HIGHLIGHTS
SUMMARY
DEEP neural_networks (DNNs) have highly flexible parametric properties, and these properties are being exploited to develop artificial_intelligence (AI) applications in various domains ranging from cloud computing to edge computing. Section Section 22introduces introducesthe thebackground backgroundof ofmodel model This quantization, quantization,the theSRAM SRAMCIM CIMmacro, macro,and andthe theCIM-based CIM-basedaccelerator. accelerator.Section Section33describes describes the theproposed proposedSRAM-based SRAM-basedCIM CIMaccelerator acceleratorarchitecture architecturedesign. design. Deep neural_networks (DNNs) have achieved remarkable accuracies in various doDeep neural_networks (DNNs) have achieved remarkable accuracies in various mains of tasks, including computer vision, speech recognition, and NLP. domains . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.