Itcomeswiththeadvantages ofVAEs, such asstable training, largesample diversity and aprincipled inference network, while having the flexibility to model a combination of continuous and discrete generative factors.

Meta-learning is a promising approach for using previous experience across a breadth of tasks to significantly accelerate learning ofnewtasks.

Neural Information Processing Systems http://nips.cc/

To facilitate this procedure, we propose Natural Program, a natural language-based deductive reasoning format. Our approach enables models to generate precise reasoning steps where subsequent steps are more rigorously grounded on prior steps.

Neural Information Processing Systems http://nips.cc/