Copertina

Developing Training Procedures for Piecewise-linear Spline Activation Functions in Neural Networks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Patty, William H
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Piecewise Constant Spectral Graph Neural Network
di: Martirosyan, Vahan, et al.
Pubblicazione: (2025)

Building Hybrid B-Spline And Neural Network Operators
di: Romagnoli, Raffaele, et al.
Pubblicazione: (2024)

SmartMixed: A Two-Phase Training Strategy for Adaptive Activation Function Learning in Neural Networks
di: Omidvar, Amin
Pubblicazione: (2025)

On the Expressive Power of Transformers for Maxout Networks and Continuous Piecewise Linear Functions
di: Gu, Linyan, et al.
Pubblicazione: (2026)

Max-Affine Spline Insights Into Deep Network Pruning
di: You, Haoran, et al.
Pubblicazione: (2021)

Detection Augmented Bandit Procedures for Piecewise Stationary MABs: A Modular Approach
di: Huang, Yu-Han, et al.
Pubblicazione: (2025)

Relating Piecewise Linear Kolmogorov Arnold Networks to ReLU Networks
di: Schoots, Nandi, et al.
Pubblicazione: (2025)

Global Convergence in Neural ODEs: Impact of Activation Functions
di: Gao, Tianxiang, et al.
Pubblicazione: (2025)

Ray-Tracing for Conditionally Activated Neural Networks
di: Gallicchio, Claudio, et al.
Pubblicazione: (2025)

Efficient Neural Networks with Discrete Cosine Transform Activations
di: Martinez-Gost, Marc, et al.
Pubblicazione: (2025)

Learning from Historical Activations in Graph Neural Networks
di: Galron, Yaniv, et al.
Pubblicazione: (2026)

APEX: Probing Neural Networks via Activation Perturbation
di: Ren, Tao, et al.
Pubblicazione: (2026)

Breaking the Conventional Forward-Backward Tie in Neural Networks: Activation Functions
di: Troiano, Luigi, et al.
Pubblicazione: (2025)

Z-Error Loss for Training Neural Networks
di: Godin, Guillaume
Pubblicazione: (2025)

Energy Consumption in Parallel Neural Network Training
di: Huber, Philipp, et al.
Pubblicazione: (2025)

Continuity, Piecewise Corrections, and Functor Models in Function-Based Learning
di: Harby, John
Pubblicazione: (2026)

Training Neural Networks for Modularity aids Interpretability
di: Golechha, Satvik, et al.
Pubblicazione: (2024)

Automatic Stability and Recovery for Neural Network Training
di: Or, Barak
Pubblicazione: (2026)

Gradient-Free Training of Quantized Neural Networks
di: Cohen, Noa, et al.
Pubblicazione: (2024)

LLM Unlearning via Neural Activation Redirection
di: Shen, William F., et al.
Pubblicazione: (2025)

On the (Non) Injectivity of Piecewise Linear Janossy Pooling
di: Reshef, Ilai, et al.
Pubblicazione: (2025)

Robust Basis Spline Decoupling for the Compression of Transformer Models
di: De Jonghe, Joppe, et al.
Pubblicazione: (2026)

Probing Graph Neural Network Activation Patterns Through Graph Topology
di: Tori, Floriano, et al.
Pubblicazione: (2026)

Dynamic Spectral Backpropagation for Efficient Neural Network Training
di: Muthuraman, Mannmohan
Pubblicazione: (2025)

ROOT: Robust Orthogonalized Optimizer for Neural Network Training
di: He, Wei, et al.
Pubblicazione: (2025)

Harnessing Orthogonality to Train Low-Rank Neural Networks
di: Coquelin, Daniel, et al.
Pubblicazione: (2024)

Explaining Neural Networks without Access to Training Data
di: Marton, Sascha, et al.
Pubblicazione: (2022)

Verification of Geometric Robustness of Neural Networks via Piecewise Linear Approximation and Lipschitz Optimisation
di: Batten, Ben, et al.
Pubblicazione: (2024)

ss-Mamba: Semantic-Spline Selective State-Space Model
di: Ye, Zuochen
Pubblicazione: (2025)

Massive Activations in Graph Neural Networks: Decoding Attention for Domain-Dependent Interpretability
di: Bini, Lorenzo, et al.
Pubblicazione: (2024)

Emergence of Globally Attracting Fixed Points in Deep Neural Networks With Nonlinear Activations
di: Joudaki, Amir, et al.
Pubblicazione: (2024)

The Spectral Bias of Shallow Neural Network Learning is Shaped by the Choice of Non-linearity
di: Sahs, Justin, et al.
Pubblicazione: (2025)

On the Rate of Convergence of GD in Non-linear Neural Networks: An Adversarial Robustness Perspective
di: Smorodinsky, Guy, et al.
Pubblicazione: (2026)

Toward Improving fNIRS Classification: A Study on Activation Functions in Deep Neural Architectures
di: Adeli, Behtom, et al.
Pubblicazione: (2025)

Mining Generalizable Activation Functions
di: Vitvitskyi, Alex, et al.
Pubblicazione: (2026)

Fast Training of Recurrent Neural Networks with Stationary State Feedbacks
di: Caillon, Paul, et al.
Pubblicazione: (2025)

No Prior, No Leakage: Revisiting Reconstruction Attacks in Trained Neural Networks
di: Refael, Yehonatan, et al.
Pubblicazione: (2025)

Feed-Forward Optimization With Delayed Feedback for Neural Network Training
di: Flügel, Katharina, et al.
Pubblicazione: (2023)

Training-free Graph Neural Networks and the Power of Labels as Features
di: Sato, Ryoma
Pubblicazione: (2024)

Improved Training of Physics-Informed Neural Networks with Model Ensembles
di: Haitsiukevich, Katsiaryna, et al.
Pubblicazione: (2022)