This repository provides a custom implementation of the Titans architecture using TensorFlow. The aim is to harness state-of-the-art neural network design principles to develop scalable and efficient deep learning models.
The repository presents an implementation based on the Titans architecture described in the paper "Titans: Learning to Memorize at Test Time". Please note that only "Memory as a Context" has been implemented, and some variations may exist compared to the paper.
- Python 3.7 or later
- TensorFlow 2.x
pip install tf-titansRefer to the example file to get started. It is recommended to use the custom training function for models that incorporate memory.
Contributions are welcome. Please feel free to submit issues and pull requests.
This project is licensed under the MIT License. See the LICENSE file for further details.
For inquiries or further discussion, please contact [email protected].
@inproceedings{Behrouz2024TitansLT,
title = {Titans: Learning to Memorize at Test Time},
author = {Ali Behrouz and Peilin Zhong and Vahab S. Mirrokni},
year = {2024},
url = {https://api.semanticscholar.org/CorpusID:275212078}
}