Biography
I received a B.S. in Psychology with Distinction from the University of Illinois at Urbana-Champaign (UIUC). As an undergraduate at UIUC, I worked in Prof. Frances Wang’s Spatial Cognition and VR Lab and studied how navigation information influences time and space perception in virtual urban environments. Meanwhile, I completed a bachelor’s thesis about the linear separability effect in color space of visual search in Vision Lab, advised by Prof. Simona Buttei and Ph.D. Candidate Jing (Zoe) Xu.
Currently, I am a second-year student in the Master of Science in Psychological Science program at UIUC. I am working with Prof. Frances Wang and Prof. Diane Beck on comparison studies about object learning between humans and machines.
Research Interests
- Category/Object Learning and Other Types of Learning
- Visual Attention and Perception
- Connections Between Human and Machine Vision
- Spatial Perception and Cognition
- Decision Making
Research Description
Our recent project compares human continual learning with deep neural networks in classification tasks. One of the main challenges in machine learning is that the network readily forgets previously learned information as it encounters new information. For example, a deep network pre-trained with some images will acquire useful features for tasks such as classification. However, when training the network with more images from other sources to further improve its performance or to perform new tasks, it will show complete forgetting of the previously learned tasks, which is called catastrophic forgetting. In collaboration with Prof. Derek Hoiem and Zhen Zhu at the Department of Computer Science, we are examining human category learning under the same scenario to see whether and why the learning sequence affects humans and neural networks differently.