Yet they are still far from true intelligence, which opens up intriguing opportunities to explore the parallels of humans and modelbehaviors.

In this paper, we present a convex optimization framework to compute guaranteed upper bounds on the Lipschitz constant of DNNs both accurately and efficiently.

NPI contributes structural biases in the form of modularity, hierarchy and recursion, which are helpful to reduce sample complexity, improve generalization and increase interpretability. AlphaZero contributes powerful neural network guided search algorithms, which we augment with recursion. AlphaNPI only assumes a hierarchical program specification with sparse rewards: 1 when the program execution satisfies the specification, and 0otherwise. This specification enables us to overcome the need for strong supervision in the form of execution traces andconsequently trainNPImodels effectivelywithreinforcement learning.

Achieving a balance between image quality (precision) and diversity (recall) is a significant challenge in the domain of generative models.

Bilinear feature transformation has shown the state-of-the-art performance in learning fine-grained image representations.

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

We introduce in this paper a novel strategy for efficiently approximating the Sinkhorn distance between twodiscrete measures.