Implementing Kak Neural Networks on a Reconfigurable Computing Platform

摘要

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 reconfig-urable 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.