Fast Computation of Wide Neural Networks
thesisposted on 02.01.2019, 18:16 by Vineeth Chigarangappa Rangadhamap
The recent advances in articial neural networks have demonstrated competitive performance of deep neural networks (and it is comparable with humans) on tasks like image classication, natural language processing and time series classication. 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 signicant 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.