Image de couverture de livre

Analytical Solution of a Three-layer Network with a Matrix Exponential Activation Function

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gai, Kuo, Zhang, Shihua
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

OTAD: An Optimal Transport-Induced Robust Model for Agnostic Adversarial Attack
par: Gai, Kuo, et autres
Publié: (2024)

Progressive Feedforward Collapse of ResNet Training
par: Wang, Sicong, et autres
Publié: (2024)

Feature Dynamics as Implicit Data Augmentation: A Depth-Decomposed View on Deep Neural Network Generalization
par: Ruan, Tianyu, et autres
Publié: (2025)

An Analytic Solution to Covariance Propagation in Neural Networks
par: Wright, Oren, et autres
Publié: (2024)

REAct: Rational Exponential Activation for Better Learning and Generalization in PINNs
par: Mishra, Sourav, et autres
Publié: (2025)

Sparse-Aware Neural Networks for Nonlinear Functionals: Mitigating the Exponential Dependence on Dimension
par: Li, Jianfei, et autres
Publié: (2026)

Developing Training Procedures for Piecewise-linear Spline Activation Functions in Neural Networks
par: Patty, William H
Publié: (2025)

Mining Generalizable Activation Functions
par: Vitvitskyi, Alex, et autres
Publié: (2026)

Analytical FFN-to-MoE Restructuring via Activation Pattern Analysis
par: Pei, Zehua, et autres
Publié: (2025)

Compressing Neural Networks Using Tensor Networks with Exponentially Fewer Variational Parameters
par: Qing, Yong, et autres
Publié: (2023)

Three Mechanisms of Feature Learning in a Linear Network
par: Xu, Yizhou, et autres
Publié: (2024)

Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) for Exponential Compression of Deep Neural Networks
par: Cichocki, Andrzej, et autres
Publié: (2026)

ANAct: Adaptive Normalization for Activation Functions
par: Peiwen, Yuan, et autres
Publié: (2022)

Polynomial Precision Dependence Solutions to Alignment Research Center Matrix Completion Problems
par: Angell, Rico
Publié: (2024)

MetaSymNet: A Tree-like Symbol Network with Adaptive Architecture and Activation Functions
par: Li, Yanjie, et autres
Publié: (2023)

The Hidden Power of Normalization Layers in Neural Networks: Exponential Capacity Control
par: Than, Khoat
Publié: (2025)

Preserving Bilinear Weight Spectra with a Signed and Shrunk Quadratic Activation Function
par: Abohwo, Jason, et autres
Publié: (2025)

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

A Method on Searching Better Activation Functions
par: Sun, Haoyuan, et autres
Publié: (2024)

ScoresActivation: A New Activation Function for Model Agnostic Global Explainability by Design
par: Covaci, Emanuel, et autres
Publié: (2025)

CauchyNet: Compact and Data-Efficient Learning using Holomorphic Activation Functions
par: Zhang, Hong-Kun, et autres
Publié: (2025)

Efficient Search for Customized Activation Functions with Gradient Descent
par: Strack, Lukas, et autres
Publié: (2024)

Global Convergence in Neural ODEs: Impact of Activation Functions
par: Gao, Tianxiang, et autres
Publié: (2025)

Do Deep Neural Network Solutions Form a Star Domain?
par: Sonthalia, Ankit, et autres
Publié: (2024)

Deciphering Shortcut Learning from an Evolutionary Game Theory Perspective
par: Li, Xiayang, et autres
Publié: (2026)

On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD
par: Zhang, Tongcheng, et autres
Publié: (2026)

Tensor and Matrix Low-Rank Value-Function Approximation in Reinforcement Learning
par: Rozada, Sergio, et autres
Publié: (2022)

Super Level Sets and Exponential Decay: A Synergistic Approach to Stable Neural Network Training
par: Chaudhary, Jatin, et autres
Publié: (2024)

Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During Training
par: Milkert, Max, et autres
Publié: (2023)

ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs
par: Zhang, Zhengyan, et autres
Publié: (2024)

ControlSynth Neural ODEs: Modeling Dynamical Systems with Guaranteed Convergence
par: Mei, Wenjie, et autres
Publié: (2024)

Ray-Tracing for Conditionally Activated Neural Networks
par: Gallicchio, Claudio, et autres
Publié: (2025)

TQL: Scaling Q-Functions with Transformers by Preventing Attention Collapse
par: Dong, Perry, et autres
Publié: (2026)

Learning from Historical Activations in Graph Neural Networks
par: Galron, Yaniv, et autres
Publié: (2026)

Tracing the Path to Grokking: Embeddings, Dropout, and Network Activation
par: Salah, Ahmed, et autres
Publié: (2025)

Efficient Neural Networks with Discrete Cosine Transform Activations
par: Martinez-Gost, Marc, et autres
Publié: (2025)

APEX: Probing Neural Networks via Activation Perturbation
par: Ren, Tao, et autres
Publié: (2026)

Structured vs. Unstructured Pruning: An Exponential Gap
par: Ferre', Davide, et autres
Publié: (2026)

The Weight Gram Matrix Captures Sequential Feature Linearization in Deep Networks
par: Cha, Taehun, et autres
Publié: (2026)

A Characterization Theorem for Equivariant Networks with Point-wise Activations
par: Pacini, Marco, et autres
Publié: (2024)