• Publications
  • Influence
Elements of artificial neural networks
TLDR
This paper presents a meta-modelling framework that automates the very labor-intensive and therefore time-heavy and therefore expensive and expensive process of supervised learning of neural networks.
An efficient k-means clustering algorithm
TLDR
The experimental results demonstrate that the proposed scheme can improve the computational speed of the direct k-means algorithm by an order to two orders of magnitude in the total number of distance calculations and the overall time of computation.
Efficient classification for multiclass problems using modular neural networks
TLDR
The approach is to use a modular network architecture, reducing a K-class problem to a set of K two-class problems, with a separately trained network for each of the simpler problems.
Conditional Anomaly Detection
TLDR
A general purpose method called conditional anomaly detection for taking differences among attributes into account, and three different expectation-maximization algorithms for learning the model that is used in conditional anomalies detection are proposed.
An improved algorithm for neural network classification of imbalanced training sets
TLDR
A modified technique for calculating a direction in weight-space which decreases the error for each class is presented and the rate of learning for two-class classification problems is accelerated by an order of magnitude.
An Efficient Algorithm for the Incremental Updation of Association Rules in Large Databases
TLDR
This paper proposes an incremental updating technique based on negative borders, for the maintenance of association rules when new transaction data is added to or deleted from a transaction database.
Dynamic cache reconfiguration and partitioning for energy optimization in real-time multi-core systems
TLDR
This paper presents a novel energy optimization technique which employs both dynamic reconfiguration of private caches and partitioning of the shared cache for multicore systems with real-time tasks and can achieve 29.29% energy saving on average.
Applications and performance analysis of a compile-time optimization approach for list scheduling algorithms on distributed memory multiprocessors
TLDR
Simulation results show that, given a directed acyclic growth (DAG), the graph parallelism of the DAG can accurately predict the number of processors to be used such that a good scheduling length and a good resource utilization can be achieved simultaneously.
Compiling Fortran 90D/HPF for Distributed Memory MIMD Computers
TLDR
This thesis describes an advanced compiler that can generate efficient parallel programs when the source programming language naturally represents an application's parallelism and Fortran 90D/HPF, described in this thesis is such a language.
...
...