Global-Local Capsule Network (GLCapsNet) is a capsule-based architecture able to provide context-based eye fixation prediction for several autonomous driving scenarios, while offering interpretability both globally and locally.

Accelerated the state-of-the-art in genome-scale metabolic network reconstruction more than 10 times by convex optimization techniques such as factorization, approximation, and regularization

A sampling algorithm that exploits context-specific independencies in probability distributions