Simon Heilig
YOU?
Author Swipe
View article: Towards an Optimal Control Perspective of ResNet Training
Towards an Optimal Control Perspective of ResNet Training Open
We propose a training formulation for ResNets reflecting an optimal control problem that is applicable for standard architectures and general loss functions. We suggest bridging both worlds via penalizing intermediate outputs of hidden sta…
View article: Port-Hamiltonian Architectural Bias for Long-Range Propagation in Deep Graph Networks
Port-Hamiltonian Architectural Bias for Long-Range Propagation in Deep Graph Networks Open
The dynamics of information diffusion within graphs is a critical open issue that heavily influences graph representation learning, especially when considering long-range propagation. This calls for principled approaches that control and r…
View article: Adaptive multi-modal positive semi-definite and indefinite kernel fusion for binary classification
Adaptive multi-modal positive semi-definite and indefinite kernel fusion for binary classification Open
Data and information are nowadays frequently available in multiple modalities like different sensor signals, textual descriptions, graph structures, and other formats.The maximum information from these heterogeneous representations can be …
View article: Revisiting Memory Efficient Kernel Approximation: An Indefinite Learning Perspective
Revisiting Memory Efficient Kernel Approximation: An Indefinite Learning Perspective Open
Matrix approximations are a key element in large-scale algebraic machine learning approaches. The recently proposed method MEKA (Si et al., 2014) effectively employs two common assumptions in Hilbert spaces: the low-rank property of an inn…
View article: Scalable embedding of multiple perspectives for indefinite life-science data analysis
Scalable embedding of multiple perspectives for indefinite life-science data analysis Open
Life science data analysis frequently encounters particular challenges that cannot be solved with classical techniques from data analytics or machine learning domains. The complex inherent structure of the data and especially the encoding …
View article: Multi-perspective embedding for non-metric time series classification
Multi-perspective embedding for non-metric time series classification Open
The interest in time series analysis is rapidly increasing, providing new challenges for machine learning. Over many decades, Dynamic Time Warping (DTW) is referred to as the de facto standard distance measure for time series and the tool …