Description: Deep learning for complex dynamical systems
Torchdyn Home About Research Contribute Join us on Slack Docs Github repo Star Join us on Slack Torchdyn Deep learning for complex dynamical systems Torchdyn is maintained by DiffeqML, an open research group for the intersection of deep learning and dynamical systems
Star pip install torchdyn === 1.0.1 Torchdyn is a PyTorch library and community dedicated to numerical deep learning: differential equations, integral transforms and implicit representations Join us on Slack Featured projects Torchdyn-related research and implementations Syntensor applies Torchdyn in biological systems simulation to predict and explain drug efficacy Syntensor is implementing Torchdyn combined with methods in geometric deep learning, to model biological flux dynamically, systemically and at
Neural Hybrid Automata provide a systematic inference method based on normalizing flows, neural differential equations, and self-supervision. This is a showcase of NHAs on several tasks, including end-to-end learning of hierarchical robot controllers.