Compression and Acceleration for Deep Convolutional Neural Networks

  • Weichao LAN

Student thesis: Doctoral Thesis

Abstract

Please refer to the "Abstract & TOC" file on the right side
Date of Award28 Jun 2024
Original languageEnglish
SupervisorYiu Ming CHEUNG (Supervisor)

User-Defined Keywords

  • Model Compression
  • Network Pruning
  • Quantization
  • Lightweight Networks
  • Knowledge Distillation

Cite this

Documents

  • Full Text

    File: application/pdf, 4.56 MB

    Type: Thesis

  • Abstract & TOC

    File: application/pdf, 65.2 KB

    Type: Supplementary materials

'