Listen in as Anders Larson, FSA, MAAA, interviews Shea Parkes, FSA, MAAA, and Michael Niemerg, FSA, MAAA, about artificial neural networks. Artificial neural networks have gone through a recent renaissance as part of deep learning. Artificial neural networks can now provide amazing accuracy, but they come with an equally amazing amount of complexity. This podcast provides a very high-level overview of everything from their history to modern implementations.
If you’ve asked Alexa to tell you the weather forecast or play your favorite song, you’ve interacted with an artificial neural network. This group of powerful algorithms originated in the 20thcentury, but it wasn’t until advances in computing power in recent years that their use has become widespread. Still, they can feel like a black box, even to professionals with expertise in other machine learning algorithms. In this episode, Michael Niemerg joins Shea Parkes and Anders Larson to talk about how neural networks work, what types of problems they are particularly suited for, and some recommended implementations in Python and R.
