Illuminating interactions between proteins and small drug molecules is a longstanding challenge in the field of drug discovery.

Generative Adversarial Networks (GANs) are a powerful class of generative models in the deep learning community.

Generative Adversarial Networks (GANs) are a powerful class of generative models in the deep learning community.

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

These methods heavily rely on the unique structure in the domain datasets (such as spatial relationships in images or semantic relationships in language).

Classical learning theory suggests that the optimal generalization performance of a machine learning model should occur at an intermediate model complexity, with simpler models exhibiting high bias and more complex models exhibiting high variance of the predictive function.

A unique benefit to this approach is that each transition's TD error can be

This paper proposes a reliable neural network pruning algorithm by setting up a scientific control. Existing pruning methods have developed various hypotheses to approximate the importance of filters to the network and then execute filter pruning accordingly.

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

An essential aspect of any machine learning system is understanding what the model does not know.