Copertina

Approximation Capabilities of Feedforward Neural Networks with GELU Activations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yakovlev, Konstantin, Puchkin, Nikita
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Simultaneous Approximation of the Score Function and Its Derivatives by Deep Neural Networks
di: Yakovlev, Konstantin, et al.
Pubblicazione: (2025)

Generalization error bound for denoising score matching under relaxed manifold assumption
di: Yakovlev, Konstantin, et al.
Pubblicazione: (2025)

Implicit score matching meets denoising score matching: improved rates of convergence and log-density Hessian estimation
di: Yakovlev, Konstantin, et al.
Pubblicazione: (2025)

Noise-contrastive Online Change Point Detection
di: Puchkin, Nikita, et al.
Pubblicazione: (2022)

Score-based change point detection via tracking the best of infinitely many experts
di: Markovich, Anna, et al.
Pubblicazione: (2024)

Activation Functions for "A Feedforward Unitary Equivariant Neural Network"
di: Ma, Pui-Wai
Pubblicazione: (2024)

Dimension-free bounds in high-dimensional linear regression via error-in-operator approach
di: Noskov, Fedor, et al.
Pubblicazione: (2025)

Towards Arbitrary QUBO Optimization: Analysis of Classical and Quantum-Activated Feedforward Neural Networks
di: Lai, Chia-Tso, et al.
Pubblicazione: (2024)

Tight Bounds for Schrödinger Potential Estimation in Unpaired Data Translation
di: Puchkin, Nikita, et al.
Pubblicazione: (2025)

Training Feedforward Neural Networks with Bayesian Hyper-Heuristics
di: Schreuder, Arné, et al.
Pubblicazione: (2023)

Schrödinger bridge problem via empirical risk minimization
di: Belomestny, Denis, et al.
Pubblicazione: (2026)

Zorro: A Flexible and Differentiable Parametric Family of Activation Functions That Extends ReLU and GELU
di: Roodschild, Matias, et al.
Pubblicazione: (2024)

NIDS Neural Networks Using Sliding Time Window Data Processing with Trainable Activations and its Generalization Capability
di: Raskovalov, Anton, et al.
Pubblicazione: (2024)

SG-Blend: Learning an Interpolation Between Improved Swish and GELU for Robust Neural Representations
di: Sarkar, Gaurav, et al.
Pubblicazione: (2025)

Optimizing Performance of Feedforward and Convolutional Neural Networks through Dynamic Activation Functions
di: Rane, Chinmay, et al.
Pubblicazione: (2023)

Reusing Softmax Hardware Unit for GELU Computation in Transformers
di: Peltekis, Christodoulos, et al.
Pubblicazione: (2024)

$λ$-GELU: Learning Gating Hardness for Controlled ReLU-ization in Deep Networks
di: Pérez-Corral, Cristian, et al.
Pubblicazione: (2026)

Rates of convergence for density estimation with generative adversarial networks
di: Puchkin, Nikita, et al.
Pubblicazione: (2021)

Breaking the Heavy-Tailed Noise Barrier in Stochastic Optimization Problems
di: Puchkin, Nikita, et al.
Pubblicazione: (2023)

Adaptive Feedforward Gradient Estimation in Neural ODEs
di: Dabounou, Jaouad
Pubblicazione: (2024)

Compression Repair for Feedforward Neural Networks Based on Model Equivalence Evaluation
di: Mo, Zihao, et al.
Pubblicazione: (2024)

The Complexity of Verifying Feedforward Neural Networks in Quantised Settings
di: Alsmann, Eric, et al.
Pubblicazione: (2026)

An Adversarial Example for Direct Logit Attribution: Memory Management in GELU-4L
di: Janiak, Jett, et al.
Pubblicazione: (2023)

Sample complexity of Schrödinger potential estimation
di: Puchkin, Nikita, et al.
Pubblicazione: (2025)

Deriving Equivalent Symbol-Based Decision Models from Feedforward Neural Networks
di: Seidel, Sebastian, et al.
Pubblicazione: (2025)

UPath: Universal Planner Across Topological Heterogeneity For Grid-Based Pathfinding
di: Ananikian, Aleksandr, et al.
Pubblicazione: (2026)

Hyper-Representations: Learning from Populations of Neural Networks
di: Schürholt, Konstantin
Pubblicazione: (2024)

Controlled Langevin Dynamics for Sampling of Feedforward Neural Networks Trained with Minibatches
di: Zambon, Alessandro, et al.
Pubblicazione: (2026)

Probabilistic Classification and Uncertainty Quantification of Sahara Desert Climate Using Feedforward Neural Networks
di: Tivenan, Stephen, et al.
Pubblicazione: (2026)

Unification of Symmetries Inside Neural Networks: Transformer, Feedforward and Neural ODE
di: Hashimoto, Koji, et al.
Pubblicazione: (2024)

Inheritance Between Feedforward and Convolutional Networks via Model Projection
di: Ewen, Nicolas, et al.
Pubblicazione: (2026)

More Expressive Feedforward Layers: Part I. Token-Adaptive Mixing of Activations
di: Wang, Mingze, et al.
Pubblicazione: (2026)

Eventizing Traditionally Opaque Binary Neural Networks as 1-safe Petri net Models
di: Tarraf, Mohamed, et al.
Pubblicazione: (2026)

A Statistical-Modelling Approach to Feedforward Neural Network Model Selection
di: McInerney, Andrew, et al.
Pubblicazione: (2022)

Safe Policy Exploration Improvement via Subgoals
di: Angulo, Brian, et al.
Pubblicazione: (2024)

RISC-V RVV efficiency for ANN algorithms
di: Rumyantsev, Konstantin, et al.
Pubblicazione: (2024)

Symbolic Feedforward Networks for Probabilistic Finite Automata: Exact Simulation and Learnability
di: Dhayalkar, Sahil Rajesh
Pubblicazione: (2025)

Predictive Coding Graphs are a Superset of Feedforward Neural Networks
di: van Zwol, Björn
Pubblicazione: (2026)

Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations
di: Sartor, Davide, et al.
Pubblicazione: (2025)

Semiring Activation in Neural Networks
di: Smets, Bart M. N., et al.
Pubblicazione: (2024)