2019-09-16, 12:30–13:00, Ferrier Hall
This talk will introduce applied deep learning in Python. We will provide an intuitive understanding of a few architectures, apply deep learning to a real problem, cover basic troubleshooting, and learn to analyze what our model gets wrong.
Deep learning is a useful tool for problems in computer vision, natural language processing, and medicine. While it might seem difficult to get started in deep learning, Python libraries, such as Keras make deep learning quite accessible. In this talk, I will discuss what deep learning is, introduce NumPy and Keras, and discuss common mistakes and debugging strategies. Throughout the talk, I will return to an example project in the medical domain, which used deep learning on vocal data to determine whether a patient has vocal trauma.