Cover Image

Integral Signatures of Activation Functions: A 9-Dimensional Taxonomy and Stability Theory for Deep Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mali, Ankur, Hall, Lawrence, Williams, Jake, Richards, Gordon
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

TeLU Activation Function for Fast and Stable Deep Learning
by: Fernandez, Alfredo, et al.
Published: (2024)

Tight Stability, Convergence, and Robustness Bounds for Predictive Coding Networks
by: Mali, Ankur, et al.
Published: (2024)

Curvature-Weighted Capacity Allocation: A Minimum Description Length Framework for Layer-Adaptive Large Language Model Optimization
by: Amaefuna, Theophilus, et al.
Published: (2026)

The Role of Inherent Bellman Error in Offline Reinforcement Learning with Linear Function Approximation
by: Golowich, Noah, et al.
Published: (2024)

Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances
by: Chrysomallis, Iason, et al.
Published: (2025)

Automated Discovery of Integral with Deep Learning
by: Yin, Xiaoxin
Published: (2024)

Deep Configuration Performance Learning: A Systematic Survey and Taxonomy
by: Gong, Jingzhi, et al.
Published: (2024)

A Survey of Deep Learning: From Activations to Transformers
by: Schneider, Johannes, et al.
Published: (2023)

Deep Learning for Cross-Domain Data Fusion in Urban Computing: Taxonomy, Advances, and Outlook
by: Zou, Xingchen, et al.
Published: (2024)

The Alignment Problem from a Deep Learning Perspective
by: Ngo, Richard, et al.
Published: (2022)

Mathematical Models of Computation in Superposition
by: Hänni, Kaarel, et al.
Published: (2024)

Linear Bellman Completeness Suffices for Efficient Online Reinforcement Learning with Few Actions
by: Golowich, Noah, et al.
Published: (2024)

Towards One Model for Classical Dimensionality Reduction: A Probabilistic Perspective on UMAP and t-SNE
by: Ravuri, Aditya, et al.
Published: (2024)

Deep Learning for Modeling and Dispatching Hybrid Wind Farm Power Generation
by: Lawrence, Zach, et al.
Published: (2025)

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

Geometry of Drifting MDPs with Path-Integral Stability Certificates
by: Zhang, Zuyuan, et al.
Published: (2026)

AUDRON: A Deep Learning Framework with Fused Acoustic Signatures for Drone Type Recognition
by: Chatterjee, Rajdeep, et al.
Published: (2025)

Pivoting Retail Supply Chain with Deep Generative Techniques: Taxonomy, Survey and Insights
by: Wang, Yuan, et al.
Published: (2024)

Diffusion Models for Reinforcement Learning: Foundations, Taxonomy, and Development
by: Xu, Changfu, et al.
Published: (2025)

Mining Generalizable Activation Functions
by: Vitvitskyi, Alex, et al.
Published: (2026)

A Method on Searching Better Activation Functions
by: Sun, Haoyuan, et al.
Published: (2024)

A Functional Perspective on Knowledge Distillation in Neural Networks
by: Mason-Williams, Israel, et al.
Published: (2025)

Position: A Theory of Deep Learning Must Include Compositional Sparsity
by: Danhofer, David A., et al.
Published: (2025)

ScoresActivation: A New Activation Function for Model Agnostic Global Explainability by Design
by: Covaci, Emanuel, et al.
Published: (2025)

Clustering-Based Weight Orthogonalization for Stabilizing Deep Reinforcement Learning
by: Ma, Guoqing, et al.
Published: (2025)

VecCity: A Taxonomy-guided Library for Map Entity Representation Learning
by: Zhang, Wentao, et al.
Published: (2024)

Stable and Robust Deep Learning By Hyperbolic Tangent Exponential Linear Unit (TeLU)
by: Fernandez, Alfredo, et al.
Published: (2024)

A Benchmark for Maximum Cut: Towards Standardization of the Evaluation of Learned Heuristics for Combinatorial Optimization
by: Nath, Ankur, et al.
Published: (2024)

CauchyNet: Compact and Data-Efficient Learning using Holomorphic Activation Functions
by: Zhang, Hong-Kun, et al.
Published: (2025)

ANAct: Adaptive Normalization for Activation Functions
by: Peiwen, Yuan, et al.
Published: (2022)

SineLoRA$Δ$: Sine-Activated Delta Compression
by: Gordon, Cameron, et al.
Published: (2025)

Enabling Off-Policy Imitation Learning with Deep Actor Critic Stabilization
by: Sen, Sayambhu, et al.
Published: (2025)

Neuron-level Balance between Stability and Plasticity in Deep Reinforcement Learning
by: Lan, Jiahua, et al.
Published: (2025)

Co-Activation Graph Analysis of Safety-Verified and Explainable Deep Reinforcement Learning Policies
by: Gross, Dennis, et al.
Published: (2025)

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

Adaptive MSD-Splitting: Enhancing C4.5 and Random Forests for Skewed Continuous Attributes
by: Lee, Jake
Published: (2026)

STORI: A Benchmark and Taxonomy for Stochastic Environments
by: Barsainyan, Aryan Amit, et al.
Published: (2025)

Generalized Regularized Evidential Deep Learning Models: Theory and Comprehensive Evaluation
by: Pandey, Deep Shankar, et al.
Published: (2025)

A* Search Without Expansions: Learning Heuristic Functions with Deep Q-Networks
by: Agostinelli, Forest, et al.
Published: (2021)

Explorative Imitation Learning: A Path Signature Approach for Continuous Environments
by: Gavenski, Nathan, et al.
Published: (2024)