Sensitivity-Aware Mixed-Precision Quantization and Width Optimization of Deep Neural Networks Through Cluster-Based Tree-Structured Parzen Estimation

Documenti analoghi

• Memory-Efficient Vision Transformers: An Activation-Aware Mixed-Rank Compression Strategy
  di: Azizi, Seyedarmin, et al.
  Pubblicazione: (2024)
• Scalable Superconductor Neuron with Ternary Synaptic Connections for Ultra-Fast SNN Hardware
  di: Karamuftuoglu, Mustafa Altay, et al.
  Pubblicazione: (2024)
• An On-Chip Trainable Neuron Circuit for SFQ-Based Spiking Neural Networks
  di: Ucpinar, Beyza Zeynep, et al.
  Pubblicazione: (2023)
• Mixed-Precision Quantization for Deep Vision Models with Integer Quadratic Programming
  di: Deng, Zihao, et al.
  Pubblicazione: (2023)
• NeuroBlend: Towards Low-Power yet Accurate Neural Network-Based Inference Engine Blending Binary and Fixed-Point Convolutions
  di: Fayyazi, Arash, et al.
  Pubblicazione: (2023)