Thesis - Open Access
Master of Science (MS)
Electrical Engineering and Computer Science
Accuracy Ensured Cmpression, CNN Pruning, Deep Neural Network, Deep Reinforcement Learning, Epoch based reward, Kernel pruning
Apart from the accuracy, the size of convolutional neural networks (CNN) models is another principal factor for facilitating the deployment of models on memory, power and budget constrained devices. However, conventional model compression techniques require human experts to setup parameters to explore the design space which is suboptimal and time consuming. Various pruning techniques are implemented to gain compression, trading off speed and accuracy. Given a CNN model , we propose an automated deep reinforcement learning  based model compression technique that can effectively turned off kernels on each layer by observing its significance on decision making. By observing accuracy, compression ratio and convergence rate, our model can automatically re-activate (turned on) the healthiest(fittest) kernels to train it again which greatly ameliorate the model compression quality. Experimented results on MNIST dataset , the proposed method reduces the size of convolution layers for VGG-like model  up to 60% with 0.5% increase in test accuracy within less than a half the number of initial amount of training (speed-up up to 2.5×), state-of-the-art results of dropping 80% kernels (86% parameters compressed) with increase in accuracy by 0.14%. Further dropping 84% kernels (94% parameters compressed) with the drop of test accuracy 0.40%. The first proposed Auto-AEC (Accuracy-Ensured Compression) model can compress the network by preserving original accuracy or increase in accuracy of the model, whereas, the second proposed Auto-CECA (Compression-Ensured Considering the Accuracy) model can compress to the maximum by preserving original accuracy or minimal drop of accuracy. Based on experiments, further analyzed effectiveness of kernels on different layers based on how proposed model explores & exploits in various stages of training.
Library of Congress Subject Headings
Neural networks (Computer science)
Number of Pages
South Dakota State University
In Copyright - Educational Use Permitted
Khatri, Romancha, "Kernel-Controlled DQN Based CNN Pruning for Model Compression and Acceleration" (2020). Electronic Theses and Dissertations. 4105.