IEEE Transactions on Nanotechnology · 2023 · 24 citations · 43 references
ComputingComputer EngineeringComputer ScienceComputer ArchitectureEdge ComputingMachine LearningData CompressionEdge ArchitectureEdge Artificial IntelligenceEdge Data ProcessingEdge DevicesEdge-cloud ArchitectureCompressionCompression TechniquesEnergy ConsumptionHardware ResourcesMemory Footprint ReductionNeural Network QuantizationQuantizationVon Neumann Architecture
The amount of data processed in the cloud, the development of Internet-of-Things (IoT) applications, and growing data privacy concerns force the transition from cloud-based to edge-based processing. Limited energy and computational resources on edge push the transition from traditional von Neumann architectures to In-memory Computing (IMC), especially for machine learning and neural network applications. Network compression techniques are applied to implement a neural network on limited hardware resources. Quantization is one of the most efficient network compression techniques allowing to reduce the memory footprint, latency, and energy consumption. This paper provides a comprehensive review of IMC-based Quantized Neural Networks (QNN) and links software-based quantization approaches to IMC hardware implementation. Moreover, open challenges, QNN design requirements, recommendations, and perspectives along with an IMC-based QNN hardware roadmap are provided.
43
Fully hardware-implemented memristor convolutional neural network
Peng Yao, Huaqiang Wu, Bin Gao et al. · Nature · 2020 · 2.1K citations
Engineering, Computer Engineering, Electrical Engineering +12
Ali Shafiee, Anirban Nag, Naveen Muralimanohar et al. · ACM SIGARCH Computer Architecture News · 2016 · 1.5K citations
Neuro-inspired computing chips
Wenqiang Zhang, Bin Gao, Jianshi Tang et al. · Nature Electronics · 2020 · 874 citations
PipeLayer: A Pipelined ReRAM-Based Accelerator for Deep Learning
Linghao Song, Xuehai Qian, Hai Li et al. · 2017 · 821 citations