A NEW HARDWARE ARCHITECTURE FOR FPGA IMPLEMENTATION OF FEED FORWARD NEURAL NETWORK
1V.A.Sumayyabeevi, JaimyJames Poovely, Anju George
138 Views
131 Downloads
Abstract:
New chips for machine learning applications appear, they are turned for specific topology being efficient by using highly parallel designs at the cost of high power or large complex devices. Although, the computational demands of deep neural networks require flexible and efficient hardware architectures able to fit different applications, neural network types, number of inputs, outputs, layers and units in each layer , making the conversion from software to hardware easy.
Keywords:
Paper DetailsFeed forward neural networks - FFNN, systolic hardware architecture, FPGA implementation
Volume24
IssueIssue 7
Pages11114-11121