CV
Hang Yang
Summary
PhD candidate in Mathematics at the University of Massachusetts Amherst. Researching machine learning, robotics, and deep learning — including mobile motion capture with robot dogs, invertible neural networks for image steganography, and vision transformers for medical AI.
Education
- Doctor of Science in MathematicsUniversity of Massachusetts Amherst (UMASS)GPA: 3.95/4.0
- Master of Science in Mathematics2024-07China Agricultural University (CAU)GPA: 3.80/4.0 (WES Evaluated: 3.86/4.0)
- Bachelor of Science in Mathematics2021-07China Agricultural University (CAU)GPA: 3.65/4.0 (WES Evaluated: 3.61/4.0)
Skills
Machine Learning
- Deep Learning
- Invertible Neural Networks
- Vision Transformers
- PyTorch
- Reinforcement Learning
- GAN
Research Areas
- Mobile Motion Capture
- Robotics
- Image Steganography
- Medical Image Analysis
- Computer Vision
Software Development
- Python
- Vue.js
- Django
Publications
- DKiS: Decay weight invertible image steganography with private key2025Neural NetworksIntroduces a decay weight mechanism and private key integration into high-capacity invertible image steganography, ensuring secure access to hidden information requires a corresponding key.
- PRIS: Practical robust invertible network for image steganography2024Engineering Applications of Artificial IntelligenceA practical robust invertible network for image steganography incorporating pre/post-enhancement modules and a gradient approximation function to handle rounding errors, achieving state-of-the-art robustness under multiple attacks.
- CovidViT: a novel neural network with self-attention mechanism to detect Covid-19 through X-ray images2022International Journal of Machine Learning and CyberneticsProposed Covid-Vision-Transformers (CovidViT) to detect Covid-19 cases through chest X-ray images using a self-attention mechanism.
Teaching
- MATH 233: Calculus 32024University of Massachusetts Amherst, Department of Mathematics and StatisticsRole: Teaching AssistantTeaching assistant for multivariable calculus covering partial derivatives, multiple integrals, and vector calculus.
- MATH 132: Calculus 22023University of Massachusetts Amherst, Department of Mathematics and StatisticsRole: Teaching AssistantTeaching assistant for integral calculus covering integration techniques, series, and applications.
Portfolio
- Personal WebsiteBuilt a personal website (yanghang.site) using Vue.js and Django.
- DQN with N-StepsReproduced the DQN algorithm from 'Human-Level Control through Deep Reinforcement Learning' and extended it with an n-step return method, achieving improved performance.
- Game AI with Policy Gradient & Q-TableDesigned and implemented automatic control for Airplane Wars and Tic-Tac-Toe games using Policy Gradient and Q-table methods.
- Automatic Figure Generation with GANImplemented a Generative Adversarial Network for automatic figure generation trained on the MNIST dataset.
- Automatic Pathfinding Based on Neural NetworkImplemented an automatic pathfinding system using neural network-based methods.