Sciweavers

5757 search results - page 908 / 1152
» Dynamic Policy Programming
Sort
View
89
Voted
IJCNN
2000
IEEE
15 years 5 months ago
On Derivation of MLP Backpropagation from the Kelley-Bryson Optimal-Control Gradient Formula and Its Application
The well-known backpropagation (BP) derivative computation process for multilayer perceptrons (MLP) learning can be viewed as a simplified version of the Kelley-Bryson gradient f...
Eiji Mizutani, Stuart E. Dreyfus, Kenichi Nishio
110
Voted
IPPS
2000
IEEE
15 years 5 months ago
An Open Market-Based Architecture for Distributed Computing
One of the challenges in large scale distributed computing is to utilize the thousands of idle personal computers. In this paper, we present a system that enables users to e ortles...
Spyros Lalis, Alexandros Karypidis
LICS
2000
IEEE
15 years 5 months ago
A Theory of Bisimulation for a Fragment of Concurrent ML with Local Names
Concurrent ML is an extension of Standard ML with π-calculus-like primitives for multi-threaded programming. CML has a reduction semantics, but to date there has been no labelled...
Alan Jeffrey, Julian Rathke
95
Voted
MICRO
2000
IEEE
137views Hardware» more  MICRO 2000»
15 years 5 months ago
Relational profiling: enabling thread-level parallelism in virtual machines
Virtual machine service threads can perform many tasks in parallel with program execution such as garbage collection, dynamic compilation, and profile collection and analysis. Har...
Timothy H. Heil, James E. Smith
ASPDAC
2000
ACM
120views Hardware» more  ASPDAC 2000»
15 years 5 months ago
Data memory minimization by sharing large size buffers
- This paper presents software synthesis techniques to deal with non-primitive data type from graphical dataflow programs based on the synchronous dataflow (SDF) model. Non-primiti...
Hyunok Oh, Soonhoi Ha