2 papers
cs.LG2026
Horizon Activation Mapping for Neural Networks in Time Series Forecasting
Krupakar Hans, V A Kandappan
Neural networks for time series forecasting have relied on error metrics and architecture-specific interpretability approaches for model selection that don't apply across models of…
math.NA2022
HODLR2D: A new class of Hierarchical matrices
V A Kandappan, Vaishnavi Gujjula, Sivaram Ambikasaran
This article introduces HODLR2D, a new hierarchical low-rank representation for a class of dense matrices arising out of body problems in two dimensions. Using this new hierarc…