Title:	On internal representations of random neural networks
DNr:	Berzelius-2024-259
Project Type:	LiU Berzelius
Principal Investigator:	Sebastian Mair <sebastian.mair@it.uu.se>
Affiliation:	Uppsala universitet
Duration:	2024-08-05 – 2025-03-01
Classification:	10201
Keywords:

Abstract

One of the long-standing challenges of learning representations with neural networks is to efficiently leverage information from a few examples out of a massive data set to learn useful representations (https://arxiv.org/abs/2304.02549) with a significantly smaller computational budget. Another recent work of us (https://arxiv.org/abs/2406.04933) shows that a decent segmentation map can be extracted from a model pre-trained for classification and not segmentation. Those promising preliminary results suggest the possibility of extracting a segmentation map from an untrained neural networks. In this project, we want to investigate the random initialization of neural networks that lead to a more data-efficient learning while being useful for downstream tasks such as image segmentation.