A survey on modern trainable activation functions

2021/02/09 by Andrea Apicella, Francesco Donnarumma, Francesco Isgrò +1 · 15 citations
Computer Science · #Neural Networks and Applications #Machine Learning and Data Classification #Machine Learning and ELM

paper · doi:10.1016/j.neunet.2021.01.026

Citations

• Improving Deep Neural Networks with Probabilistic Maxout Units
• Gradient-based learning applied to document recognition
• The “independent components” of natural scenes are edge filters
• Multilayer feedforward networks are universal approximators
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

Cited by

• Self-Scalable Tanh (Stan): Multi-Scale Solutions for Physics-Informed Neural Networks
• Effect of the output activation function on the probabilities and errors in medical image segmentation
• SmartMixed: A Two-Phase Training Strategy for Adaptive Activation Function Learning in Neural Networks
• Controlling the image generation process with parametric activation functions
• Hybrid Ridgelet Deep Neural Networks for Data-Driven Arbitrage Strategies
• PO-CKAN:Physics Informed Deep Operator Kolmogorov Arnold Networks with Chunk Rational Structure
• Multi-Activation Hidden Units for Neural Networks with Random Weights
• Integral Signatures of Activation Functions: A 9-Dimensional Taxonomy and Stability Theory for Deep Learning
• Learning Polynomial Activation Functions for Deep Neural Networks
• BEKAN: Boundary condition-guaranteed evolutionary Kolmogorov-Arnold networks with radial basis functions for solving PDE problems
• A Bio-Inspired Minimal Model for Non-Stationary K-Armed Bandits
• Variational Autoencoders-based Detection of Extremes in Plant Productivity in an Earth System Model
• Jim137/qkan: v0.1.0
• Optimizing Neural Networks with Learnable Non-Linear Activation Functions via Lookup-Based FPGA Acceleration
• Human Body Weight Estimation Through Music-Induced Bed Vibrations
• HOTSPOT-YOLO: A Lightweight Deep Learning Attention-Driven Model for Detecting Thermal Anomalies in Drone-Based Solar Photovoltaic Inspections