Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/bornlex/meta
https://github.com/bornlex/meta
Last synced: 11 days ago
JSON representation
- Host: GitHub
- URL: https://github.com/bornlex/meta
- Owner: Bornlex
- Created: 2023-11-09T13:02:48.000Z (about 1 year ago)
- Default Branch: master
- Last Pushed: 2024-05-03T19:15:15.000Z (8 months ago)
- Last Synced: 2024-11-08T15:30:32.769Z (2 months ago)
- Language: Python
- Size: 62.5 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Meta Learning
The Notion page associated with the project is located at the following address: https://www.notion.so/narcissetechnologies/Meta-Learning-f00f0afc5c844b4bb38fdd1d178f8581?pvs=4.
## Motivations
The goal of this project is to train a model that teaches another model some task.
The first model is learning how to update the weights each time it sees an example from the training set.
The second model is making predictions based.At the end of training, we then have two models:
- a model that is able to make inference
- a meta-model that is able to update the weights of the first model when a new example is given to, allowing one-shot learning## Models
### Prediction model
For the MVP, the model that predicts will be a very simple linear model.
### Meta model
The meta model is based on the Recurrent Neural Network architecture.