Displaying 1 to 9 from 9 results

Meta-Learning-Papers - Meta Learning / Learning to Learn / One Shot Learning / Few Shot Learning

  •    

[1] Nicolas Schweighofer and Kenji Doya. Meta-learning in reinforcement learning. Neural Networks, 16(1):5–9, 2003. [2] Sepp Hochreiter, A Steven Younger, and Peter R Conwell. Learning to learn using gradient descent. In International Conference on Artificial Neural Networks, pages 87–94. Springer, 2001.

LearningToCompare_FSL - PyTorch code for CVPR 2018 paper: Learning to Compare: Relation Network for Few-Shot Learning (Few-Shot Learning part)

  •    Python

For Zero-Shot Learning part, please visit here. For Omniglot experiments, I directly attach omniglot 28x28 resized images in the git, which is created based on omniglot and maml.

EPG - Open-sourced code for Evolved Policy Gradients

  •    Python

The paper is located at https://arxiv.org/abs/1802.04821. A demonstration video can be found at https://youtu.be/-Z-ieH6w0LA. Houthooft, R., Chen, R. Y., Isola, P., Stadie, B. C., Wolski, F., Ho, J., Abbeel, P. (2018). Evolved Policy Gradients. arXiv preprint arXiv:1802.04821.




meta-critic-networks - Pytorch code for Arxiv Paper: Learning to learn: Meta-Critic Networks for Sample-Efficient Learning

  •    Python

Pytorch code for Arxiv Paper: Learning to learn: Meta-Critic Networks for Sample-Efficient Learning

maml-tensorflow - This repository implements the paper, Model-Agnostic Meta-Leanring for Fast Adaptation of Deep Networks

  •    Python

This repository implements the paper, Model-Agnostic Meta-Leanring for Fast Adaptation of Deep Networks. Downlaod Omniglot dataset from the link. Only images_background.zip and images_evalueation.zip are required.


keita - My personal toolkit for PyTorch development.

  •    Python

A couple of PyTorch utilities, dataset loaders, and layers suitable for natural language processing, computer vision, meta-learning, etc. which I'm opening out to the community. In terms of code organization, I would like to clarify that I myself am not a fan of using huge repositories of highly un-maintained, dependant code and thus intend to keep this repository as modular as possible. Hence, for all modules you wish to use in your project, copy-pasting the module alongside a few utility methods should be all that you need to do to get it incorporated into your project.