Asif Khan

5.19 Informatics Forum, University of Edinburgh.

I am a third-year PhD student in the Bayesian and Neural Systems group, advised by Prof. Amos Storkey and Prof. Chris Williams. My research interests are:

  • Deep Generative Models
  • Representation Learning
  • Bayesian Inference
  • Physics-prior in Neural Networks

Previously, I completed MSc. in Computer Science at the University of Bonn, where I was a research assistant at the Smart Data Analytics (SDA) group. I worked on Machine Learning for Knowledge Graphs with Prof. Asja Fischer and Prof. Jens Lehmann. In my master thesis, I developed a GAN framework for speech-to-speech synthesis advised by Prof. Asja Fischer and Dr. Fabien Cardinaux.

Selected Publications

  1. HALO: HAmiltonian Latent Operators for content and motion disentanglement in image sequences
    Khan, Asif, and Storkey, Amos
    Advances in Neural Information Processing Systems (to appear) 2022
  2. Adversarial robustness of β−VAE through the lens of local geometry
    Khan, Asif, and Storkey, Amos
    Workshop on New Frontiers in Adversarial Machine Learning, ICML 2022
  3. Trust-region Bayesian optimisation with developability constraints enables sample efficient, high-affinity antibody design
    Khan, Asif, Cowen-Rivers, Alexander I, and others,
    Workshop on Computational Biology, ICML 2022