Strongly-Typed Recurrent Neural Networks

Understand

Recurrent neural networks are increasing popular models for sequential learning.

• Unfortunately, although the most effective RNN architectures are perhaps excessively complicated, extensive searches have not found simpler alternatives.
• This paper imports ideas from physics and functional programming into RNN design to provide guiding principles.
• From physics, we introduce type constraints, analogous to the constraints that forbids adding meters to seconds.