2DSCNs improve image data analytics by extending SCN to handle spatial information.
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Trend · papers per month
RCNs match and exceed MLPs and SCNs in reinforcement learning tasks.
SCN learns and compensates for data bias in citizen science projects.
Study quantifies financial contagion risks in supply chains.
This paper proposes a novel selective autoencoder approach within the framework of deep convolutional networks. The crux of the idea is to train a deep convolutional autoencoder to suppress undesired parts of an image frame while allowing the desired parts resulting in efficient object detection. The efficacy of the fr…
Researchers infer firm-level supply chain networks from sector-level data to assess systemic risk.
Model predicts time evolution of supply chain networks under varying costs.
DSSCN improves lifelong learning of non-stationary data streams through adaptive network construction.
Simple stochastic Newton and cubic Newton methods with fast convergence.
SORSCNs improve nonstationary data modeling by self-organizing and adjusting network parameters.
Study limits of circadian synchronization under different light signals.