raminmh/liquid_time_constant_networks
An implementation of Liquid Time-Constant Networks, continuous-time neural network models for time-series and sequence prediction tasks.
Not currently ranked — collecting fresh signals.
star history
This repository provides TensorFlow implementations of Liquid Time-Constant Networks (LTCs), a class of continuous-time recurrent neural networks with time-dependent dynamics. The implementation supports backpropagation through time (BPTT) for training and includes comparison baselines such as Neural ODEs, CTRNNs, LSTM, and GRU. It provides training scripts for time-series benchmarks including gesture segmentation, room occupancy detection, human activity recognition, traffic volume prediction, and ozone level forecasting.
Frequently asked
- What is raminmh/liquid_time_constant_networks?
- An implementation of Liquid Time-Constant Networks, continuous-time neural network models for time-series and sequence prediction tasks.
- Is liquid_time_constant_networks open source?
- Yes — raminmh/liquid_time_constant_networks is open source, released under the Apache-2.0 license.
- What language is liquid_time_constant_networks written in?
- raminmh/liquid_time_constant_networks is primarily written in Python.
- How popular is liquid_time_constant_networks?
- raminmh/liquid_time_constant_networks has 1.8k stars on GitHub.
- Where can I find liquid_time_constant_networks?
- raminmh/liquid_time_constant_networks is on GitHub at https://github.com/raminmh/liquid_time_constant_networks.