Spark: Modular Spiking Neural Networks
This work addresses data and energy inefficiency in neural networks for researchers in spiking neural networks and efficient AI, but it appears incremental as it builds on existing modular and plasticity ideas.
The paper tackles the inefficiency of neural networks in data and energy by proposing Spark, a modular framework for spiking neural networks, and demonstrates it by solving the sparse-reward cartpole problem with simple plasticity mechanisms.
Nowadays, neural networks act as a synonym for artificial intelligence. Present neural network models, although remarkably powerful, are inefficient both in terms of data and energy. Several alternative forms of neural networks have been proposed to address some of these problems. Specifically, spiking neural networks are suitable for efficient hardware implementations. However, effective learning algorithms for spiking networks remain elusive, although it is suspected that effective plasticity mechanisms could alleviate the problem of data efficiency. Here, we present a new framework for spiking neural networks - Spark - built upon the idea of modular design, from simple components to entire models. The aim of this framework is to provide an efficient and streamlined pipeline for spiking neural networks. We showcase this framework by solving the sparse-reward cartpole problem with simple plasticity mechanisms. We hope that a framework compatible with traditional ML pipelines may accelerate research in the area, specifically for continuous and unbatched learning, akin to the one animals exhibit.