172 search results - page 8 / 35 » Learning predictive representations from a history |
JMLR
2012
12 years 6 days ago
2012
Unsupervised discovery of latent representations, in addition to being useful for density modeling, visualisation and exploratory data analysis, is also increasingly important for...
AAAI
1996
13 years 11 months ago
1996
As more information becomes available electronically, tools for finding information of interest to users becomes increasingly important. The goal of the research described here is...
AROBOTS
1999
13 years 9 months ago
1999
We present a framework for constructing representations of space in an autonomous agent which does not obtain any direct information about its location. Instead the algorithm relie...
FLAIRS
2008
14 years 3 days ago
2008
We investigate the use of self-predicting neural networks for autonomous robot learning within noisy or partially predictable environments. A benchmark experiment is performed in ...
IEEEICCI
2009
IEEE
13 years 7 months ago
2009
IEEE
Abstract-In this paper, we construct a neural-inspired computational model based on the representational capabilities of receptive fields. The proposed model, known as Shape Encodi...