Dynamic Activation with Knowledge Distillation for Energy-Efficient Spiking NN Ensembles

• URL: http://arxiv.org/abs/2502.14023v1
• Date: Wed, 19 Feb 2025 18:50:08 GMT
• Title: Dynamic Activation with Knowledge Distillation for Energy-Efficient Spiking NN Ensembles
• Authors: Orestis Konstantaropoulos, Theodoris Mallios, Maria Papadopouli,
• Abstract summary: This work introduces a novel system that combines knowledge distillation and ensemble learning to bridge the performance gap between artificial neural networks (ANNs) and SNNs. A foundation AI model acts as a teacher network, guiding smaller student SNNs organized into an ensemble, called Spiking Neural Ensemble (SNE) SNE is significantly more efficient than the teacher network, reducing computational requirements by up to 20x with only a 2% drop in accuracy on the CIFAR-10 dataset.
• Score: 0.2621730497733947
• License:
• Abstract: While foundation AI models excel at tasks like classification and decision-making, their high energy consumption makes them unsuitable for energy-constrained applications. Inspired by the brain's efficiency, spiking neural networks (SNNs) have emerged as a viable alternative due to their event-driven nature and compatibility with neuromorphic chips. This work introduces a novel system that combines knowledge distillation and ensemble learning to bridge the performance gap between artificial neural networks (ANNs) and SNNs. A foundation AI model acts as a teacher network, guiding smaller student SNNs organized into an ensemble, called Spiking Neural Ensemble (SNE). SNE enables the disentanglement of the teacher's knowledge, allowing each student to specialize in predicting a distinct aspect of it, while processing the same input. The core innovation of SNE is the adaptive activation of a subset of SNN models of an ensemble, leveraging knowledge-distillation, enhanced with an informed-partitioning (disentanglement) of the teacher's feature space. By dynamically activating only a subset of these student SNNs, the system balances accuracy and energy efficiency, achieving substantial energy savings with minimal accuracy loss. Moreover, SNE is significantly more efficient than the teacher network, reducing computational requirements by up to 20x with only a 2% drop in accuracy on the CIFAR-10 dataset. This disentanglement procedure achieves an accuracy improvement of up to 2.4% on the CIFAR-10 dataset compared to other partitioning schemes. Finally, we comparatively analyze SNE performance under noisy conditions, demonstrating enhanced robustness compared to its ANN teacher. In summary, SNE offers a promising new direction for energy-constrained applications.

