Abstract: In traditional binary classification tasks, learning algorithms conventionally distinguish positive and negative samples by leveraging fully labeled training data. However, in practical ...

Abstract: Though quite challenging, training a deep neural network for automatically solving Math Word Problems (MWPs) has increasingly attracted attention due to its significance in investigating how ...

Penn researchers have developed a smarter AI method for solving notoriously difficult inverse equations, which help scientists uncover hidden causes behind observable effects. By introducing ...

Robots are trained for specific tasks, such as cutting, using simulation. However, collecting real-world data is expensive, slow, and sometimes unsafe, particularly for tasks involving physical ...