[ Collaborated with Toyota Research, Illinois Tech ]
Material development heavily relies on domain knowledge and professional’s intuitive, which hinders the discovery of new material. We are collaborating with material experts and propose generative models for boosting material discovery.
[ Collaborated with George Manson University ]
Boolean Satisfiability (SAT) problem is a fundamental problem in computer science and the core of many real-world applications such as hardware and software design. However, its solving or estimating hardness of SAT is NP-hard. We are seeking for a series of a methodology by deep learning to significantly accelerate its solving and estimation.
[ Collaborated with Georgia Tech ]
Computational creativity is a lively research area that focuses on understanding and facilitating human creativity through the implementation of software programs. With the rapid advances in data driven algorithms such as deep learning, the exploration into computational creativity via machine learning approaches have become increasingly popular.
[ Collaborated with DAC at Virginia Tech ]
Graph neural networks (GNNs) motivate many applications based on network data such as transportation road. However, as a practical scenario, the road has very different characteristics from a smooth network (e.g., social network) often used by GNN experiments. We plan to identify these special features and accordingly adjust GNN to adopt transportation problems.
[ Collaborated with University of Taxes at Dallas, Rensselaer Polytechnic Institute ]
Today’s deep learning is still a black box. Similarly, graph neural network is another black box. This incurs difficult in comparison and improvement since each method is acclaimed as state-of-the-art. A unified framework is needed to avoid the potential risks, which is our goal.
The current generation is inspired by neuron’s connection. However, more effective mechanisms of human’s brain are remains ignored. We plan to introduce more brain’s feature to advance current deep learning techniques
Intuitively, humans understand and infer among multiple types of data such as image, video and text, which are often represented by vector subjecting to very different distributions. How to integrate multimodal data for understanding the world is critical to boosting the power of general AI.