Virtual Talk: Interpreting Deep Neural Networks towards Trustworthiness

Bin Yu
University of California, Berkeley (UC Berkeley)
Department of Statistics

Recent deep learning models have achieved impressive predictive performance by learning
complex functions of many variables, often at the cost of interpretability. This lecture
first defines interpretable machine learning in general and introduces the agglomerative
contextual decomposition (ACD) method to interpret neural networks. Extending ACD to
the scientifically meaningful frequency domain, an adaptive wavelet distillation (AWD)
interpretation method is developed. AWD is shown to be both outperforming deep neural
networks and interpretable in two prediction problems from cosmology and cell biology.
Finally, a quality-controlled data science life cycle is advocated for building
any model for trustworthy interpretation and introduce a Predictability Computability
Stability (PCS) framework for such a data science life cycle.


Back to Explainable AI for the Sciences: Towards Novel Insights