search

BIDData / BIDMach

CPU and GPU-accelerated Machine Learning Library
BSD 3-Clause "New" or "Revised" License
915 stars 168 forks source link

Huffman code and Bidmach #116

Open arita37 opened 8 years ago

arita37 commented 8 years ago

Hello,

For the DNN and large memory ML algo, wondering if you will intend to use Huffman code to reduce the memory footprint of the parameters (weights for DNN).

Also, wondering if you will use techniques like pruning and weight sharing by quantization to reduce the memory usage ?

Thanks

jcanny commented 8 years ago

Probably not. We'd have to keep uncompressing them with each operation, which would undercut the value of using the GPU.