Automatic Pruning for Quantized Neural Networks

    Guerra Luis
    Guerra Luis
    Drummond Tom
    Drummond Tom
    Cited by: 0|Bibtex|Views10|Links

    Abstract:

    Neural network quantization and pruning are two techniques commonly used to reduce the computational complexity and memory footprint of these models for deployment. However, most existing pruning strategies operate on full-precision and cannot be directly applied to discrete parameter distributions after quantization. In contrast, we st...More

    Code:

    Data:

    Your rating :
    0

     

    Tags
    Comments