Dendritic Neuron Model and Its Capability of Approximation
- Resource Type
- Conference
- Authors
- Teng, Fei; Todo, Yuki
- Source
- 2019 6th International Conference on Systems and Informatics (ICSAI) Systems and Informatics (ICSAI), 2019 6th International Conference on. :542-546 Nov, 2019
- Subject
- Bioengineering
Communication, Networking and Broadcast Technologies
Computing and Processing
Engineered Materials, Dielectrics and Plasmas
General Topics for Engineers
Photonics and Electrooptics
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Neurons
Synapses
Computational modeling
Mathematical model
Brain modeling
Biological system modeling
Artificial neural networks
neuron
dendrite
dendritic neuron model
function approximation
sigmoid function
stone-weierstrass theorem
- Language
Recently, an artificial neural network (ANN) named dendritic neuron model has been proposed which mimics the nonlinear interaction in the signal processing in a neuron. in order to research the approximation performance of this model, this paper use the mathematical theory to prove that single dendritic neuron model neuron is able to approximate any Borel measurable function to any desired degree of accuracy.