https://github.com/sagelywizard/snail

A PyTorch implementation of the blocks from the _A Simple Neural Attentive Meta-Learner_ paper
https://github.com/sagelywizard/snail

Last synced: about 2 months ago
JSON representation

A PyTorch implementation of the blocks from the _A Simple Neural Attentive Meta-Learner_ paper

• Host: GitHub
• URL: https://github.com/sagelywizard/snail
• Owner: sagelywizard
• License: mit
• Created: 2018-01-19T04:39:46.000Z (almost 7 years ago)
• Default Branch: master
• Last Pushed: 2018-04-17T21:18:10.000Z (over 6 years ago)
• Last Synced: 2024-07-31T23:44:52.033Z (4 months ago)
• Language: Python
• Homepage:
• Size: 7.81 KB
• Stars: 96
• Watchers: 9
• Forks: 18
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-few-shot-meta-learning - code (PyTorch) - 2

README

        
# A Simple Neural Attentive Meta-Learner implementation in PyTorch

A PyTorch implementation of the SNAIL building blocks.

This module implements the three blocks in [_A Simple Neural Attentive

Meta-Learner_](https://openreview.net/forum?id=B1DmUzWAW&noteId=B1DmUzWAW) by Mishra et al.

The three building blocks are the following:

- A dense block, built with causal convolutions.

- A TC Block, built with a stack of dense blocks.

- An attention block, similar to the attention mechanism described by Vaswani et al (2017).