Related Experiment Video
Updated: Aug 9, 2025
07:34
A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions
Published on: March 25, 2014
10.0K
Supervised Learning Algorithm Based on Spike Train Inner Product for Deep Spiking Neural Networks
Xianghong Lin1, Zhen Zhang1, Donghao Zheng1
1College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, China.
Brain Sciences
|February 25, 2023
Summary
Deep spiking neural networks (DSNNs) learn hierarchical features for spatio-temporal data. New algorithms like FA-STIP and BA-STIP improve learning performance and stability on the MNIST dataset.
Area of Science:
- Artificial Intelligence
- Computational Neuroscience
- Machine Learning
Background:
- Deep Spiking Neural Networks (DSNNs) mimic the human brain's hierarchical structure for effective spatio-temporal information processing.
- Supervised learning for DSNNs at the spike train level is challenging due to complex structures and nonlinear mechanisms.
Purpose of the Study:
- To develop novel supervised learning algorithms for DSNNs.
- To address the weight transport problem inherent in backpropagation (BP) for DSNNs.
- To evaluate the performance and stability of proposed algorithms.
Main Methods:
- Proposed BP-STIP algorithm based on kernel functions and spike trains inner product (STIP) with error backpropagation.
- Introduced FA-STIP and BA-STIP algorithms utilizing feedback alignment (FA) and broadcast alignment (BA) to optimize error feedback.
- Validated algorithms on the MNIST handwritten digit dataset.
Main Results:
- FA-STIP achieved 94.73% classification accuracy, and BP-STIP achieved 95.65% accuracy on MNIST.
- The proposed FA-STIP and BA-STIP algorithms demonstrated improved learning performance and stability over the benchmark BP-STIP.
- Analyzed the impact of different kernel functions on DSNN learning across various network scales.
Conclusions:
- The developed FA-STIP and BA-STIP algorithms offer effective solutions for supervised learning in DSNNs.
- These methods show enhanced performance and stability, outperforming existing benchmark algorithms.
- The study highlights the potential of biologically inspired learning mechanisms for advanced neural network applications.
