DeepAI
Log In Sign Up

DASNet: Dynamic Activation Sparsity for Neural Network Efficiency Improvement

09/13/2019
by   Qing Yang, et al.
3

To improve the execution speed and efficiency of neural networks in embedded systems, it is crucial to decrease the model size and computational complexity. In addition to conventional compression techniques, e.g., weight pruning and quantization, removing unimportant activations can reduce the amount of data communication and the computation cost. Unlike weight parameters, the pattern of activations is directly related to input data and thereby changes dynamically. To regulate the dynamic activation sparsity (DAS), in this work, we propose a generic low-cost approach based on winners-take-all (WTA) dropout technique. The network enhanced by the proposed WTA dropout, namely DASNet, features structured activation sparsity with an improved sparsity level. Compared to the static feature map pruning methods, DASNets provide better computation cost reduction. The WTA technique can be easily applied in deep neural networks without incurring additional training variables. More importantly, DASNet can be seamlessly integrated with other compression techniques, such as weight pruning and quantization, without compromising on accuracy. Our experiments on various networks and datasets present significant run-time speedups with negligible accuracy loss.

READ FULL TEXT

page 1

page 2

page 4

page 7

06/19/2019

Joint Pruning on Activations and Weights for Efficient Neural Networks

With rapidly scaling up of deep neural networks (DNNs), extensive resear...
08/14/2020

AntiDote: Attention-based Dynamic Optimization for Neural Network Runtime Efficiency

Convolutional Neural Networks (CNNs) achieved great cognitive performanc...
11/24/2021

Accelerating Deep Learning with Dynamic Data Pruning

Deep learning's success has been attributed to the training of large, ov...
08/11/2020

Bunched LPCNet : Vocoder for Low-cost Neural Text-To-Speech Systems

LPCNet is an efficient vocoder that combines linear prediction and deep ...
04/17/2019

Sparseout: Controlling Sparsity in Deep Networks

Dropout is commonly used to help reduce overfitting in deep neural netwo...
12/29/2015

Structured Pruning of Deep Convolutional Neural Networks

Real time application of deep learning algorithms is often hindered by h...
04/09/2018

Distribution-Aware Binarization of Neural Networks for Sketch Recognition

Deep neural networks are highly effective at a range of computational ta...