分群剪枝與支援稀疏性之預測閥值動態量化的節能深度神經網路加速器晶片設計

Translated title of the contribution: Cluster Pruning and Dynamic Quantization of Sparsity-Supported Prediction Threshold Energy-Efficient Accelerator Chip Design for Deep Neural Networks

顏郁霖

Research output: Types of Thesis › Master's thesis

Translated title of the contributionCluster Pruning and Dynamic Quantization of Sparsity-Supported Prediction Threshold Energy-Efficient Accelerator Chip Design for Deep Neural Networks
Original languageChinese (Traditional)
Supervisors/Advisors
  • Wey, I-Chyn, Supervisor
StatePublished - 2022
Externally publishedYes

Access to Document

Cite this