Well File:
- Well Planning ( results)
- Shallow Hazard Analysis ( results)
- Well Plat ( results)
- Wellbore Schematic ( results)
- Directional Survey ( results)
- Fluid Sample ( results)
- Log ( results)
- Density ( results)
- Gamma Ray ( results)
- Mud ( results)
- Resistivity ( results)
- Report ( results)
- Daily Report ( results)
- End of Well Report ( results)
- Well Completion Report ( results)
- Rock Sample ( results)
Mark Elliot
Breaking the Activation Function Bottleneck through Adaptive Parameterization
Sebastian Flennerhag, Hujun Yin, John Keane, Mark Elliot
Neural Information Processing Systems http://nips.cc/
Breaking the Activation Function Bottleneck through Adaptive Parameterization
Sebastian Flennerhag, Hujun Yin, John Keane, Mark Elliot
Standard neural network architectures are non-linear only by virtue of a simple element-wise activation function, making them both brittle and excessively large. In this paper, we consider methods for making the feed-forward layer more flexible while preserving its basic structure. We develop simple drop-in replacements that learn to adapt their parameterization conditional on the input, thereby increasing statistical efficiency significantly.