Topic: Training performance

Seminar
2 seminars
SeminarDeep LearningRecording

Optimal initialization strategies for Deep Spiking Neural Networks

Julia Gygax
Friedrich Miescher Institute for Biomedical Research (FMI)
Nov 3, 2021

Recent advances in neuromorphic hardware and Surrogate Gradient (SG) learning highlight the potential of Spiking Neural Networks (SNNs) for energy-efficient signal processing and learning. Like in Artificial Neural Networks (ANNs), training performance in SNNs strongly depends on the initialization of synaptic and neuronal parameters. While there are established methods of initializing deep ANNs for high performance, effective strategies for optimal SNN initialization are lacking. Here, we address this gap and propose flexible data-dependent initialization strategies for SNNs.

SeminarComputational NeuroscienceRecording

Understanding the role of neural heterogeneity in learning

Nicolas Perez-Nieves
Imperial College London
Nov 2, 2021

The brain has a hugely diverse and heterogeneous nature. The exact role of heterogeneity has been relatively little explored as most neural models tend to be largely homogeneous. We trained spiking neural networks with varying degrees of heterogeneity on complex real-world tasks and found that heterogeneity resulted in more stable and robust training and improved training performance, especially for tasks with a higher temporal structure. Moreover, the optimal distribution of parameters found by training was found to be similar to experimental observations. These findings suggest that heterogeneity is not simply a result of noisy biological processes, but it may play a crucial role for learning in complex, changing environments.

We use essential cookies to run the site. Analytics cookies are optional and help us improve World Wide. Learn more.