We describe significant developments towards a real-time implementation of SonArt, the parameter mapping framework first presented in [1] 1 . Enhancements include the incorporatio...
Competitive learning is a technique for training classification and clustering networks. We have designed and fabricated an 11transistor primitive, that we term an automaximizing ...
Inspired by the attractive Flops/dollar ratio and the incredible growth in the speed of modern graphics processing units (GPUs), we propose to use a cluster of GPUs for high perfo...
Zhe Fan, Feng Qiu, Arie E. Kaufman, Suzanne Yoakum...
This paper introduces an approach called Clustering and Co-evolution to Construct Neural Network Ensembles (CONE). This approach creates neural network ensembles in an innovative ...
This paper presents Cluster-Aware Remote Disks (CARDs), a Single System I/O architecture for cluster computing. CARDs virtualize accesses to remote cluster disks over a System Are...