Image de couverture de livre

A Significantly Better Class of Activation Functions Than ReLU Like Activation Functions

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Noel, Mathew Mithra, Oswal, Yug
Format:	Preprint
Publié:	2024
Sujets:	Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Neural and Evolutionary Computing 68T07
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Efficient Vectorized Backpropagation Algorithms for Training Feedforward Networks Composed of Quadratic Neurons
par: Noel, Mathew Mithra, et autres
Publié: (2023)

Alternate Loss Functions for Classification and Robust Regression Can Improve the Accuracy of Artificial Neural Networks
par: Noel, Mathew Mithra, et autres
Publié: (2023)

Planarian Neural Networks: Evolutionary Patterns from Basic Bilateria Shaping Modern Artificial Neural Network Architectures
par: Huang, Ziyuan, et autres
Publié: (2025)

Proximity-Based Evidence Retrieval for Uncertainty-Aware Neural Networks
par: Gharoun, Hassan, et autres
Publié: (2025)

Growing Cosine Unit: A Novel Oscillatory Activation Function That Can Speedup Training and Reduce Parameters in Convolutional Neural Networks
par: Noel, Mathew Mithra, et autres
Publié: (2021)

SoftReMish: A Novel Activation Function for Enhanced Convolutional Neural Networks for Visual Recognition Performance
par: Gücen, Mustafa Bayram
Publié: (2025)

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

APTx: better activation function than MISH, SWISH, and ReLU's variants used in deep learning
par: Kumar, Ravin
Publié: (2022)

Efficient Approximation to Analytic and $L^p$ functions by Height-Augmented ReLU Networks
par: Li, ZeYu, et autres
Publié: (2026)

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

NACHOS: Neural Architecture Search for Hardware Constrained Early Exit Neural Networks
par: Gambella, Matteo, et autres
Publié: (2024)

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

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

Deep Learning using Rectified Linear Units (ReLU)
par: Agarap, Abien Fred
Publié: (2018)

The Geometry of ReLU Networks through the ReLU Transition Graph
par: Dhayalkar, Sahil Rajesh
Publié: (2025)

On the Principles of ReLU Networks with One Hidden Layer
par: Huang, Changcun
Publié: (2024)

CLEAR: Cue Learning using Evolution for Accurate Recognition Applied to Sustainability Data Extraction
par: Bentley, Peter J., et autres
Publié: (2025)

Uncertainty-Aware Post-Hoc Calibration: Mitigating Confidently Incorrect Predictions Beyond Calibration Metrics
par: Gharoun, Hassan, et autres
Publié: (2025)

Unveiling the frontiers of deep learning: innovations shaping diverse domains
par: Ahmed, Shams Forruque, et autres
Publié: (2023)

From Embeddings to Equations: Genetic-Programming Surrogates for Interpretable Transformer Classification
par: Khorshidi, Mohammad Sadegh, et autres
Publié: (2025)

Nonlinearity Enhanced Adaptive Activation Functions
par: Yevick, David
Publié: (2024)

Learning Morphisms with Gauss-Newton Approximation for Growing Networks
par: Lawton, Neal, et autres
Publié: (2024)

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)

Dynamic Activation with Knowledge Distillation for Energy-Efficient Spiking NN Ensembles
par: Konstantaropoulos, Orestis, et autres
Publié: (2025)

APTx Neuron: A Unified Trainable Neuron Architecture Integrating Activation and Computation
par: Kumar, Ravin
Publié: (2025)

Zorro: A Flexible and Differentiable Parametric Family of Activation Functions That Extends ReLU and GELU
par: Roodschild, Matias, et autres
Publié: (2024)

HERCULES: Hardware-Efficient, Robust, Continual Learning Neural Architecture Search
par: Gambella, Matteo, et autres
Publié: (2026)

Improving Quaternion Neural Networks with Quaternionic Activation Functions
par: Pöppelbaum, Johannes, et autres
Publié: (2024)

Tangma: A Tanh-Guided Activation Function with Learnable Parameters
par: Golwala, Shreel
Publié: (2025)

Exploring the Intersection between Neural Architecture Search and Continual Learning
par: Shahawy, Mohamed, et autres
Publié: (2022)

Fast Data Aware Neural Architecture Search via Supernet Accelerated Evaluation
par: Njor, Emil, et autres
Publié: (2025)

Regularizing Differentiable Architecture Search with Smooth Activation
par: Zhou, Yanlin, et autres
Publié: (2025)

ElegansNet: a brief scientific report and initial experiments
par: Bardozzo, Francesco, et autres
Publié: (2023)

From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networks
par: Lee, Jae Hee, et autres
Publié: (2023)

Fast and Efficient Local Search for Genetic Programming Based Loss Function Learning
par: Raymond, Christian, et autres
Publié: (2024)

When Person Re-Identification Meets Event Camera: A Benchmark Dataset and An Attribute-guided Re-Identification Framework
par: Wang, Xiao, et autres
Publié: (2025)

Noise-Tolerant Coreset-Based Class Incremental Continual Learning
par: Mucllari, Edison, et autres
Publié: (2025)

Task-Specific Activation Functions for Neuroevolution using Grammatical Evolution
par: Winter, Benjamin David, et autres
Publié: (2025)

Biologically Inspired Oscillating Activation Functions Can Bridge the Performance Gap between Biological and Artificial Neurons
par: Noel, Matthew Mithra, et autres
Publié: (2021)