blindedjoy/RcTorch
a PyTorch based Reservoir Computing package with Automatic Hyper-Parameter Tuning
This helps researchers and engineers who work with time-series data to quickly build and optimize Echo State Networks (ESNs) for tasks like predicting system behavior or modeling dynamic systems. You provide your time-series data, and it outputs a trained ESN model along with its predictions and performance metrics. It's designed for practitioners who need accurate, efficient, and automated model development for complex time-dependent phenomena.
No commits in the last 6 months. Available on PyPI.
Use this if you need to predict future states of a dynamic system from time-series data, especially when dealing with complex or chaotic systems like a forced pendulum, and want an automated way to tune your model for best performance.
Not ideal if your problem involves static data prediction or if you prefer manual, fine-grained control over every aspect of a neural network's architecture and training process.
Stars
46
Forks
12
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jan 01, 2023
Commits (30d)
0
Dependencies
12
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/blindedjoy/RcTorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
sbi-dev/sbi
sbi is a Python package for simulation-based inference, designed to meet the needs of both...
SMTorg/smt
Surrogate Modeling Toolbox
reservoirpy/reservoirpy
A simple and flexible code for Reservoir Computing architectures like Echo State Networks
GPflow/GPflow
Gaussian processes in TensorFlow
dswah/pyGAM
[CONTRIBUTORS WELCOME] Generalized Additive Models in Python