Scholar
Micha Livne
Google Scholar ID: Cmm8ZugAAAAJ
Research Scientist, NVIDIA
Citations & Impact
Citations
189
H-index
6
i10-index
4
Publications
20
Co-authors
7
list available
Publications
Resume (English only)
Background
- Machine learning researcher focusing on latent variable models, representation learning, Bayesian inference, and semi-supervised/unsupervised learning.
- Has worked on machine learning, computer vision, physical inference, and optimization problems for the past decade.
- Previously focused on 3D video tracking combined with physical models.
- Currently researching representation learning, generative models, Bayesian modeling (strongly pro-Bayesian), and particularly the Mutual Information Machine (MIM).
- MIM uses a novel symmetric variational inference approach to learn latent representations with high mutual information and low marginal entropy, and is not prone to posterior collapse unlike VAEs.
