Sciweavers

567 search results - page 22 / 114
» Decomposing replicable functions
Sort
View
112
Voted
AAAI
2007
15 years 6 months ago
Compact Spectral Bases for Value Function Approximation Using Kronecker Factorization
A new spectral approach to value function approximation has recently been proposed to automatically construct basis functions from samples. Global basis functions called proto-val...
Jeffrey Johns, Sridhar Mahadevan, Chang Wang
139
Voted
TOPLAS
1998
133views more  TOPLAS 1998»
15 years 3 months ago
A Systematic Study of Functional Language Implementations
Abstract: We introduce a unified framework to describe, relate, compare and classify functional language implementations. The compilation process is expressed as a succession of p...
Rémi Douence, Pascal Fradet
147
Voted
JMLR
2012
13 years 6 months ago
Structured Output Learning with High Order Loss Functions
Often when modeling structured domains, it is desirable to leverage information that is not naturally expressed as simply a label. Examples include knowledge about the evaluation ...
Daniel Tarlow, Richard S. Zemel
114
Voted
CORR
2011
Springer
194views Education» more  CORR 2011»
14 years 10 months ago
Energy-Latency Tradeoff for In-Network Function Computation in Random Networks
—The problem of designing policies for in-network function computation with minimum energy consumption subject to a latency constraint is considered. The scaling behavior of the ...
Paul N. Balister, Béla Bollobás, Ani...
143
Voted
ISCAS
2008
IEEE
145views Hardware» more  ISCAS 2008»
15 years 10 months ago
Group learning using contrast NMF : Application to functional and structural MRI of schizophrenia
— Non-negative Matrix factorization (NMF) has increasingly been used as a tool in signal processing in the last couple of years. NMF, like independent component analysis (ICA) is...
Vamsi K. Potluru, Vince D. Calhoun