Rethinking lipschitz neural networks and certified robustness: A boolean function perspective
Designing neural networks with bounded Lipschitz constant is a promising way to obtain
certifiably robust classifiers against adversarial examples. However, the relevant progress …
certifiably robust classifiers against adversarial examples. However, the relevant progress …
fkan: Fractional kolmogorov-arnold networks with trainable jacobi basis functions
AA Aghaei - Neurocomputing, 2025 - Elsevier
Recent advancements in neural network design have given rise to the development of
Kolmogorov-Arnold Networks (KANs), which enhance interpretability and precision of these …
Kolmogorov-Arnold Networks (KANs), which enhance interpretability and precision of these …
Three Decades of Activations: A Comprehensive Survey of 400 Activation Functions for Neural Networks
V Kunc, J Kléma - ar**s. Specifically, they partition the input domain into regions on which the …
[PDF][PDF] A neural-network-based convex regularizer for image reconstruction
The emergence of deep-learning-based methods for solving inverse problems has enabled
a significant increase in reconstruction quality. Unfortunately, these new methods often lack …
a significant increase in reconstruction quality. Unfortunately, these new methods often lack …
Provably convergent plug-and-play quasi-Newton methods
Plug-and-Play (PnP) methods are a class of efficient iterative methods that aim to combine
data fidelity terms and deep denoisers using classical optimization algorithms, such as ISTA …
data fidelity terms and deep denoisers using classical optimization algorithms, such as ISTA …
Compact: Approximating complex activation functions for secure computation
Secure multi-party computation (MPC) techniques can be used to provide data privacy when
users query deep neural network (DNN) models hosted on a public cloud. State-of-the-art …
users query deep neural network (DNN) models hosted on a public cloud. State-of-the-art …