neural-ode
Jupyter notebook with Pytorch implementation of Neural Ordinary Differential Equations
view repo
We introduce a new family of deep neural network models. Instead of specifying a discrete sequence of hidden layers, we parameterize the derivative of the hidden state using a neural network. The output of the network is computed using a blackbox differential equation solver. These continuous-depth models have constant memory cost, adapt their evaluation strategy to each input, and can explicitly trade numerical precision for speed. We demonstrate these properties in continuous-depth residual networks and continuous-time latent variable models. We also construct continuous normalizing flows, a generative model that can train by maximum likelihood, without partitioning or ordering the data dimensions. For training, we show how to scalably backpropagate through any ODE solver, without access to its internal operations. This allows end-to-end training of ODEs within larger models.
READ FULL TEXTJupyter notebook with Pytorch implementation of Neural Ordinary Differential Equations
Sample implementation of Neural Ordinary Differential Equations
Neural Ordinary Differential Equation
[IJCAI'19, NeurIPS'19] Anode: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs
Code for the NeurIPS 2019 paper: "Learning Dynamics of Attention: Human Prior for Interpretable Machine Reasoning"