Acceleration of Convolutional Neural Networks
In recent years, Convolutional Neural Networks (CNNs) have demonstrated impressive performance on a wide range of computer vision problems. However, modern CNNs require huge amount of computation, which is a limiting factor for deployment on mobile platforms. The goal of this project is to explore the possible ways of accelerating the modern CNN architectures during the training time and the testing time.
Papers: M. Figurnov, D. Vetrov, P. Kohli. PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions, 2015 [arXiv preprint]
Have you spotted a typo?
Highlight it, click Ctrl+Enter and send us a message. Thank you for your help!