ASSET Seminar: “Inherent Interpretability via Language Model Guided Bottleneck Design” (Mark Yatskar, Penn)
Levine 307 3330 Walnut Street, Philadelphia, PA, United StatesABSTRACT: As deep learning systems improve, their applicability to critical domains is hampered because of a lack of transparency. Post-hoc explanations attempt to address this concern but they provide no guarantee of faithfulness to the model’s computations. Inherently interpretable models are an alternative but such models are often considered to be too simple to perform […]