Phase State Space Models: Parallel, Surrogate-Free Training of Spiking Networks
This paper presents a novel interpretation of resonate-and-fire neural networks using state-space models, enabling parallel training with real and spiking inputs, and maintaining biologically-realistic features.
Provides a novel interpretation of resonate-and-fire neural networks using state-space models, enabling parallel training with real and spiking inputs and maintaining biologically-realistic features.
Keywords
Before reading this…
Applications
- →Neural networks
- →Parallel processing
- →Biologically-realistic models
To understand this paper, make sure you know these concepts first:
- Understanding of neural networksfind papers →
- State-space modelsfind papers →
- Spiking modelsfind papers →
Abstract
More Like ThisState-space models (SSMs) provide a powerful theoretical framework to enable parallel training of recurrent networks. We expand on previous work adapting SSMs to spiking models to provide a novel interpretation of resonate-and-fire (R\&F) neural networks which is compatible both with real and spiking inputs, parallel and recurrent execution, has clear connections to hyperdimensional (HD) computing, and maintains biologically-realistic features. We demonstrate an implementation of this approach which integrates an STFT, recurrent memory, and attentional features within a single spike-compatible network.