Apr 30, 2020
George's paper this week is Sanity Checks for Saliency Maps. This work takes stock of a group of techniques that generate local interpretability - and assesses their trustworthiness through two 'sanity checks'. From this analysis, Adebayo et al demonstrate that a number of these tools are invariant to the model's...
Apr 28, 2020
George dives into his blog post experimenting with Scott Lundberg's SHAP library. By training an XGBoost model on a dataset about academic attainment and alcohol consumption can we develop a global interpretation of the underlying relationships? Lan leads the discussion of the paper Adversarial Examples Are Not Bugs,...
Apr 15, 2020
Today on the show, George leads a discussion about the Giant Language Test Room. Lan presents a news item about Setting Fairness Goals with TensorFlow Constrained Optimization Library. This library lets users configure and train machine learning problems based on multiple different metrics, making it easy to formulate...
Apr 8, 2020
Today on the show, Lan presents a blog post revealing the Dark secrets of BERT. This work uses telling visualizations of self-attention patterns before and after fine-tuning to probe: what happens in the fine-tuned BERT? George brings a novel technique to the show, "radioactive data" - a marriage of data...
Apr 1, 2020
Today on the show, Lan presents a blog post from Google Deepmind about Dopamine and temporal difference learning. This is the story of a fruitful collaboration between Neuroscience and AI researchers that found the activity of dopamine neurons in the mouse ventral tegmental area during a learnt probabilistic reward task...