Accelerating Depthwise Separable Convolutions on Ultra-Low-Power Devices

Documenti analoghi

• Lightweight Software Kernels and Hardware Extensions for Efficient Sparse Deep Neural Networks on Microcontrollers
  di: Daghero, Francesco, et al.
  Pubblicazione: (2025)
• MATCHA: Efficient Deployment of Deep Neural Networks on Multi-Accelerator Heterogeneous Edge SoCs
  di: Russo, Enrico, et al.
  Pubblicazione: (2026)
• Optimizing the Deployment of Tiny Transformers on Low-Power MCUs
  di: Jung, Victor J. B., et al.
  Pubblicazione: (2024)
• MATCH: Model-Aware TVM-based Compilation for Heterogeneous Edge Devices
  di: Hamdi, Mohamed Amine, et al.
  Pubblicazione: (2024)
• EDEA: Efficient Dual-Engine Accelerator for Depthwise Separable Convolution with Direct Data Transfer
  di: Chen, Yi, et al.
  Pubblicazione: (2025)