liquid_time_constant_networks and Liquid-Time-stochasticity-networks
LTCs provide a foundational neural network architecture with continuous-time dynamics, while LTSs extend this framework by introducing stochastic elements to the liquid time-constant mechanism, making them evolutionary variants rather than direct competitors or complements.
About liquid_time_constant_networks
raminmh/liquid_time_constant_networks
Code Repository for Liquid Time-Constant Networks (LTCs)
This project helps researchers and machine learning practitioners benchmark and compare the performance of different continuous-time neural network models on various time-series prediction and classification tasks. You input raw time-series datasets (like sensor readings or gesture data) and it outputs model performance metrics (e.g., accuracy, loss) for different continuous-time network architectures. This is primarily for machine learning researchers or data scientists focused on advanced time-series analysis.
About Liquid-Time-stochasticity-networks
Ammar-Raneez/Liquid-Time-stochasticity-networks
Code repository for Liquid Time-stochasticity networks (LTSs)
This project helps researchers and data scientists working with time-series data, especially when dealing with unpredictable or 'stochastic' patterns. It takes in sequential data, like financial market prices or sensor readings, and produces models capable of predicting future values based on past observations. This is ideal for those needing to analyze and forecast complex, time-dependent systems.
Scores updated daily from GitHub, PyPI, and npm data. How scores work