Brain Networks Laboratory (Choe Lab)

Compressing Deep Neural Networks: A New Hashing Pipeline Using Kac's Random Walk Matrices

Jan 12, 2018

Compressing Deep Neural Networks: A New Hashing Pipeline Using Kac's Random Walk Matrices

Abstract: 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.

https://arxiv.org/abs/1801.02764v1


← Back to all articles         Quick Navigation:    Next:[ j ] – Prev:[ k ] – List:[ l ]