Many important machine learning tasks are instances of structured prediction problems.

MAPO improves the sample efficiency and robustness of policy gradient, especially on tasks with sparse rewards.

Language encoding models help explain language processing in the human brain by learning functions that predict brain responses from the language stimuli that elicited them.

The goal is to find the model, i.e. hyper-parameters, with the highest validation accuracy.

Proposed loss functions can be readily applied with any existing DNN architecture and algorithm, while yielding good performance in a wide range of noisy label scenarios.

In contrast, we treat filters from an additive perspective. A series of secondary filters can be derived from a primary filter.

We propose stochastic ensemble value expansion (STEVE), a novel model-based technique that addresses this issue. By dynamically interpolating between model rollouts of various horizon lengths for each individual example, STEVE ensures that the model is only utilized when doing so does not introduce significant errors.

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

Learning low-dimensional embeddings of knowledge graphs is a powerful approach used to predict unobserved or missing edges between entities.

However, paired regression and adversarial loss still CANNOT solve image blur and motion deformation problems in principle.