Modern massively-parallel Graphics Processing Units (GPUs) and Machine Learning (ML) frameworks enable neural network implementations of unprecedented performance and sophistication. However, state-of-the-art GPU hardware platforms are extremely power-hungry, while microprocessors cannot achieve the performance requirements. Biologically-inspired Spiking Neural Networks (SNN) have inherent characteristics that lead to lower power consumption. We thus present a bit-serial SNN-like hardware architecture. By using counters, comparators, and an indexing scheme, the design effectively implements the sum-of-products inherent in neurons. In addition, we experimented with various strength-reduction methods to lower neural network resource usage. The proposed Spiking Hybrid Network (SHiNe), validated on an FPGA, has been found to achieve reasonable performance with a low resource utilization, with some trade-off with respect to hardware throughput and signal representation.
Free Powerpoint Template - Computer Circuit Boards
Solved Calculate the distance olive oil (a lipid) could move, entfernung membran
Electronics Free Full-Text Experimental Analysis Of, 47% OFF
Electronics Free Full-Text Experimental Analysis Of, 47% OFF
Electronics, Free Full-Text, mod player action optimization
PDF) Circuit Fundamentals and Basic Electronics
RF adapters T+M - RF components T+M - Electronics test and, mercedes benz t nuts adapter
Electronics, Free Full-Text, car & vehicle electronics
Electronics All-in-One For Dummies 3rd Edition eBook at TradePub
Google Slides Templates Free Download - Computer Circuit Boards
13 Free Electronics Ebooks