Strongly recurrent transformations

Strongly-Typed Recurrent Neural Networks

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, analog...

Termination of Grounding Is Not Preserved by Strongly Equivalent Transformations

The operation of a typical answer set solver begins with grounding—replacing the given program with a program without variables that has the same answer sets. When the given program contains function symbols, the process of grounding may not terminate. In this note we give an example of a pair of consistent, strongly equivalent programs such that one of them can be grounded by lparse, dlv, and ...

How strong are correlations in strongly recurrent neuronal networks?

Cross-correlations in the activity in neural networks are commonly used to characterize their dynamical states and their anatomical and functional organizations. Yet, how these latter network features affect the spatiotemporal structure of the correlations in recurrent networks is not fully understood. Here, we develop a general theory for the emergence of correlated neuronal activity from the ...

Tryptophan immunoadsorption strongly reduces proteinuria in recurrent nephrotic syndrome.

Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis

An important problem for both graphics and vision is to synthesize novel views of a 3D object from a single image. This is particularly challenging due to the partial observability inherent in projecting a 3D object onto the image space, and the ill-posedness of inferring object shape and pose. However, we can train a neural network to address the problem if we restrict our attention to specifi...