Compressing Deep Neural Networks A New Hashing Pipeline Using Kacs Random Walk Matrices

Parker-holder Jack, Gass Sam. Arxiv 2018

[Paper]    
ARXIV Deep Learning Supervised

The popularity of deep learning is increasing by the day. However, despite the recent advancements in hardware, deep neural networks remain computationally intensive. Recent work has shown that by preserving the angular distance between vectors, random feature maps are able to reduce dimensionality without introducing bias to the estimator. We test a variety of established hashing pipelines as well as a new approach using Kac’s random walk matrices. We demonstrate that this method achieves similar accuracy to existing pipelines.

Similar Work