Sciweavers

680 search results - page 91 / 136
» Intrinsically Motivated Machines
Sort
View
ENTCS
2007
153views more  ENTCS 2007»
13 years 8 months ago
The Methods of Approximation and Lifting in Real Computation
The basic motivation behind this work is to tie together various computational complexity classes, whether over different domains such as the naturals or the reals, or whether de...
Manuel Lameiras Campagnolo, Kerry Ojakian
ALT
2011
Springer
12 years 8 months ago
On the Expressive Power of Deep Architectures
Deep architectures are families of functions corresponding to deep circuits. Deep Learning algorithms are based on parametrizing such circuits and tuning their parameters so as to ...
Yoshua Bengio, Olivier Delalleau
CVPR
2009
IEEE
1528views Computer Vision» more  CVPR 2009»
15 years 10 days ago
Structured Output-Associative Regression
Structured outputs such as multidimensional vectors or graphs are frequently encountered in real world pattern recognition applications such as computer vision, natural language pr...
Liefeng Bo and Cristian Sminchisescu
KDD
2007
ACM
139views Data Mining» more  KDD 2007»
14 years 8 months ago
Raising the baseline for high-precision text classifiers
Many important application areas of text classifiers demand high precision and it is common to compare prospective solutions to the performance of Naive Bayes. This baseline is us...
Aleksander Kolcz, Wen-tau Yih
POPL
2007
ACM
14 years 8 months ago
Logic-flow analysis of higher-order programs
This work presents a framework for fusing flow analysis and theorem proving called logic-flow analysis (LFA). The framework itthe reduced product of two abstract interpretations: ...
Matthew Might