5 papers
Aliasing in Convnets: A Frame-Theoretic Perspective
Daniel Haider, Vincent Lostanlen, Martin Ehler +2
Using a stride in a convolutional layer inherently introduces aliasing, which has implications for numerical stability and statistical generalization. While techniques such as the…
ISAC: An Invertible and Stable Auditory Filter Bank with Customizable Kernels for ML Integration
Daniel Haider, Felix Perfler, Peter Balazs +2
This paper introduces ISAC, an invertible and stable, perceptually-motivated filter bank that is specifically designed to be integrated into machine learning paradigms. More precis…
(Almost) Smooth Sailing: Towards Numerical Stability of Neural Networks Through Differentiable Regularization of the Condition Number
Rossen Nenov, Daniel Haider, Peter Balazs
Maintaining numerical stability in machine learning models is crucial for their reliability and performance. One approach to maintain stability of a network layer is to integrate t…
Hold Me Tight: Stable Encoder-Decoder Design for Speech Enhancement
Daniel Haider, Felix Perfler, Vincent Lostanlen +2
Convolutional layers with 1-D filters are often used as frontend to encode audio signals. Unlike fixed time-frequency representations, they can adapt to the local characteristics o…
Injectivity of ReLU-layers: Tools from Frame Theory
Daniel Haider, Martin Ehler, Peter Balazs
Injectivity is the defining property of a mapping that ensures no information is lost and any input can be perfectly reconstructed from its output. By performing hard thresholding,…