Doctoral colloquium - Matej Fandl (16.10.2023)

Monday 16.10.2023 at 13:10, Lecture room I/9

11. 10. 2023 14.02 hod.
Od: Damas Gruska

Matej Fandl:
Retrieving memories from meta-stable states of continuous modern Hopfield networks

Abstract:
Continuous modern Hopfield networks are a model of associative memory with large storage capacity. They can be used both as a component in deep learning architectures and as a standalone component for pattern completion and denoisifying. Our work is aimed at improving the training method of these methods by using competition to achieve distributed representations of training patterns and their effective storage in meta-stable states.