Goto

Collaborating Authors

 Government









LearningFrequencyDomainApproximationfor BinaryNeuralNetworks

Neural Information Processing Systems

Since the gradient ofthe conventional sign function is almost zero everywhere which cannot be used for back-propagation, several attempts have been proposed to alleviate the optimization difficulty by using approximate gradient.



Explainable and Efficient Randomized Voting Rules

Neural Information Processing Systems

With a rapid growth in the deployment of AI tools for making critical decisions (or aiding humans in doing so), there is a growing demand to be able to explain to the stakeholders how these tools arrive at a decision.