Dendritic Resonate-and-Fire Neuron for Effective and Efficient Long Sequence Modeling
By: Dehao Zhang , Malu Zhang , Shuai Wang and more
Potential Business Impact:
Helps computers understand long, complex information faster.
The explosive growth in sequence length has intensified the demand for effective and efficient long sequence modeling. Benefiting from intrinsic oscillatory membrane dynamics, Resonate-and-Fire (RF) neurons can efficiently extract frequency components from input signals and encode them into spatiotemporal spike trains, making them well-suited for long sequence modeling. However, RF neurons exhibit limited effective memory capacity and a trade-off between energy efficiency and training speed on complex temporal tasks. Inspired by the dendritic structure of biological neurons, we propose a Dendritic Resonate-and-Fire (D-RF) model, which explicitly incorporates a multi-dendritic and soma architecture. Each dendritic branch encodes specific frequency bands by utilizing the intrinsic oscillatory dynamics of RF neurons, thereby collectively achieving comprehensive frequency representation. Furthermore, we introduce an adaptive threshold mechanism into the soma structure that adjusts the threshold based on historical spiking activity, reducing redundant spikes while maintaining training efficiency in long sequence tasks. Extensive experiments demonstrate that our method maintains competitive accuracy while substantially ensuring sparse spikes without compromising computational efficiency during training. These results underscore its potential as an effective and efficient solution for long sequence modeling on edge platforms.
Similar Papers
Scaling Up Resonate-and-Fire Networks for Fast Deep Learning
Neural and Evolutionary Computing
Makes AI understand sounds faster and better.
An Asynchronous Mixed-Signal Resonate-and-Fire Neuron
Signal Processing
Makes computers "hear" and understand sounds better.
Memory-DD: A Low-Complexity Dendrite-Inspired Neuron for Temporal Prediction Tasks
Neural and Evolutionary Computing
Predicts future events faster and with fewer computer parts.