Image de couverture de livre

An accurate flatness measure to estimate the generalization performance of CNN models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Taleghani, Rahman, Mohammadi, Maryam, Marchetti, Francesco
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Computer Vision and Pattern Recognition Neural and Evolutionary Computing 68T07, 62M45, 65F30, 68T05, 49Q12
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Diffeomorphic Measure Matching with Kernels for Generative Modeling
par: Pandey, Biraj, et autres
Publié: (2024)

Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data
par: Kratsios, Anastasis, et autres
Publié: (2025)

NervePool: A Simplicial Pooling Layer
par: Scullen, Sarah McGuire, et autres
Publié: (2023)

Pointer Networks Trained Better via Evolutionary Algorithms
par: Zhong, Muyao, et autres
Publié: (2023)

Reconstructing shared dynamics with a deep neural network
par: Benkő, Zsigmond, et autres
Publié: (2021)

Fractional Artificial Neural Networks for Growth Models
par: Najera-Tinoco, Juan Carlos, et autres
Publié: (2025)

Neural Networks Trained by Weight Permutation are Universal Approximators
par: Cai, Yongqiang, et autres
Publié: (2024)

LayerAct: Advanced Activation Mechanism for Robust Inference of CNNs
par: Yoon, Kihyuk, et autres
Publié: (2023)

A quantum-inspired multi-level tensor-train monolithic space-time method for nonlinear PDEs
par: Rapaka, N. R., et autres
Publié: (2026)

Algorithmic Analysis of Dense Associative Memory: Finite-Size Guarantees and Adversarial Robustness
par: Gaikwad, Madhava
Publié: (2026)

OptiRoulette Optimizer: A New Stochastic Meta-Optimizer for up to 5.3x Faster Convergence
par: Mastromichalakis, Stamatis
Publié: (2026)

Error Bounds for Learning with Vector-Valued Random Features
par: Lanthaler, Samuel, et autres
Publié: (2023)

Greedy feature selection: Classifier-dependent feature selection via greedy methods
par: Camattari, Fabiana, et autres
Publié: (2024)

Quantifying The Limits of AI Reasoning: Systematic Neural Network Representations of Algorithms
par: Kratsios, Anastasis, et autres
Publié: (2025)

Composition of Relational Features with an Application to Explaining Black-Box Predictors
par: Srinivasan, Ashwin, et autres
Publié: (2022)

K-Means as a Radial Basis function Network: a Variational and Gradient-based Equivalence
par: Arredondo, Felipe de Jesus Felix, et autres
Publié: (2026)

A Plug-and-Play Method with Inpainting Network for Bayesian Uncertainty Quantification in Imaging
par: Wang, Xiaoyu, et autres
Publié: (2023)

Error analysis for empirical risk minimization over clipped ReLU networks in solving linear Kolmogorov partial differential equations
par: Xiao, Jichang, et autres
Publié: (2023)

A parametric activation function based on Wendland RBF
par: Darehmiraki, Majid
Publié: (2025)

Towards Understanding the Link Between Modularity and Performance in Neural Networks for Reinforcement Learning
par: Munn, Humphrey, et autres
Publié: (2022)

P1-KAN: an effective Kolmogorov-Arnold network with application to hydraulic valley optimization
par: Warin, Xavier
Publié: (2024)

One-Spike SNN: Single-Spike Phase Coding with Base Manipulation for ANN-to-SNN Conversion Loss Minimization
par: Hwang, Sangwoo, et autres
Publié: (2024)

Implementing Online Reinforcement Learning with Clustering Neural Networks
par: Smith, James E.
Publié: (2024)

Adjusting Dynamics of Hopfield Neural Network via Time-variant Stimulus
par: Peng, Xuenan, et autres
Publié: (2024)

Every Feedforward Neural Network Definable in an o-Minimal Structure Has Finite Sample Complexity
par: Kratsios, Anastasis, et autres
Publié: (2026)

Beyond LLMs, Sparse Distributed Memory, and Neuromorphics <A Hyper-Dimensional SRAM-CAM "VaCoAl" for Ultra-High Speed, Ultra-Low Power, and Low Cost>
par: Chuma, Hiroyuki, et autres
Publié: (2026)

The Trap of Presumed Equivalence: Artificial General Intelligence Should Not Be Assessed on the Scale of Human Intelligence
par: Dolgikh, Serge
Publié: (2024)

How many samples to label for an application given a foundation model? Chest X-ray classification study
par: Nechaev, Nikolay, et autres
Publié: (2025)

Adaptivity Under Realizability Constraints: Comparing In-Context and Agentic Learning
par: Kratsios, Anastasis, et autres
Publié: (2026)

Runtime Analyses of NSGA-III on Many-Objective Problems
par: Opris, Andre, et autres
Publié: (2024)

Achieving Tight $O(4^k)$ Runtime Bounds on Jump$_k$ by Proving that Genetic Algorithms Evolve Near-Maximal Population Diversity
par: Opris, Andre, et autres
Publié: (2024)

A First Runtime Analysis of the PAES-25: An Enhanced Variant of the Pareto Archived Evolution Strategy
par: Opris, Andre
Publié: (2025)

Towards a Rigorous Understanding of the Population Dynamics of the NSGA-III: Tight Runtime Bounds
par: Opris, Andre
Publié: (2025)

Higher-Order Transformer Derivative Estimates for Explicit Pathwise Learning Guarantees
par: Limmer, Yannick, et autres
Publié: (2024)

Transformers Can Solve Non-Linear and Non-Markovian Filtering Problems in Continuous Time For Conditionally Gaussian Signals
par: Horvath, Blanka, et autres
Publié: (2023)

Quantitative Convergence of Wasserstein Gradient Flows of Kernel Mean Discrepancies
par: Chizat, Lénaïc, et autres
Publié: (2026)

LieDetect: Detection of representation orbits of compact Lie groups from point clouds
par: Ennes, Henrique, et autres
Publié: (2023)

Spiking Sequence Machines and Transformers
par: Bose, Joy
Publié: (2026)

Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization
par: Kavun, Sergii
Publié: (2025)

Advanced Physics-Informed Neural Network with Residuals for Solving Complex Integral Equations
par: Moghaddam, Mahdi Movahedian, et autres
Publié: (2025)