Deep learning has become a ubiquitous technology to improve machine intelligence. However, most of the existing deep models are structurally very complex, making them difficult to be deployed on the mobile platforms with limited computational power. In this paper, we propose a novel network compression method called dynamic network surgery, which can remarkably reduce the network complexity by making on-the-fly connection pruning...
Authors
Yurong Chen
Senior Research Director & Principle Research Scientist, Cognitive Computing Lab, Intel Labs China
Related Content
Enabling Factor Analysis on Thousand-Subject Neuroimaging Datasets
The scale of functional magnetic resonance image data is rapidly increasing as large multi-subject datasets are becoming widely available and...
Faster CNNs with Direct Sparse Convolutions and Guided...
Phenomenally successful in practical inference problems, convolutional neural networks (CNN) are widely deployed in mobile devices, data centers, and even...
On Large-Batch Training for Deep Learning: Generalization Gap...
The stochastic gradient descent (SGD) method and its variants are algorithms of choice for many Deep Learning tasks. These methods...
A Multilevel Framework for Sparse Optimization with Application...
Solving l1 regularized optimization problems is common in the fields of computational biology, signal processing and machine learning. Such l1...