Related papers

• Efficient Distillation of Deep Spiking Neural Networks for Full-Range Timestep Deployment [10.026742974971189]
  Spiking Neural Networks (SNNs) are emerging as a brain-inspired alternative to traditional Artificial Neural Networks (ANNs) Despite this, SNNs often suffer from accuracy compared to ANNs and face deployment challenges due to inference timesteps, which require retraining for adjustments, limiting operational flexibility. We propose a novel distillation framework for deep SNNs that optimize performance across full-range timesteps without specific retraining, enhancing both efficacy and adaptability.
  arXiv  Detail & Related papers  (2025-01-27T10:22:38Z)
• ALADE-SNN: Adaptive Logit Alignment in Dynamically Expandable Spiking Neural Networks for Class Incremental Learning [15.022211557367273]
  We develop spiking neural networks (SNNs) with dynamic structures for Class Incremental Learning (CIL) We propose the ALADE-SNN framework, which includes adaptive logit alignment for balanced feature representation and OtoN suppression to manage weights mapping frozen old features to new classes during training. Experiment results show that ALADE-SNN achieves an average incremental accuracy of 75.42 on the CIFAR100-B0 benchmark over 10 incremental steps.
  arXiv  Detail & Related papers  (2024-12-17T09:13:22Z)
• Skip Connections in Spiking Neural Networks: An Analysis of Their Effect on Network Training [0.8602553195689513]
  Spiking neural networks (SNNs) have gained attention as a promising alternative to traditional artificial neural networks (ANNs) In this paper, we study the impact of skip connections on SNNs and propose a hyper parameter optimization technique that adapts models from ANN to SNN. We demonstrate that optimizing the position, type, and number of skip connections can significantly improve the accuracy and efficiency of SNNs.
  arXiv  Detail & Related papers  (2023-03-23T07:57:32Z)
• Training Spiking Neural Networks with Local Tandem Learning [96.32026780517097]
  Spiking neural networks (SNNs) are shown to be more biologically plausible and energy efficient than their predecessors. In this paper, we put forward a generalized learning rule, termed Local Tandem Learning (LTL) We demonstrate rapid network convergence within five training epochs on the CIFAR-10 dataset while having low computational complexity.
  arXiv  Detail & Related papers  (2022-10-10T10:05:00Z)
• On the Intrinsic Structures of Spiking Neural Networks [66.57589494713515]
  Recent years have emerged a surge of interest in SNNs owing to their remarkable potential to handle time-dependent and event-driven data. There has been a dearth of comprehensive studies examining the impact of intrinsic structures within spiking computations. This work delves deep into the intrinsic structures of SNNs, by elucidating their influence on the expressivity of SNNs.
  arXiv  Detail & Related papers  (2022-06-21T09:42:30Z)
• Knowledge Enhanced Neural Networks for relational domains [83.9217787335878]
  We focus on a specific method, KENN, a Neural-Symbolic architecture that injects prior logical knowledge into a neural network. In this paper, we propose an extension of KENN for relational data.
  arXiv  Detail & Related papers  (2022-05-31T13:00:34Z)
• Deep Reinforcement Learning with Spiking Q-learning [51.386945803485084]
  spiking neural networks (SNNs) are expected to realize artificial intelligence (AI) with less energy consumption. It provides a promising energy-efficient way for realistic control tasks by combining SNNs with deep reinforcement learning (RL)
  arXiv  Detail & Related papers  (2022-01-21T16:42:11Z)
• Low-Precision Training in Logarithmic Number System using Multiplicative Weight Update [49.948082497688404]
  Training large-scale deep neural networks (DNNs) currently requires a significant amount of energy, leading to serious environmental impacts. One promising approach to reduce the energy costs is representing DNNs with low-precision numbers. We jointly design a lowprecision training framework involving a logarithmic number system (LNS) and a multiplicative weight update training method, termed LNS-Madam.
  arXiv  Detail & Related papers  (2021-06-26T00:32:17Z)
• SpikeDyn: A Framework for Energy-Efficient Spiking Neural Networks with Continual and Unsupervised Learning Capabilities in Dynamic Environments [14.727296040550392]
  Spiking Neural Networks (SNNs) bear the potential of efficient unsupervised and continual learning capabilities because of their biological plausibility. We propose SpikeDyn, a framework for energy-efficient SNNs with continual and unsupervised learning capabilities in dynamic environments.
  arXiv  Detail & Related papers  (2021-02-28T08:26:23Z)
• Progressive Tandem Learning for Pattern Recognition with Deep Spiking Neural Networks [80.15411508088522]
  Spiking neural networks (SNNs) have shown advantages over traditional artificial neural networks (ANNs) for low latency and high computational efficiency. We propose a novel ANN-to-SNN conversion and layer-wise learning framework for rapid and efficient pattern recognition.
  arXiv  Detail & Related papers  (2020-07-02T15:38:44Z)
• Distilling Spikes: Knowledge Distillation in Spiking Neural Networks [22.331135708302586]
  Spiking Neural Networks (SNNs) are energy-efficient computing architectures that exchange spikes for processing information. We propose techniques for knowledge distillation in spiking neural networks for the task of image classification. Our approach is expected to open up new avenues for deploying high performing large SNN models on resource-constrained hardware platforms.
  arXiv  Detail & Related papers  (2020-05-01T09:36:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.