Search Results for author:
Found 3 papers, 0 papers with code
Holistic Filter Pruning for Efficient Deep Neural Networks
Deep neural networks (DNNs) are usually over-parameterized to increase the likelihood of getting adequate initial weights by random initialization.
SYMOG: learning symmetric mixture of Gaussian modes for improved fixed-point quantization
We propose SYMOG (symmetric mixture of Gaussian modes), which significantly decreases the complexity of DNNs through low-bit fixed-point quantization.
Learning Multimodal Fixed-Point Weights using Gradient Descent
Due to their high computational complexity, deep neural networks are still limited to powerful processing units.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
