network
higher-order units
invariances
manifolds
unsupervised learning
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
暂无机构信息
引用论文
WHAT HAS BEEN HAPPENING TO AGGREGATE CONCENTRATION IN THE U.S. ECONOMY IN THE TWENTY‐FIRST CENTURY?
PREAI
分享收藏Identification and Characterisation CRN Effectors in Phytophthora capsici Shows Modularity and Functional Diversity.png)
PLoS ONE
OAAI
PLoS ONEIF0
OAAI分享收藏