Fast Computation of Wide Neural Networks
Abstract
The recent advances in artificial neural networks have demonstrated competitive performance of deep neural networks (and it is comparable with humans) on tasks like image classification, natural language processing and time series classification. These large scale networks pose an enormous computational challenge, especially in resource constrained devices. The current work proposes a targeted-rank based framework for accelerated computation of wide neural networks. It investigates the problem of rank-selection for tensor ring nets to achieve optimal network compression. When applied to a state of the art wide residual network, namely WideResnet, the framework yielded a significant reduction in computational time. The optimally compressed non-parallel WideResnet is faster to compute on a CPU by almost 2x with only 5% degradation in accuracy when compared to a non-parallel implementation of uncompressed WideResnet.
Degree
M.Sc.
Advisors
Aggarwal, Purdue University.
Subject Area
Artificial intelligence
Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server.