2024/02/15 · In this work, we propose a general Transformer-based SNN architecture, termed as Meta-SpikeFormer, whose goals are: 1) Lower-power, supports the spike-driven ...

In this work, we propose a general Transformer-based SNN architecture, termed as Meta-SpikeFormer, whose goals are: (1) Lower-power, supports the spike-driven ...

We extend the Spike-driven Transformer into a meta architecture, and explore the impact of structure, spike-driven self-attention, and skip connection on its ...

This work extends the Spike-driven Transformer into a meta architecture, and explores the impact of structure, spike-driven self-attention, and skip connection ...

In this work, we propose a general Transformer-based SNN architecture, termed as “Meta-SpikeFormer", whose goals are: i) Lower-power, supports the spike-driven ...

In this work, we propose a general Transformer-based SNN architecture, termed as “Meta-SpikeFormer", whose goals are: i) Lower-power, supports the spike-driven ...

2024/04/07 · The paper introduces a new type of neural network architecture called Spike-driven Transformer V2 (SDT-V2) that is inspired by the way the brain processes ...

2024/08/16 · Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips. image.png.

Co-authors ; Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips. M Yao, J Hu, T Hu, ...

Offical implementation of Integer-Valued Training and Spike-Driven Inference Spiking Neural Network for High-performance and Energy-efficient Object Detection.