RNN computation is recovered from multi-hop graph pathways, and constraining these pathways via resolvent regularization yields improved temporal sparsity and task performance over standard L1.
FastGR: Global Routing on CPU–GPU With Heterogeneous Task Graph Scheduler.IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 42(7):2317–2330, July 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Unifying Dynamical Systems and Graph Theory to Mechanistically Understand Computation in Neural Networks
RNN computation is recovered from multi-hop graph pathways, and constraining these pathways via resolvent regularization yields improved temporal sparsity and task performance over standard L1.