Memory Bottleneck

Summary: Documentation and files about the Memory Bottleneck component, as part of the GUT-AI Initiative.

Table of Contents

• About
• Main papers
  • Selected publications
  • References
• Component files
  • Component page
  • Component DOI
  • Component dependencies
  • Environment simulators
  • Datasets
  • Model Zoos
• Getting involved
• How to cite this
• License

About

The purpose of this component is to solve the issue of memory bottleneck in order to enable the Inference of Deep Learning models in embedded devices (while also addressing Moravec's Paradox).

Main papers

Selected publications

• Kourouklides, I. (2022). Bayesian Deep Multi-Agent Multimodal Reinforcement Learning for Embedded Systems in Games, Natural Language Processing and Robotics. OSF Preprints. https://doi.org/10.31219/osf.io/sjrkh

References

See References.

Component files

Component page

Thanks to OSF (by the Center for Open Science), the project is temporarily hosted at:

• https://osf.io/fvndu/

Component DOI

Project identifier: https://doi.org/10.17605/OSF.IO/D2A5M

Component dependencies

This component depends on the following components of GUT-AI:

• NAS

Environment simulators

See Simulators.

Datasets

See Datasets.

Model Zoos

See Model Zoos.

Getting involved

• Community Discord for collaboration and discussion.

How to cite this

If you want to do so, feel free to cite this component in your publications:

@article{kourouklides2022mb,
  author = {Ioannis Kourouklides},
  journal = {OSF Preprints},
  title = {Memory Bottleneck},
  year = {2022},
  doi = {10.17605/osf.io/d2a5m},
  license = {Creative Commons Zero CC0 1.0}
}

License

Creative Commons Zero CC0 1.0 (Public Domain)