Live briefing
Everything about Activation function
Artificial neural network node function
In artificial neural networks, the activation function of a node is a function that calculates the output of the node based on its individual inputs and their weights. Nontrivial problems can be solved using only a few nodes if the activation function is nonlinear. Wikipedia →
🧭 Start here: a 6-step reading path
- Read the overview: Activation functionA 5-minute orientation
- Skim a recent paper: Activation functions in deep learning: A comprehensive survey and benchmarkInfluential work since 2022
- Pick up a classic book: Lectures on conditioned reflexesThe most-reprinted book on the subject
- Read the landmark paper: TGF-β Activation and Function in ImmunityCited 840 times
- Go sideways: Rectified linear unitA closely related topic
- Go sideways: Multilayer perceptronA closely related topic
📖 Definitions
Noun A function that defines the output of a particular node in an artificial neural network on the basis of its inputs.
🗂️ The subject at a glance
🏆 Landmark papers (most cited)
TGF-β Activation and Function in Immunity
IRF7: activation, regulation, modification and function
The inflammasomes: mechanisms of activation and function
Structure and function of transcriptional activation domains
Cocoa inhibits platelet activation and function
Interferon‐γ activation of polymorphonuclear neutrophil function
Mechanisms of androgen receptor activation and function
Neuronal Ca2+ stores: activation and function
🆕 Influential since 2022
Activation functions in deep learning: A comprehensive survey and benchmark
New insights into activation and function of the AMPK
Molecular determinants of complexin clamping and activation function
MicroRNAs in Macrophages: Regulators of Activation and Function
Chronic Activation of Tubulin Tyrosination Improves Heart Function
📚 Books worth reading
Lectures on conditioned reflexesIvan Petrovich Pavlov · 1928
Motor control and learningRichard A. Schmidt, Richard A. Schmidt · 1982
Hands-On Geometry (Kindergarten Through Grade Nine) (Kindergarten Through Grade Nine)Linda-Sue Brisby · 1989
Unicorns are realBarbara Meister Vitale · 1982
Developing Literacy Skills in the Early YearsHilary White · 2005
Frontier CollegeMarlene Pionteck · 1999- 📕African Peace MilitariesFrancis, David J. · 2017
- 📕Discrete-layer piezoelectric plate and shell models for active tip-clearance controlP. R. Heyliger · 1994
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
🔗 Related topics
- Rectified linear unit In the context of artificial neural networks, the rectifier or ReLU (rectified linear unit) activation function is an activation function defined as the…
- Multilayer perceptron In deep learning, a multilayer perceptron (MLP) is a kind of modern feedforward neural network consisting of fully connected neurons with nonlinear activation…
- Feedforward neural network A feedforward neural network is an artificial neural network in which information flows in a single direction – inputs are multiplied by weights to obtain…
- Weight initialization In deep learning, weight initialization or parameter initialization describes the initial step in creating a neural network. A neural network contains…
- Residual neural network A residual neural network (also referred to as a residual network or ResNet) is a deep learning architecture in which the layers learn residual functions…
- Universal approximation theorem In the field of machine learning, the universal approximation theorems (UATs) state that neural networks with a certain structure can, in principle, approximate…
- Quantum neural network Quantum neural networks (QNN) are computational neural network models which are based on the principles of quantum mechanics. The first ideas on quantum…
- Autoencoder An autoencoder is a type of artificial neural network used to learn efficient codings of unlabeled data (unsupervised learning). An autoencoder learns…