A Binary-Tree Hierarchical Multiple-Chip Architecture for Real-Time Large-Scale Learning Processor Systems
Authors:
- 1 April 2010
- journal article
- Published by IOP Publishing in Japanese Journal of Applied Physics
- Vol. 49 (4S) , 04DE08
Abstract
A binary-tree hierarchical multiple-chip processor architecture leveraging the K-means clustering algorithm has been developed for real-time learning of large amounts of sample data. To improve the computational speed, an embedded memory configuration has been used to store all sample data on the same chip for massively parallel processing. As a solution to the problem of the maximum sample data size limited by the chip area, a multiple-chip architecture has been developed, in which dedicated processor chips are connected in a binary-tree hierarchical structure. As a result, the system has been made extendible to any larger scale depending on the application needs. Furthermore, the pipeline calculation flow has been introduced to compensate for the interchip data communication delay. A proof-of-concept chip was designed using a 0.18 µm five-metal complementary metal–oxide–semiconductor (CMOS) technology. The chip operation was verified by NanoSim simulation, and pipeline calculation flow was demonstrated by test chip measurement.Keywords
This publication has 12 references indexed in Scilit:
- Real-Time Learning Capability of Neural NetworksIEEE Transactions on Neural Networks, 2006
- Transformation-invariant clustering using the EM algorithmIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003
- An efficient k-means clustering algorithm: analysis and implementationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- Multigradient: a new neural network learning algorithm for pattern classificationIEEE Transactions on Geoscience and Remote Sensing, 2001
- The annealing robust backpropagation (ARBP) learning algorithmIEEE Transactions on Neural Networks, 2000
- Data clusteringACM Computing Surveys, 1999
- Genetic K-means algorithmIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 1999
- Neural-network front ends in unsupervised learningIEEE Transactions on Neural Networks, 1997
- Adaptive color segmentation-a comparison of neural and statistical methodsIEEE Transactions on Neural Networks, 1997
- Efficient learning algorithms for neural networks (ELEANNE)IEEE Transactions on Systems, Man, and Cybernetics, 1993