Accelerating Deep Learning with Shrinkage and Recall
This work addresses efficiency issues in deep learning for practitioners dealing with large data and models, though it appears incremental by adapting existing techniques from SVM and LASSO.
The paper tackles the problem of slow deep learning training on large-scale data and architectures by proposing a shrinking Deep Learning with recall (sDLr) approach, which achieves a speedup of over 2.0 while maintaining competitive classification performance across multiple neural network types and datasets.
Deep Learning is a very powerful machine learning model. Deep Learning trains a large number of parameters for multiple layers and is very slow when data is in large scale and the architecture size is large. Inspired from the shrinking technique used in accelerating computation of Support Vector Machines (SVM) algorithm and screening technique used in LASSO, we propose a shrinking Deep Learning with recall (sDLr) approach to speed up deep learning computation. We experiment shrinking Deep Learning with recall (sDLr) using Deep Neural Network (DNN), Deep Belief Network (DBN) and Convolution Neural Network (CNN) on 4 data sets. Results show that the speedup using shrinking Deep Learning with recall (sDLr) can reach more than 2.0 while still giving competitive classification performance.