Maximilian Dreyer's scientific contributions

Publications (3)

Preprint
The emerging field of eXplainable Artificial Intelligence (XAI) aims to bring transparency to today's powerful but opaque deep learning models. While local XAI methods explain individual predictions in form of attribution maps, thereby identifying where important features occur (but not providing information about what they represent), global expla...
Chapter
The remarkable success of deep neural networks (DNNs) in various applications is accompanied by a significant increase in network parameters and arithmetic operations. Such increases in memory and computational demands make deep learning prohibitive for resource-constrained hardware platforms such as mobile devices. Recent efforts aim to reduce the...
Preprint
Full-text available
The remarkable success of deep neural networks (DNNs) in various applications is accompanied by a significant increase in network parameters and arithmetic operations. Such increases in memory and computational demands make deep learning prohibitive for resource-constrained hardware platforms such as mobile devices. Recent efforts aim to reduce the...

Citations

... One such method is Layer-wise Relevance Propagation (LRP) [3], which assigns relevance scores to latent network structures through modified backpropagation. In the past, this information has been used to great success to efficiently reduce neural network complexity without sacrificing performance by [5,43]. ...