Related Experiment Video
Updated: Oct 16, 2025
06:08
Automatic Identification of Dendritic Branches and their Orientation
Published on: September 17, 2021
2.0K
Dendritic Computing: Branching Deeper into Machine Learning
Jyotibdha Acharya1, Arindam Basu2, Robert Legenstein3
1Institute of Infocomm Research, A*STAR, Singapore.
Neuroscience
|October 17, 2021
Summary
Dendrites in neurons offer significant nonlinear computational power, enhancing machine learning models by improving expressivity and enabling continual learning through various plasticity rules.
Area of Science:
- Neuroscience
- Artificial Intelligence
- Computational Neuroscience
Background:
- Biological neurons utilize dendritic nonlinearities for complex computations.
- Dendritic plasticity rules influence learning in biological systems.
- Computational models assess the impact of dendritic features on learning.
Purpose of the Study:
- To explore the nonlinear computational power of dendrites in biological and artificial neurons.
- To identify computational implications of dendritic nonlinearities and plasticity.
- To review applications of dendritic computations in machine learning classification tasks.
Main Methods:
- Review of biological evidence on dendritic nonlinearities and plasticity.
- Analysis of computational models demonstrating dendritic learning.
- Categorization of dendritic computation works based on plasticity methods (structural, weight, synaptic delay).
- Discussion of the integration of deep learning concepts with dendritic computations.
Main Results:
- Dendritic nonlinearities provide four key computational advantages: improved expressivity, resource efficiency, internal learning signals, and continual learning.
- Dendritic computations have been successfully applied to real-world classification problems using established machine learning datasets.
- Works are classified based on plasticity mechanisms: structural plasticity, weight plasticity, and synaptic delay plasticity.
Conclusions:
- Dendritic computations offer powerful capabilities for artificial neural networks.
- The integration of deep learning with dendritic principles is a promising research direction.
- Future research should further explore and leverage dendritic computational power.
Related Concept Videos
01:25Neural Circuits
1.9K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
1.9K
01:19The Role of Ion Channels in Neuronal Computation
3.3K
A postsynaptic neuron usually receives numerous impulses from several other presynaptic neurons. The axon hillock of the postsynaptic neuron integrates all these signals and determines the likelihood of firing an action potential.
Sometimes a single EPSP is strong enough to induce an action potential in the postsynaptic neuron. However, multiple presynaptic inputs must often create EPSPs around the same time for the postsynaptic neuron to be sufficiently depolarized to fire an action potential....
Sometimes a single EPSP is strong enough to induce an action potential in the postsynaptic neuron. However, multiple presynaptic inputs must often create EPSPs around the same time for the postsynaptic neuron to be sufficiently depolarized to fire an action potential....
3.3K