The Learner’s Bug Spotter, or how to spot bugs in source code.
Learning to program is fun and rewarding, but it also can be frustrating when we are stuck on a hard to find bug. Automated tests can tell if a solution is right or wrong, but often can’t say why it is wrong and how it should be fixed. What if computers could intelligently highlight problems in program logic and unusual constructs? In the talk I will present machine learning solutions to code bug-spotting and explain on which problems we can attain high accuracy.
Bio:
Dr Jan Chorowski is an associate professor at the Faculty of Mathematics and Computer Science of the University of Wrocław and the head of AI at NavAlgo. He holds a masters degree from the Wrocław University of Science and Technology and a PhD from the University of Louisville. He collaborated with many research teams, including Google Brain, Microsoft Research and MILA. He also led research during the JSALT 2019 workshop organized by Johns Hopkins University. His research interests are the application of neural networks to problems that are intuitive and easy for humans, but difficult for machines, such as speech and natural language processing. At NavAlgo, Dr. Chorowski develops artificial intelligence solutions for objects in motion.