4 papers
Critical initialization destabilizes higher input derivatives in wide scalar-input networks
Prashant Singh, Pranav Singh
The edge-of-chaos condition preserves first-order input perturbations in wide randomly initialized networks, but physics-informed losses, score matching and derivative regularizati…
Leveraging Language Prior for Infrared Small Target Detection
Pranav Singh, Pravendra Singh
IRSTD (InfraRed Small Target Detection) detects small targets in infrared blurry backgrounds and is essential for various applications. The detection task is challenging due to the…
Adaptive higher order reversible integrators for memory efficient deep learning
Sofya Maslovskaya, Sina Ober-Blöbaum, Christian Offen +2
The depth of networks plays a crucial role in the effectiveness of deep learning. However, the memory requirement for backpropagation scales linearly with the number of layers, whi…
Commutator-free Cayley methods
Boris Wembe, Christian Offen, Sofya Maslovskaya +2
Differential equations posed on quadratic matrix Lie groups arise in the context of classical mechanics and quantum dynamical systems. Lie group numerical integrators preserve the…