KEYNOTE 2 : Interpreting Deep Neural Networks towards Trustworthy AI,
SPEAKER: Prof. Bin Yu, UC Berkeley
MODERATOR: Alfred H. Balch
Abstract: In this talk, I describe adaptive wavelet distillation (AWD) interpretation method for pre-trained deep learning models. AWD is shown to be both outperforming deep neural networks and interpretable in the motivating cosmology problem and an external validating cell biology problem. Moreover, I discuss an investigation into the effects of pre-training data distributions on large language models (LLMs) for fine-tuning pathology report classification. Finally, I address the need to quality control the entire data science life cycle to build any model for trustworthy interpretable data results throughout Predictability-Computability-Stability (PCS) framework and documentation for veridical data science.
Bin Yu is Chancellor’s Distinguished Professor and Class of 1936 Second Chair in the Departments of statistics and EECS, and Center for Computational Biology at UC Berkeley. She obtained her BS Degree in Mathematics from Peking University, and MS and PhD Degrees in Statistics from UC Berkeley. She was Assistant Professor at UW-Madison, Visiting Assistant Professor at Yale University, Member of Technical Staff at Lucent Bell-Labs, and Miller Research Professor at Berkeley. She was a Visiting Faculty at MIT, ETH, Poincare Institute, Peking University, INRIA-Paris, Fields Institute at University of Toronto, Newton Institute at Cambridge University, and the Flatiron Institute in NYC. She was Chair of the Department of Statistics at UC Berkeley.
She has published more than 170 publications in premier venues and these papers not only investigate a wide range of research topics from practice to algorithms and to theory, but also seek deep insights. The breadth and depth of her research experience enabled unique and novel solutions to interdisciplinary data problems in audio and image compression, network tomography, remote sensing, neuroscience, genomics, and precision medicine.
Bin Yu is a Member of the U.S. National Academy of Sciences and of the American Academy of Arts and Sciences. She is Past President of the Institute of Mathematical Statistics (IMS), Guggenheim Fellow, Tukey Memorial Lecturer of the Bernoulli Society, Rietz Lecturer of IMS, and a COPSS E. L. Scott Prize winner. She has been selected to deliver the Wald Memorial Lectures of IMS at JSM in 2023.