Deep Learning
You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle
Dinghuai Zhang, Tianyuan Zhang, Yiping Lu, Zhanxing Zhu, Bin Dong
Neural Information Processing Systems http://nips.cc/
ExplainMySurprise: LearningEfficientLong-Term MemorybyPredictingUncertainOutcomes
In many sequential tasks, a model needs to remember relevant events from the distant past to make correct predictions. Unfortunately, a straightforward application ofgradient based training requires intermediate computations tobestored for every element of a sequence. This requires to store prohibitively large intermediate data ifasequence consists ofthousands oreven millions elements, and asaresult, makeslearning ofverylong-term dependencies infeasible.
Reducing Network Agnostophobia
Akshay Raj Dhamija, Manuel Gรผnther, Terrance Boult
Neural Information Processing Systems http://nips.cc/
Riemannian Laplace approximations for Bayesian neural networks
However, practical posteriors are often, even locally, highly non-Gaussian, and empirical performance deteriorates.
