Reproduce “Learning Disentangled Representations with Semi-Supervised Deep Generative Models” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
N. Siddharth, Brooks Paige, Jan-Willem van de Meent, Alban Desmaison, Noah D. Goodman, Pushmeet Kohli, Frank Wood, Philip H.S. Torr
The authors introduce a framework for learning image representations with selected, interpretable latent variables and partially labeled data. Modellers specify variables such as digit identity and their dependencies, while neural networks learn remaining factors such as writing style. On MNIST, classification error with 3,000 labels is 1.57% (±0.93), versus 3.92% (±0.63) for M2, with minor setup differences.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.