NCSI: A Visual Answering System for Crossword Puzzles using Deep Learning

Status	Completed
Mentor Name	Hao Ji
Mentor's XSEDE Affiliation	Education Allocation
Mentor Has Been in XSEDE Community	3-4 years
Project Title	A Visual Answering System for Crossword Puzzles using Deep Learning
Summary	We are currently witnessing an excitement in the research and industrial communities regarding advances in AI. In this project, we target an AI supporting system for crossword puzzles to provide visual aids through the image captured by a mobile phone. The system will tie together skills and knowledge in deep learning and computer vision. Our past efforts are investigating the approaches of deep learning and computer vision for crossword puzzle grid detection and alphabet letter identification. Our following research will continue to focus on developing deep learning models to solve crossword puzzle problems. We would like to apply for an XSEDE empower position, which will allow us to continue studying, developing, and training effective deep learning models for this AI-driven crossword puzzle system.
Job Description	The students will help the project by collecting and processing large datasets and by developing deep learning models to solve crossword puzzle problem.
Computational Resources	Bridges's GPU nodes Bridges Storage (Pylon)
Contribution to Community
Position Type	Learner
Training Plan	I will work closely with the students on this project to help the student gain in-depth understanding of deep learning and computer vision. To advise the student, I plan to meet with the students weekly to guide research progress.
Student Prerequisites/Conditions/Qualifications	Senior undergraduate students
Duration	Semester
Start Date	01/02/2018
End Date	03/24/2018