In this work, we present a large-scale synthetic dataset that includes a differential diagnosis, along with the ground truth pathology, for each patient.
This presents an interesting machine learning challenge: can we predict runtime errors in a "static" setting, where program execution is not possible?
We further improve performance by adding data augmentation to the future prediction loss, which forces the agent's representations to be consistent across multiple views of an observation.
Ranked #3 on Atari Games 100k on Atari 100k
Time is an important feature in many applications involving events that occur synchronously and/or asynchronously.
In this paper, we build novel models for temporal KG completion through equipping static models with a diachronic entity embedding function which provides the characteristics of entities at any point in time.
Graphs arise naturally in many real-world applications including social networks, recommender systems, ontologies, biology, and computational finance.
Good temporal representations are crucial for video understanding, and the state-of-the-art video recognition framework is based on two-stream networks.