Learning Spiking Neural Network from Easy to Hard task
Not on the map. Why?
Abstract (arXiv)
Starting with small and simple concepts, and gradually introducing complex and difficult concepts is the natural process of human learning. Spiking Neural Networks (SNNs) aim to mimic the way humans process information, but current SNNs models treat all samples equally, which does not align with the principles of human learning and overlooks the biological plausibility of SNNs. To address this, we propose a CL-SNN model that introduces Curriculum Learning(CL) into SNNs, making SNNs learn more like humans and providing higher biological interpretability. CL is a training strategy that advocates presenting easier data to models before gradually introducing more challenging data, mimicking the human learning process. We use a confidence-aware loss to measure and process the samples with different difficulty levels. By learning the confidence of different samples, the model reduces the contribution of difficult samples to parameter optimization automatically. We conducted experiments on static image datasets MNIST, Fashion-MNIST, CIFAR10, and neuromorphic datasets N-MNIST, CIFAR10-DVS, DVS-Gesture. The results are promising. To our best knowledge, this is the first proposal to enhance the biologically plausibility of SNNs by introducing CL.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 47 references that are in the map. First posted on arXiv 9 Sep 2023.
Builds on
27 of 47 references.
References · 27
- 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
- 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 604
- 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 340
- 2021Deep Residual Learning in Spiking Neural Networkscited by 326
- 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 268
- 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 222
- 2021Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networkscited by 134
- 2018CurriculumNet: Weakly Supervised Learning from Large-Scale Web Imagescited by 126
- 2018Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networkscited by 113
- 2021A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibrationcited by 111
- 2022Attention Spiking Neural Networkscited by 103
- 2016Supervised learning based on temporal coding in spiking neural networkscited by 75
15 more
- 2018Unsupervised Learning of a Hierarchical Spiking Neural Network for Optical Flow Estimation: From Events to Global Motion Perceptioncited by 48
- 2017Gradient Descent for Spiking Neural Networkscited by 47
- 2019Pseudo-Labeling Curriculum for Unsupervised Domain Adaptationcited by 46
- 2020Progressive Tandem Learning for Pattern Recognition with Deep Spiking Neural Networkscited by 46
- 2020Exploring Adversarial Attack in Spiking Neural Networks with Spike-Compatible Gradientcited by 31
- 2018Self-supervised Learning of Geometrically Stable Features Through Probabilistic Introspectioncited by 27
- 2019An Introduction to Probabilistic Spiking Neural Networks: Probabilistic Models, Learning Rules, and Applicationscited by 25
- 2021BackEISNN: A Deep Spiking Neural Network with Adaptive Self-Feedback and Balanced Excitatory-Inhibitory Neuronscited by 22
- 2023Complex Dynamic Neurons Improved Spiking Transformer Network for Efficient Automatic Speech Recognitioncited by 19
- 2020Tuning Convolutional Spiking Neural Network with Biologically-plausible Reward Propagationcited by 15
- 2018Unsupervised Learning with Self-Organizing Spiking Neural Networkscited by 11
- 2018Unsupervised Feature Learning Architecture with Multi-clustering Integration RBMcited by 4
- 2020Micro-supervised Disturbance Learning: A Perspective of Representation Probability Distributioncited by 4
- 2022Motif-topology and Reward-learning improved Spiking Neural Network for Efficient Multi-sensory Integrationcited by 4
- 2017Restricted Boltzmann Machines with Gaussian Visible Units Guided by Pairwise Constraintscited by 3
Built on by
Not cited yet.