Zhongzhan Huang - IEEE Xplore Author Profile
Subscribe
ADVANCED SEARCH

Author details

< Back

Zhongzhan Huang

Publications
3
Citations
5
Publications by Year
20212024
Co-Authors:
Show All Co-Authors (9)
Image of author Zhongzhan Huang

Zhongzhan Huang

Affiliation

School of Computer Science and Engineering
Sun Yat-sen University
Guangzhou, China

Publication Topics

Biography

Zhongzhan Huang is currently working toward the Ph.D. degree with Sun Yat-sen University, Guangzhou, China, advised by Prof. Liang Lin. His research interests include foundations of deep learning, neural network formulation (e.g., network pruning, design of effective network architectures, attention mechanism), and artificial intelligence for scientific computing.(Based on document published on 4 June 2024).
Publications
3
Citations
5
Publications by Year
20212024
Co-Authors:
Show All Co-Authors (9)
Author's Published Works

Showing 1-3 of 3 results

  • Sort

Filter Results

Show

Sort By

Results

Continuous Value Assignment: A Doubly Robust Data Augmentation for Off-Policy Learning

Junfan Lin;Zhongzhan Huang;Keze Wang;Lingbo Liu;Liang Lin

IEEE Transactions on Neural Networks and Learning Systems
Year: 2024 | Early Access Article |
Deep reinforcement learning (RL) has witnessed remarkable success in a wide range of control tasks. To overcome RL’s notorious sample inefficiency, prior studies have explored data augmentation techniques leveraging collected transition data. However, these methods face challenges in synthesizing transitions adhering to the authentic environment dynamics, especially when the transition is high-dim...Show More

Continuous Value Assignment: A Doubly Robust Data Augmentation for Off-Policy Learning

Junfan Lin;Zhongzhan Huang;Keze Wang;Lingbo Liu;Liang Lin

Year: 2024 | Early Access Article |

An Introspective Data Augmentation Method for Training Math Word Problem Solvers

Jinghui Qin;Zhongzhan Huang;Ying Zeng;Quanshi Zhang;Liang Lin

IEEE/ACM Transactions on Audio, Speech, and Language Processing
Year: 2024 | Volume: 32 | Journal Article |
Though quite challenging, training a deep neural network for automatically solving Math Word Problems (MWPs) has increasingly attracted attention due to its significance in investigating how a machine can understand and reason complex problems like a human. However, the data volume of existing high-quality MWP datasets is far from sufficient to train a robust solver since collecting these datasets...Show More

An Introspective Data Augmentation Method for Training Math Word Problem Solvers

Jinghui Qin;Zhongzhan Huang;Ying Zeng;Quanshi Zhang;Liang Lin

Year: 2024 | Volume: 32 | Journal Article |

Continuous Transition: Improving Sample Efficiency for Continuous Control Problems via MixUp

Junfan Lin;Zhongzhan Huang;Keze Wang;Xiaodan Liang;Weiwei Chen;Liang Lin

2021 IEEE International Conference on Robotics and Automation (ICRA)
Year: 2021 | Conference Paper |
Cited by: Papers (5)
Although deep reinforcement learning (RL) has been successfully applied to a variety of robotic control tasks, it’s still challenging to apply it to real-world tasks, due to the poor sample efficiency. Attempting to overcome this shortcoming, several works focus on reusing the collected trajectory data during the training by decomposing them into a set of policy-irrelevant discrete transitions. Ho...Show More

Continuous Transition: Improving Sample Efficiency for Continuous Control Problems via MixUp

Junfan Lin;Zhongzhan Huang;Keze Wang;Xiaodan Liang;Weiwei Chen;Liang Lin

Year: 2021 | Conference Paper |

IEEE Account

Purchase Details

Profile Information

Need Help?

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2025 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.