Evolutionary feature selection for spiking neural network pattern classifiers
Michal Valko, Nuno C. Marques, Marco Castelani
TLDR
This paper extends evolutionary feature selection to JASTAP spiking neural networks, enabling smaller, more robust classifiers for noisy data.
Key contributions
- Applies the biologically realistic JASTAP spiking neural network model to classification tasks.
- Extends an evolutionary procedure for feature selection and training to JASTAP SNNs.
- Achieves comparable classification accuracy with smaller JASTAP networks on noisy data.
Why it matters
This work presents a promising alternative to traditional MLPs using biologically realistic spiking neural networks (SNNs). By integrating evolutionary feature selection, it enables the development of smaller, more robust SNN classifiers capable of handling noisy data effectively. This could lead to more efficient and biologically inspired AI systems.
Original Abstract
This paper presents an application of the biologically realistic JASTAP neural network model to classification tasks. The JASTAP neural network model is presented as an alternative to the basic multi-layer perceptron model. An evolutionary procedure previously applied to the simultaneous solution of feature selection and neural network training on standard multi-layer perceptrons is extended with JASTAP model. Preliminary results on IRIS standard data set give evidence that this extension allows the use of smaller neural networks that can handle noisier data without any degradation in classification accuracy.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.