From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networks

arXiv:2310.11884v2 Announce Type: replace-cross
Abstract: In this paper, we review recent approaches for explaining concepts in neural networks. Concepts can act as a natural link between learning and reasoning: once the concepts are identified that a neural learning system uses, one can integrate those concepts with a reasoning system for inference or use a reasoning system to act upon them to improve or enhance the learning system. On the other hand, knowledge can not only be extracted from neural networks …

abstract act arxiv concepts cs.ai cs.cl cs.cv cs.lg cs.ne natural networks neural networks paper reasoning review survey type