Chunyuan Zhang

Chunyuan Zhang


Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 August 2020 in Information Sciences
Verified
Journal Article
Closed access
HDHongyao Deng
Hongyao Deng
JTJinsong Tao
Jinsong Tao
XSXiuli Song
Xiuli Song
CZChunyuan Zhang
Chunyuan Zhang

26 July 2023 in Applied Intelligence
Verified
Journal Article
Open access
PDF file
TYTianzong Yu
Tianzong Yu
CZChunyuan Zhang
Chunyuan Zhang
MMMeng Ma
Meng Ma
YWYuan Wang
Yuan Wang
Convolutional neural networks (CNNs) have shown good performance in many practical applications. However, their high computational and storage requirements make them difficult to deploy on resource-constrained devices. To address this issue, in this paper, we propose a novel iterative structured pruning algorithm for CNNs based on the recursive least squares (RLS) optimization. Our algorithm combines inverse input autocorrelation matrices with weight matrices to evaluate and prune unimportant input channels or nodes in each CNN layer and performs the next pruning operation when the testing loss is tuned down to the last unpruned level. Our algorithm can be used to prune feedforward neural networks (FNNs) as well. The fast convergence speed of the RLS optimization allows our algorithm to prune CNNs and FNNs multiple times in a small number of epochs. We validate its effectiveness in pruning VGG-16 and ResNet-50 on CIFAR-10 and CIFAR-100 and pruning a three-layer FNN on MNIST. Compared with four popular pruning algorithms, our algorithm can adaptively prune CNNs according to the learning task difficulty and can effectively prune CNNs and FNNs with a small or even no reduction in accuracy. In addition, our algorithm can prune the original sample features in the input layer.

1 January 2021 in Computational Intelligence and Neuroscience
Verified
Journal Article
Open access
PDF file
CZChunyuan Zhang
Chunyuan Zhang
QSQi Song
Qi Song
ZMZeng Meng
Zeng Meng
The deep Q‐network (DQN) is one of the most successful reinforcement learning algorithms, but it has some drawbacks such as slow convergence and instability. In contrast, the traditional reinforcement learning algorithms with linear function approximation usually have faster convergence and better stability, although they easily suffer from the curse of dimensionality. In recent years, many improvements to DQN have been made, but they seldom make use of the advantage of traditional algorithms to improve DQN. In this paper, we propose a novel Q‐learning algorithm with linear function approximation, called the minibatch recursive least squares Q‐learning (MRLS‐Q). Different from the traditional Q‐learning algorithm with linear function approximation, the learning mechanism and model structure of MRLS‐Q are more similar to those of DQNs with only one input layer and one linear output layer. It uses the experience replay and the minibatch training mode and uses the agent’s states rather than the agent’s state‐action pairs as the inputs. As a result, it can be used alone for low‐dimensional problems and can be seamlessly integrated into DQN as the last layer for high‐dimensional problems as well. In addition, MRLS‐Q uses our proposed average RLS optimization technique, so that it can achieve better convergence performance whether it is used alone or integrated with DQN. At the end of this paper, we demonstrate the effectiveness of MRLS‐Q on the CartPole problem and four Atari games and investigate the influences of its hyperparameters experimentally.

12 July 2016
Verified
Book Chapter
Closed access
PDF file
CZChunyuan Zhang
Chunyuan Zhang
QZQingxin Zhu
Qingxin Zhu
XNXinzheng Niu
Xinzheng Niu

13 January 2022 in arXiv
Verified
Preprint
Open access
PDF file
TYTianzong Yu
Tianzong Yu
CZChunyuan Zhang
Chunyuan Zhang
YWYuan Wang
Yuan Wang
MMMeng Ma
Meng Ma
QSQi Song
Qi Song
Convolutional neural networks (CNNs) have succeeded in many practical applications. However, their high computation and storage requirements often make them difficult to deploy on resource-constrained devices. In order to tackle this issue, many pruning algorithms have been proposed for CNNs, but most of them can't prune CNNs to a reasonable level. In this paper, we propose a novel algorithm for training and pruning CNNs based on the recursive least squares (RLS) optimization. After training a CNN for some epochs, our algorithm combines inverse input autocorrelation matrices and weight matrices to evaluate and prune unimportant input channels or nodes layer by layer. Then, our algorithm will continue to train the pruned network, and won't do the next pruning until the pruned network recovers the full performance of the old network. Besides for CNNs, the proposed algorithm can be used for feedforward neural networks (FNNs). Three experiments on MNIST, CIFAR-10 and SVHN datasets show that our algorithm can achieve the more reasonable pruning and have higher learning efficiency than other four popular pruning algorithms.

1 January 2009 in Journal of Electronics (China)
Verified
Journal Article
Closed access
PDF file
YXYajie Xu
Yajie Xu
ZMZhi Ma
Zhi Ma
CZChunyuan Zhang
Chunyuan Zhang