Closed-form Continuous-time Neural Networks (CfCs)

Closed-form Continuous-time Neural Networks (CfCs) are powerful sequential liquid neural information processing units.

Paper Open Access: https://www.nature.com/articles/s42256-022-00556-7

Arxiv: https://arxiv.org/abs/2106.13898

Neural Circuit Policies(NCPs)

Neural Circuit Policies are recurrent neural network models inspired by the nervous system of the nematode C. elegans. The package currently provides two neuron models: LTC and CfC

A Tutorial on Liquid Neural Networks(NCPs) including Liquid CfCs: https://ncps.readthedocs.io/en/latest/quickstart.html

Module description

• NCPs_CfC.py CfC model implemented using Neural Circuit Policies (NCPs)
• CfC_miscredit.py Training and Forecasting Time Series Using CfC Models
• data.xlsx Dataset for CfC_miscredit.py file
• CfC.xlsx Output of CfC_miscredit.py file