Cover Image

Neural networks with trainable matrix activation functions

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Zhengqi, Cao, Shuhao, Li, Yuwen, Zikatanov, Ludmil
Format:	Preprint
Published:	2021
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Nodal auxiliary a posteriori error estimates
by: Li, Yuwen, et al.
Published: (2020)

Superconvergence in finite element method by smoothing
by: Li, Yuwen, et al.
Published: (2026)

Reduced Krylov Basis Methods for Parametric Partial Differential Equations
by: Li, Yuwen, et al.
Published: (2024)

A reduced conjugate gradient basis method for fractional diffusion
by: Li, Yuwen, et al.
Published: (2023)

Low Regularity Primal-Dual Weak Galerkin Finite Element Methods for Convection-Diffusion Equations
by: Wang, Chunmei, et al.
Published: (2019)

Multiscale lubrication simulation based on fourier feature networks with trainable frequency
by: Tang, Yihu, et al.
Published: (2024)

The boundary of neural network trainability is fractal
by: Sohl-Dickstein, Jascha
Published: (2024)

Hard constraint learning approaches with trainable influence functions for evolutionary equations
by: Zhang, Yushi, et al.
Published: (2025)

fKAN: Fractional Kolmogorov-Arnold Networks with trainable Jacobi basis functions
by: Aghaei, Alireza Afzal
Published: (2024)

A Mollification Approach to Ramified Transport and Tree Shape Optimization
by: Bressan, Alberto, et al.
Published: (2026)

QuasiNet: a neural network with trainable product layers
by: Malinovská, Kristína, et al.
Published: (2023)

Quantum automated learning with provable and explainable trainability
by: Ye, Qi, et al.
Published: (2025)

Some Super-approximation Rates of ReLU Neural Networks for Korobov Functions
by: Li, Yuwen, et al.
Published: (2025)

How to find expressible and trainable parameterized quantum circuits?
by: Röseler, Peter, et al.
Published: (2026)

On the relation between trainability and dequantization of variational quantum learning models
by: Gil-Fuster, Elies, et al.
Published: (2024)

Opening the Black Box: predicting the trainability of deep neural networks with reconstruction entropy
by: Thurn, Yanick, et al.
Published: (2024)

Complex fractal trainability boundary can arise from trivial non-convexity
by: Liu, Yizhou
Published: (2024)

Nonparametric learning of heterogeneous graphical model on network-linked data
by: Wang, Yuwen, et al.
Published: (2025)

Boolean matrix logic programming for active learning of gene functions in genome-scale metabolic network models
by: Ai, Lun, et al.
Published: (2024)

On the choice of the non-trainable internal weights in random feature maps
by: Mandal, Pinak, et al.
Published: (2024)

Weakly coupled systems of eikonal equations for autonomous vehicles
by: Chiri, Maria Teresa, et al.
Published: (2023)

On the power of graph neural networks and the role of the activation function
by: Khalife, Sammy, et al.
Published: (2023)

Inference of Utilities and Time Preference in Sequential Decision-Making
by: Cao, Haoyang, et al.
Published: (2024)

Finite-Sample Analysis of Nonlinear Independent Component Analysis:Sample Complexity and Identifiability Bounds
by: Jiang, Yuwen
Published: (2026)

Deep Hierarchical Graph Alignment Kernels
by: Tang, Shuhao, et al.
Published: (2024)

From GNNs to Trees: Multi-Granular Interpretability for Graph Neural Networks
by: Yang, Jie, et al.
Published: (2025)

VC dimension of Graph Neural Networks with Pfaffian activation functions
by: D'Inverno, Giuseppe Alessio, et al.
Published: (2024)

Risk-sensitive Markov Decision Process and Learning under General Utility Functions
by: Wu, Zhengqi, et al.
Published: (2023)

Federated Calculation of the Free-Support Transportation Barycenter by Single-Loop Dual Decomposition
by: Lin, Zhengqi, et al.
Published: (2025)

Nonlinear subspace clustering by functional link neural networks
by: Shi, Long, et al.
Published: (2024)

Mitigating spectral bias for the multiscale operator learning
by: Liu, Xinliang, et al.
Published: (2022)

Higher Order Approximation Rates for ReLU CNNs in Korobov Spaces
by: Li, Yuwen, et al.
Published: (2025)

LLMs Know When They Know, but Do Not Act on It: A Metacognitive Harness for Test-time Scaling
by: Cao, Qi, et al.
Published: (2026)

Unveiling Global Interactive Patterns across Graphs: Towards Interpretable Graph Neural Networks
by: Wang, Yuwen, et al.
Published: (2024)

KirchhoffNet: A Scalable Ultra Fast Analog Neural Network
by: Gao, Zhengqi, et al.
Published: (2023)

Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection Defense
by: Zhang, Shuhao, et al.
Published: (2026)

Stochastic Weight Sharing for Bayesian Neural Networks
by: Lin, Moule, et al.
Published: (2025)

Beyond Imbalance Ratio: Data Characteristics as Critical Moderators of Oversampling Method Selection
by: Jiang, Yuwen, et al.
Published: (2026)

An Information-Theoretic Criterion for Efficient Data Synthesis
by: Li, Hanyu, et al.
Published: (2026)

Leveraging Optimal Transport for Distributed Two-Sample Testing: An Integrated Transportation Distance-based Framework
by: Lin, Zhengqi, et al.
Published: (2025)