3 citations · 4 across the 7 of their papers we have counts for
5 papers · 1 filter
Smooth Model Compression without Fine-Tuning
Christina Runkel, Natacha Kuete Meli, Jovita Lukasik +3
Compressing and pruning large machine learning models has become a critical step towards their deployment in real-world applications. Standard pruning and compression techniques ar…
Training Data Reconstruction: Privacy due to Uncertainty?
Christina Runkel, Kanchana Vaishnavi Gandikota, Jonas Geiping +2
Being able to reconstruct training data from the parameters of a neural network is a major privacy concern. Previous works have shown that reconstructing training data, under certa…
Continuous Learned Primal Dual
Christina Runkel, Ander Biguri, Carola-Bibiane Schönlieb
Neural ordinary differential equations (Neural ODEs) propose the idea that a sequence of layers in a neural network is just a discretisation of an ODE, and thus can instead be dire…
Multi-Modal Hypergraph Diffusion Network with Dual Prior for Alzheimer Classification
Angelica I. Aviles-Rivero, Christina Runkel, Nicolas Papadakis +2
The automatic early diagnosis of prodromal stages of Alzheimer's disease is of great relevance for patient treatment to improve quality of life. We address this problem as a multi-…
Depthwise Separable Convolutions Allow for Fast and Memory-Efficient Spectral Normalization
Christina Runkel, Christian Etmann, Michael Möller +1
An increasing number of models require the control of the spectral norm of convolutional layers of a neural network. While there is an abundance of methods for estimating and enfor…