Bio-Inspired Classification: Combining Information Theory and Spiking Neural Networks -- Influence of the Learning Rules

2025-06-07 · Zofia Rudnicka, Janusz Szczepanski, Agnieszka Pregowska

Training of Spiking Neural Networks (SNN) is challenging due to their unique properties, including temporal dynamics, non-differentiability of spike events, and sparse event-driven activations. In this paper, we widely consider the influence of the type of chosen learning algorithm, including bioinspired learning rules on the accuracy of classification. We proposed a bioinspired classifier based on the combination of SNN and Lempel-Ziv complexity (LZC). This approach synergizes the strengths of SNNs in temporal precision and biological realism with LZC's structural complexity analysis, facilitating efficient and interpretable classification of spatiotemporal neural data. It turned out that the classic backpropagation algorithm achieves excellent classification accuracy, but at extremely high computational cost, which makes it impractical for real-time applications. Biologically inspired learning algorithms such as tempotron and Spikprop provide increased computational efficiency while maintaining competitive classification performance, making them suitable for time-sensitive tasks. The results obtained indicate that the selection of the most appropriate learning algorithm depends on the trade-off between classification accuracy and computational cost as well as application constraints.

📄 PDF Abstract BibTeX arXiv:2506.06750

Code (0)

등록된 구현이 없습니다.

Tasks

Classification Computational Efficiency

Methods 이 논문이 사용한 방법론

SNN Spiking Neural Networks (SNNs) are a class of artificial neural networks inspired by the structure and functioning of the brain's neural networks. Unlike traditional…

Learning Regularities from Data using Spiking Functions: A Theory

2024-05-19 · Canlin Zhang, Xiuwen Liu

Deep neural networks trained in an end-to-end manner are proven to be efficient in a wide range of machine learning tasks. However, there is one drawback of end-to-end learning: The learned features and information are i…

Learning Theory

Reinforcement learning with a network of spiking agents

2019-10-15 · NeurIPS Workshop Neuro_AI 2019 12 · Sneha Aenugu, Abhishek Sharma, Sasikiran Yelamarthi, Hananel Hazan 외

Neuroscientific theory suggests that dopaminergic neurons broadcast global reward prediction errors to large areas of the brain influencing the synaptic plasticity of the neurons in those regions. We build on this theory…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Quantum Superposition Inspired Spiking Neural Network

2020-10-23 · Yinqian Sun, Yi Zeng, Tielin Zhang

Despite advances in artificial intelligence models, neural networks still cannot achieve human performance, partly due to differences in how information is encoded and processed compared to human brain. Information in an…

BIG-bench Machine Learning

Sustainable AI: Mathematical Foundations of Spiking Neural Networks

2025-03-03 · Adalbert Fono, Manjot Singh, Ernesto Araya, Philipp C. Petersen 외

Deep learning's success comes with growing energy demands, raising concerns about the long-term sustainability of the field. Spiking neural networks, inspired by biological neurons, offer a promising alternative with pot…