• Publications
  • Influence
Difference-Based Modules: A Class-Independent Module Mechanism
tl;dr
We describe a module mechanism, which we call difference-based modules, and an object-oriented language we call MixJuice. Expand
  • 44
  • 6
  • Open Access
Multi-tasking Method on Parallel Computers which Combines a Contiguous and Non-contiguous Processor Partitioning Algorithm
tl;dr
We propose a partitioning algorithm which combines a contiguous and a non-contiguous partitioninggorithm which combines the Adaptive Scan and the Multi Buddy. Expand
  • 23
  • 4
A Cerebral Cortex Model that Self-Organizes Conditional Probability Tables and Executes Belief Propagation
  • Yuuji Ichisugi
  • Computer Science
  • International Joint Conference on Neural Networks
  • 29 October 2007
tl;dr
This paper describes a neural network model of cerebral cortex, BESOM model, that acquires conditional probability tables for a Bayesian network using self-organizing maps and estimates states of random variables with an approximate belief propagation algorithm. Expand
  • 17
  • 3
  • Open Access
Exception Handling and Real Time Features in an Object-Oriented Concurrent Language
  • 22
  • 1
RbCl: A Reflective Object-Oriented Concurrent Language without a Run-time Kernel
tl;dr
We propose a re ective object-oriented concurrent language RbCl which has no run-time kernel. Expand
  • 39
  • 1
The Extensible Java Preprocessor Kit and a Tiny Data-Parallel Java
tl;dr
We describe the extensible Java preprocessor EPP and a data-parallel extension of Java implemented with EPP. Expand
  • 30
  • 1
Time sharing systems that use a partitioning algorithm on mesh-connected parallel computers
tl;dr
This paper describes the installation and performance of scheduling for ecient execution of parallel processes on a parallel OS called AP/Linux[1] that is designed for AP1000+ parallel computers. Expand
  • 9
  • 1
  • Open Access
An efficient recognition algorithm for restricted bayesian networks
We propose an optimization method for belief propagation. First we mathematically show that the belief propagation algorithm can be optimized by imposing a reasonable restriction on the conditionalExpand
  • 3
  • 1
  • Open Access
Hierarchical Reinforcement Learning with Unlimited Recursive Subroutine Calls
tl;dr
We propose a new hierarchical reinforcement learning architecture called RGoal, which combines learned simple tasks to solve unknown complicated tasks rapidly, sometimes in zero-shot time. Expand
  • 1
  • 1
Object-Oriented Concurrent Reflective Architectures
tl;dr
Reflection provides the abilities to reason and alter the dynamic behavior of computation from within the language framework. Expand
  • 14