![Journal Club artwork](https://is2-ssl.mzstatic.com/image/thumb/Podcasts113/v4/64/ed/d6/64edd667-48f6-01a3-577e-3b728c379b9b/mza_2305178031294040920.jpg/100x100bb.jpg)
Albert, Seinfeld, and Explainable AI
Journal Club
English - March 22, 2020 17:06 - 36 minutes - 41.6 MBMathematics Science Education computerscience machinelearning modelinterpretability Homepage Download Google Podcasts Overcast Castro Pocket Casts RSS feed
Previous Episode: Chess Transformer, Kaggle Scandal, and Interpretability Zoo
Next Episode: Google's New Data Engine, Activation Atlas, and LIME
Kyle discusses Google's recent open sourcing of ALBERT, a variant of the famous BERT model for natural language processing. ALBERT is more compact and uses fewer parameters. George leads a discussion about the paper Explainable Artificial Intelligence: Understanding, visualizing, and interpreting deep learning models by Samek, Wiegand, and Muller. This work introduces two tools for generating local interpretability and a novel metric to objectively compare the quality of explanations. Last but not least, Lan talks about her experience generating new Seinfeld scripts using GPT-2.