Related Experiment Video
Updated: Jan 20, 2026
08:29
Averaging of Viral Envelope Glycoprotein Spikes from Electron Cryotomography Reconstructions using Jsubtomo
Published on: October 21, 2014
12.6K
Back-Propagation Learning in Deep Spike-By-Spike Networks
David Rotermund1, Klaus R Pawelzik1
1Institute for Theoretical Physics, University of Bremen, Bremen, Germany.
Frontiers in Computational Neuroscience
|August 29, 2019
Summary
A new learning rule for Spike-by-Spike (SbS) networks bridges the gap between artificial neural networks (ANNs) and real brains. This advance enables high-performance deep SbS networks for technical applications and neuroscience research.
Area of Science:
- Computational Neuroscience
- Machine Learning
- Artificial Intelligence
Background:
- Artificial neural networks (ANNs) utilize continuous signals, unlike biological brains that use discrete action potentials.
- Bridging this gap is crucial for developing more brain-like computational models.
Purpose of the Study:
- To develop a learning rule for optimizing deep Spike-by-Spike (SbS) networks.
- To enable SbS networks to perform complex tasks comparable to traditional ANNs.
Main Methods:
- Derivation of a novel learning rule for feed-forward SbS networks.
- Investigation of the learning rule's properties through simulations.
- Application of the learning rule to a Deep Convolutional SbS network.
Main Results:
- The derived learning rule optimizes weight sets for deep SbS networks.
- A Deep Convolutional SbS network achieved ~99.3% accuracy on MNIST handwritten digit classification.
- Performance approaches ANN benchmarks without extensive parameter tuning.
Conclusions:
- The developed learning rule provides a viable method for training deep SbS networks.
- This approach offers a new foundation for neuroscience research and technical applications.
- Potential for implementation on specialized computational hardware.
Keywords:
compressed sensing (CS)deep network (DN)error back propagation (BP) neural networksparsenessspiking network modelMore Related Videos
Related Concept Videos
02:26Protein Networks
4.5K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.5K
01:07Propagation of Waves
2.9K
When a wave propagates from one medium to another, part of it may get reflected in the first medium, and part of it may get transmitted to the second medium. In such a case, the interface of the two mediums can be considered as a boundary that is neither fixed nor free.
Consider a scenario where a wave propagates from a string of low linear mass density to a string of high linear mass density. In such a case, the reflected wave is out of phase with respect to the incident wave, however the...
Consider a scenario where a wave propagates from a string of low linear mass density to a string of high linear mass density. In such a case, the reflected wave is out of phase with respect to the incident wave, however the...
2.9K
02:18Network Covalent Solids
16.1K
Network covalent solids contain a three-dimensional network of covalently bonded atoms as found in the crystal structures of nonmetals like diamond, graphite, silicon, and some covalent compounds, such as silicon dioxide (sand) and silicon carbide (carborundum, the abrasive on sandpaper). Many minerals have networks of covalent bonds.
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
16.1K
01:23Propagation of Action Potentials
9.0K
The propagation of an action potential refers to the process by which a nerve impulse, or "action potential," travels along a neuron.
Neurons (nerve cells) have a resting membrane potential, with a slightly negative charge inside compared to outside. This is maintained by ion channels, such as sodium (Na+) and potassium (K+) channels, which control the flow of ions. When a stimulus, like a touch or a signal from another neuron, triggers the neuron, sodium channels open, allowing sodium ions to...
Neurons (nerve cells) have a resting membrane potential, with a slightly negative charge inside compared to outside. This is maintained by ion channels, such as sodium (Na+) and potassium (K+) channels, which control the flow of ions. When a stimulus, like a touch or a signal from another neuron, triggers the neuron, sodium channels open, allowing sodium ions to...
9.0K
01:14Avoidance Learning and Learned Helplessness
2.5K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
2.5K
01:10Propagation of Uncertainty from Systematic Error
1.4K
The atomic mass of an element varies due to the relative ratio of its isotopes. A sample's relative proportion of oxygen isotopes influences its average atomic mass. For instance, if we were to measure the atomic mass of oxygen from a sample, the mass would be a weighted average of the isotopic masses of oxygen in that sample. Since a single sample is not likely to perfectly reflect the true atomic mass of oxygen for all the molecules of oxygen on Earth, the mass we obtain from this...
1.4K