Comparison of learning and generalization capabilities of the Kak and the backpropagation algorithms
Information Sciences—Intelligent Systems: An International Journal
On generalization by neural networks
Information Sciences—Informatics and Computer Science: An International Journal
Artificial Neural Network Implementation on a Fine-Grained FPGA
FPL '94 Proceedings of the 4th International Workshop on Field-Programmable Logic and Applications: Field-Programmable Logic, Architectures, Synthesis and Applications
Design methodologies for partially reconfigured systems
FCCM '95 Proceedings of the IEEE Symposium on FPGA's for Custom Computing Machines
| Hi-index | 0.00 |
The training of neural networks occurs instantaneously with Kak's corner classification algorithm CC4. It is based on prescriptive learning, hence is extremely fast compared with iterative supervised learning algorithms such as backpropagation. This paper shows that the Kak algorithm is hardware friendly and is especially suited for implementation in reconfigurable computing using fine grained parallelism. We also demonstrate that on-line learning with the algorithm is possible through dynamic evolution of the topology of a Kak neural network.