nature-machine-intelligence

PyTorch and TensorFlow implementation of NCP, LTC, and CfC wired neural models

Official implementation of paper on Nature Machine Intelligence: "Preserving and Combining Knowledge in Robotic Lifelong Reinforcement Learning"

resVAE is a restricted latent variational autoencoder that we wrote to uncover hidden structures in gene expression data, especially using single-cell RNA sequencing. In principle it can be used with any hierarchically structured data though, so feel free to play around with it.