Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications
international conference on learning representations, 2015.
Although the latest high-end smartphone has powerful CPU and GPU, running deeper convolutional neural networks (CNNs) for complex tasks such as ImageNet classification on mobile devices is challenging. To deploy deep CNNs on mobile devices, we present a simple and effective scheme to compress the entire CNN, which we call one-shot whole...More
PPT (Upload PPT)