Gradient optimization of coupling networks for synchrony produces sparse bipartite monophilic topologies with provable threshold-free phase-locking in Kuramoto models.
Automatic differentiation in PyTorch
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
The Indirect Convolution algorithm avoids im2col by using an indirection buffer, reducing memory overhead proportionally to input channels and outperforming GEMM-based methods by up to 62% for convolutions requiring transformation.
citing papers explorer
-
Emergent Topology of Optimal Networks for Synchrony
Gradient optimization of coupling networks for synchrony produces sparse bipartite monophilic topologies with provable threshold-free phase-locking in Kuramoto models.
-
The Indirect Convolution Algorithm
The Indirect Convolution algorithm avoids im2col by using an indirection buffer, reducing memory overhead proportionally to input channels and outperforming GEMM-based methods by up to 62% for convolutions requiring transformation.