Search results with tag "Compressing deep"

D COMPRESSION: COMPRESSING DEEP NEURAL ETWORKS …

Network quantization and weight sharing further compresses the pruned network by reducing the number of bits required to represent each weight. We limit the number of effective weights we need to store by having multiple connections share the same weight, and then fine-tune those shared weights. Weight sharing is illustrated in Figure 3.

  Deep, Compression, Compressing, Quantization, Compressing deep