Nowadays, artificial intelligence (AI) and machine learning (ML) technologies are developing rapidly, especially in applications of deep learning (DL) in computer vision, which made giant progress in recent years. Meanwhile, structural damage recognition using images becomes one of the important topics in vision-based Structural Health Monitoring (SHM) and structural reconnaissance, which greatly relies on human visual inspection and experience. Thus, following these exciting developments, it is timely to implement the state-of-art ML and DL technologies in civil engineering applications and evaluate its potential benefits. In an effort towards this direction, the Pacific Earthquake Engineering Research (PEER) Center will organize the first image-based structural damage recognition competition, namely PEER Hub ImageNet (PHI) Challenge, in the summer of 2018.
Bootcamp related to application of ML in vision-based SHM will be held in June, and the main objectives are (1) to form a regular student staff team to prepare data and do preprocessing for the upcoming PHI Challenge,(2) to train the team members with several basics of ML and DL (several short lectures will be presented as shown in the schedule above), (3) to test the dataset through skills learned in this Bootcamp, (4) to attend the competition as a “Staff Team”. So all of you can enjoy the competition and compete with world-wide participants .
The temporary Bootcamp schedule is posted, and estimated time period is from May 28th to June 13th. Size of the official team will be around 8 to 12 members, but you are welcome to only attend the Bootcamp, which does not have a limit. Bootcamp sessions will be held in Davis Hall, specific location is TBD. Application is open to all Berkeley students.
If you are interested in joining us in the organization of this exciting event and attending the Bootcamp, please feel free to submit an application!
Application form: https://goo.gl/forms/jFMHJaOZ2eSJDCVl1
If you have any questions, please feel free to contact us:
- Mr. Yuqing Gao: gaoyuqing@berkeley.edu
- Dr. Selim Günay: selimgunay@berkeley.edu