Open AccessEffective and High Computing Algorithms for Convolution Neural Networks
Author(s) -
P. S. V. Srinivasa Rao,
G.P.SaradhiVarma,
Rajasekhar Mutukuri
Publication year - 2018
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i3.31.18203
Subject(s) - computer science , convolutional neural network , convolution (computer science) , algorithm , benchmark (surveying) , computation , artificial neural network , artificial intelligence , geodesy , geography
Training a large set of data takes GPU days using Deep convolution neural networks which are a time taking process. Self-driving cars require very low latency for pedestrian detection. Image recognition constrained by limited processing resources for mobile phones. The computation speed of the training set determines that in these situations convolution neural networks was a success. For large filters, Conventional Faster Fourier Transform based convolution is preferably fast, yet in case of small, 3 × 3 filters state of the art convolutional neural networks is used. By using Winograd's minimal filtering algorithms the new class of fast algorithms for convolutional neural networks was introduced by us. Instead of small tiles, minimal complexity convolution was computed by the algorithms, this increases the computing speed with small batch sizes and small filters. With the VGG network, we benchmark a GPU implementation of our algorithm and at batch sizes from 1 to 64 state of the art throughput was shown.