# Hybrid ANN-SNN Pipeline with Local Plasticity

arXiv: https://arxiv.org/abs/2606.20151 · HTML: https://mlsanity.com/paper/2606.20151/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 18 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Builds on (most cited first, 8 of 8)

- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Big Transfer (BiT): General Visual Representation Learning](https://mlsanity.com/paper/1912.11370/) (2019)
- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [Neuromorphic Artificial Intelligence Systems](https://mlsanity.com/paper/2205.13037/) (2022)
- [CoLaNET -- A Spiking Neural Network with Columnar Layered Architecture for Classification](https://mlsanity.com/paper/2409.01230/) (2024)
- [Classifying Images with CoLaNET Spiking Neural Network -- the MNIST Example](https://mlsanity.com/paper/2409.07833/) (2024)
- [A Digital Machine Learning Algorithm Simulating Spiking Neural Network CoLaNET](https://mlsanity.com/paper/2503.17111/) (2025)
- [Continual Learning with Columnar Spiking Neural Networks](https://mlsanity.com/paper/2506.17169/) (2025)

## Abstract (arXiv)

This work proposes a hybrid ANN-SNN pipeline that effectively leverages the rich embeddings of pretrained artificial neural networks (ANNs) to enable high-performance spiking neural networks (SNNs). The architecture couples a pretrained EfficientNet encoder with a CoLaNET spiking classifier. We convert the encoder's activations into spike trains via rate-coding and train the subsequent SNN classifier using local, biologically inspired learning rules, bypassing end-to-end gradient propagation. This approach achieves 99.09% accuracy on a 64-class ImageNet benchmark, demonstrating performance on par with conventional deep networks. The work presents a biologically plausible and efficient framework for adapting powerful pretrained encoders to downstream spiking neural network tasks.