Sciweavers

773 search results - page 43 / 155
» Efficient system design space exploration using machine lear...
Sort
View
ATAL
2008
Springer
14 years 11 months ago
Efficient multi-agent reinforcement learning through automated supervision
Multi-Agent Reinforcement Learning (MARL) algorithms suffer from slow convergence and even divergence, especially in large-scale systems. In this work, we develop a supervision fr...
Chongjie Zhang, Sherief Abdallah, Victor R. Lesser
EDUTAINMENT
2009
Springer
15 years 4 months ago
AdMoVeo: A Robotic Platform for Teaching Creative Programming to Designers
Designing intelligent products, systems and related services require the designers to be able to integrate technology in their designs. Among other skills, programming is the key f...
Sjriek Alers, Jun Hu
GECCO
2007
Springer
187views Optimization» more  GECCO 2007»
15 years 3 months ago
Defining implicit objective functions for design problems
In many design tasks it is difficult to explicitly define an objective function. This paper uses machine learning to derive an objective in a feature space based on selected examp...
Sean Hanna
GECCO
2004
Springer
148views Optimization» more  GECCO 2004»
15 years 3 months ago
A Multi-objective Approach to Configuring Embedded System Architectures
Portable embedded systems are being driven by consumer demands to be thermally efficient, perform faster, and have longer battery life. To design such a system, various hardware un...
James Northern III, Michael A. Shanblatt
IJCAI
2007
14 years 11 months ago
Kernel Conjugate Gradient for Fast Kernel Machines
We propose a novel variant of the conjugate gradient algorithm, Kernel Conjugate Gradient (KCG), designed to speed up learning for kernel machines with differentiable loss functio...
Nathan D. Ratliff, J. Andrew Bagnell