seal -dynamic
Technology:
Country:
- North America > United States > Minnesota > Hennepin County > Minneapolis (0.14)
- North America > United States > California (0.14)
- Asia > South Korea > Seoul > Seoul (0.04)
- (6 more...)
Structured Energy Network as a Loss Function Jay-Y oon Lee
Belanger & McCallum (2016) and Gygli et al. (2017) have shown that energy In this work, we propose Structured Energy As Loss (SEAL) to take advantage of the expressivity of energy networks without incurring the high inference cost. This raises a question: Can energy networks be used in a way that is as expressive as SPENs, as efficient at inference as feedforward approaches, and also easy to train?
Country:
- North America > United States > Minnesota > Hennepin County > Minneapolis (0.14)
- North America > United States > California (0.14)
- Asia > South Korea > Seoul > Seoul (0.04)
- (6 more...)
Industry:
- Education (0.93)
- Energy > Power Industry (0.86)