Sciweavers

1184 search results - page 167 / 237
» Memory Design for Constrained Dynamic Optimization Problems
Sort
View
EUROCAST
2007
Springer
182views Hardware» more  EUROCAST 2007»
15 years 8 months ago
A k-NN Based Perception Scheme for Reinforcement Learning
Abstract a paradigm of modern Machine Learning (ML) which uses rewards and punishments to guide the learning process. One of the central ideas of RL is learning by “direct-online...
José Antonio Martin H., Javier de Lope Asia...
DAC
2006
ACM
15 years 8 months ago
Signature-based workload estimation for mobile 3D graphics
Until recently, most 3D graphics applications had been regarded as too computationally intensive for devices other than desktop computers and gaming consoles. This notion is rapid...
Bren Mochocki, Kanishka Lahiri, Srihari Cadambi, X...
GECCO
2009
Springer
15 years 6 months ago
NEAT in increasingly non-linear control situations
Evolution of neural networks, as implemented in NEAT, has proven itself successful on a variety of low-level control problems such as pole balancing and vehicle control. Nonethele...
Matthias J. Linhardt, Martin V. Butz
AUTOMATICA
2005
178views more  AUTOMATICA 2005»
15 years 1 months ago
Spacecraft attitude control using explicit model predictive control
In this paper, an explicit model predictive controller for the attitude of a satellite is designed. Explicit solutions to constrained linear MPC problems can be computed by solvin...
Øyvind Hegrenæs, Jan Tommy Gravdahl, ...
TVLSI
2002
97views more  TVLSI 2002»
15 years 1 months ago
Techniques for energy-efficient communication pipeline design
The performance of many modern computer and communication systems is dictated by the latency of communication pipelines. At the same time, power/energy consumption is often another...
Gang Qu, Miodrag Potkonjak