Data quality and model under-specification issues (keynote)
Foutse Khomh · 2022
Nowadays, we are witnessing an increasing demand in both industry and academia for exploiting Deep Learning (DL) to solve complex real-world problems. However, the performance of these high-capacity learners is currently bounded by the quality and volume of their underlying training data. The use of incomplete, erroneous, or inappropriate training data, and the implementation of poor data management practices in a training pipeline often result into unreliable, biased, or under specified models. In this talk, I will report about some recent research works that we have conducted to identify best practices of data management for DL. I will also report about recent techniques and tools that we have developed to help detect the root cause of model under-specification issues early on during a DL training process.