An architecture design using VLSI building blocks for dynamic programming neural networks
Great Lakes Symposium on VLSI(1991)
摘要
An architecture for dynamic programming neural networks is presented. The architecture is based on a building block paradigm in which the network is constructed from neuron array and weight assignment chips. Because of its simple and regular structure, the architecture is a feasible implementation for dynamic programming neural networks with current VLSI technology. Moreover, this architecture can be further extended to other Hopfield-Tank type networks
更多查看译文
关键词
analogue computer circuits,neural networks,hopfield-tank type networks,parallel architectures,neuron array,weight assignment chips,vlsi building blocks,vlsi,dynamic programming,architecture design,neural nets,cost function,artificial neural networks,neural network,energy states,very large scale integration,chip,linear programming
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要