Cargando…
Whether the Support Region of Three-Bit Uniform Quantizer Has a Strong Impact on Post-Training Quantization for MNIST Dataset?
Driven by the need for the compression of weights in neural networks (NNs), which is especially beneficial for edge devices with a constrained resource, and by the need to utilize the simplest possible quantization model, in this paper, we study the performance of three-bit post-training uniform qua...
Autores principales: | Nikolić, Jelena, Perić, Zoran, Aleksić, Danijela, Tomić, Stefan, Jovanović, Aleksandra |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8700806/ https://www.ncbi.nlm.nih.gov/pubmed/34946005 http://dx.doi.org/10.3390/e23121699 |
Ejemplares similares
-
Design of a 2-Bit Neural Network Quantizer for Laplacian Source
por: Perić, Zoran, et al.
Publicado: (2021) -
Single Abrikosov vortices as quantized information bits
por: Golod, T., et al.
Publicado: (2015) -
Optimization of the Sampling Periods and the Quantization Bit Lengths for Networked Estimation
por: Suh, Young Soo, et al.
Publicado: (2010) -
Gaussian Multiple Access Channels with One-Bit Quantizer at the Receiver †(,)‡
por: Rassouli, Borzoo, et al.
Publicado: (2018) -
Path integral quantization and stochastic quantization
por: Masujima, Michio
Publicado: (2000)