raminmh/CfC
Closed-form Continuous-time Neural Networks (CfC) are recurrent neural network units for sequential data processing in PyTorch and TensorFlow.
Not currently ranked — collecting fresh signals.
star history
This repository implements CfC, a continuous-time neural network model designed for handling irregularly sampled sequential data. It provides implementations in both TensorFlow 2.x and PyTorch with various model variants including gated and minimal configurations. The library includes training scripts for datasets like Physionet 2012, IMDB, and Walker2d, making it a practical tool for benchmarking continuous-time neural network architectures.
Frequently asked
- What is raminmh/CfC?
- Closed-form Continuous-time Neural Networks (CfC) are recurrent neural network units for sequential data processing in PyTorch and TensorFlow.
- Is CfC open source?
- Yes — raminmh/CfC is open source, released under the Apache-2.0 license.
- What language is CfC written in?
- raminmh/CfC is primarily written in Python.
- How popular is CfC?
- raminmh/CfC has 1k stars on GitHub.
- Where can I find CfC?
- raminmh/CfC is on GitHub at https://github.com/raminmh/CfC.