Sciweavers

879 search results - page 2 / 176
» Kolmogorov Complexity and Model Selection
Sort
View
MCU
2007
95views Hardware» more  MCU 2007»
13 years 8 months ago
Slightly Beyond Turing's Computability for Studying Genetic Programming
Inspired by genetic programming (GP), we study iterative algorithms for non-computable tasks and compare them to naive models. This framework justifies many practical standard tri...
Olivier Teytaud
ICANN
2009
Springer
14 years 1 months ago
Modelling Image Complexity by Independent Component Analysis, with Application to Content-Based Image Retrieval
Abstract. Estimating the degree of similarity between images is a challenging task as the similarity always depends on the context. Because of this context dependency, it seems qui...
Jukka Perkiö, Aapo Hyvärinen
STACS
2005
Springer
14 years 9 days ago
Kolmogorov-Loveland Randomness and Stochasticity
An infinite binary sequence X is Kolmogorov-Loveland (or KL) random if there is no computable non-monotonic betting strategy that succeeds on X in the sense of having an unbounde...
Wolfgang Merkle, Joseph S. Miller, André Ni...
NIPS
2003
13 years 8 months ago
From Algorithmic to Subjective Randomness
We explore the phenomena of subjective randomness as a case study in understanding how people discover structure embedded in noise. We present a rational account of randomness per...
Thomas L. Griffiths, Joshua B. Tenenbaum
DCC
2006
IEEE
14 years 6 months ago
Compression and Machine Learning: A New Perspective on Feature Space Vectors
The use of compression algorithms in machine learning tasks such as clustering and classification has appeared in a variety of fields, sometimes with the promise of reducing probl...
D. Sculley, Carla E. Brodley