In the scientific report “Biologically-informed excitatory and inhibitory ratio for robust spiking neural network training” published in Scientific Reports, researchers from George Washington University and George Mason University advanced brain-inspired artificial intelligence by addressing key challenges in training spiking neural networks, a critical step toward more efficient and sustainable AI systems. GW Engineering’s Professor Gina Adam, from Department of Electrical and Computer Engineering, and her doctoral student Joseph Kilgore contributed to the study.
Here is and excerpt from the study abstract: “In this work, we identify several key factors, such as low initial firing rates and diverse inhibitory spiking patterns, that determine the overall ability to train in the context of spiking networks with various ratios of excitatory to inhibitory neurons. The results indicate networks with biologically-realistic excitatory:inhibitory ratios can reliably train at low activity levels and in noisy environments.”
Read the full study in the journal, Scientific Reports.