PhD Candidate working on NLP and AI Safety

Research Data Analyst; QBI Bold & Basic Fellow (2019-2020). Jacob’s interests span the theory and applications of machine learning models – and deep learning in particular. He previously graduated from Ecole Polytechnique, in Paris, with an M1 (masters) in data science and a focus on NLP and machine vision. He was researching applications of deep learning to automated diagnosis in dermatology. His work included everything from data wrangling to refining convolutional architectures for the medical context.

Lab papers

  1. Stress testing reveals gaps in clinic readiness of image-based diagnostic artificial intelligence models.

    Young AT, Fernandez K, Pfau J, Reddy R, Cao NA, von Franque MY, Johal A, Wu BV, Wu RR, Chen JY, Fadadu RP, Vasquez JA, Tam A, Keiser MJ, Wei ML. NPJ Digit Med. 2021 Jan 21.

  2. Artificial Intelligence in Dermatology- A Primer.

    Young AT, Xiong M, Pfau J, Keiser MJ, Wei ML. J Invest Dermatol. 2020 Aug.

  3. Robust Semantic Interpretability- Revisiting Concept Activation Vectors.

    Pfau J, Young AT, Wei J, Wei ML, Keiser MJ. arXiv - ICML - WHI. 2020 Jul 17.

  4. Global Saliency- Aggregating Saliency Maps to Assess Dataset Artefact Bias.

    Pfau J, Young AT, Wei ML, Keiser MJ. arXiv - NeurIPS ML4H. 2019 Oct 16.