Abstract
Task-Free Continual Learning (TFCL) poses a formidable challenge in lifelong learning, as it operates without task-specific information. Leveraging spiking neural networks (SNNs) for TFCL is particularly intriguing due to their promising results in low-energy applications. However, existing research has predominantly focused on employing SNNs for solving single-task classification problems. In this work, our goal is to utilize ANN to guide SNN in addressing catastrophic forgetting and model compression issues, while treating SNNs as the basic network of the model. We introduce AGT-SNN (ANN-Guided TFCL for Spiking Neural Networks), a novel framework that empowers SNNs to engage in lifelong learning without relying on task-specific information. We conceptualize the learning process of the model as a multiplayer game, involving participants in the roles of players and referees. Our model’s fundamental components comprise player-referee pairs, where the player module adopts a SNN-based Variational Autoencoder (VAE) and the referee module employs a ANN-based Generative Adversarial Network (GAN). To dynamically expand the number of components, we propose an innovative method called Adversarial Similarity Expansion (ASE). ASE evaluates the performance of the current player against previously learned players without accessing any task-specific information. Additionally, we propose a innovative pruning strategy that selectively removes redundant components while preserving the diversity of knowledge, thereby reducing the model’s complexity. Through comprehensive experimental validation, we demonstrate that our proposed framework enables SNNs to achieve exceptional performance while maintaining an appropriate network size.
Supported in part by the National Natural Science Foundation of China (62276106), the Guangdong Provincial Key Laboratory IRADS (2022B1212010006, R0400001-22) and the UIC Start-up Research Fund (UICR0700056-23) and the Artificial Intelligence and Data Science Research Hub (AIRH) of BNU-HKBU United International College (UIC).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aljundi, R., et al.: Online continual learning with maximal interfered retrieval. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Aljundi, R., Kelchtermans, K., Tuytelaars, T.: Task-free continual learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11254–11263 (2019)
Arribas, D., Zhao, Y., Park, I.M.: Rescuing neural spike train models from bad MLE. In: Advances in Neural Information Processing Systems, pp. 2293–2303 (2020)
Davies, M., et al.: Loihi: a neuromorphic manycore processor with on-chip learning. IEEE Micro 38(1), 82–99 (2018)
De Lange, M., Tuytelaars, T.: Continual prototype evolution: learning online from non-stationary data streams. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8250–8259 (2021)
Fan, W., Bouguila, N., Du, J.X., Liu, X.: Axially symmetric data clustering through Dirichlet process mixture models of Watson distributions. IEEE Trans. Neural Networks Learn. Syst. 30(6), 1683–1694 (2019)
Fan, W., Yang, L., Bouguila, N.: Unsupervised grouped axial data modeling via hierarchical Bayesian nonparametric models with Watson distributions. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 9654–9668 (2022)
French, R.M.: Catastrophic forgetting in connectionist networks. Trends Cogn. Sci. 3(4), 128–135 (1999)
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of Wasserstein GANs. In: Advances in Neural Information Processing Systems, pp. 5767–5777 (2017)
Hanle, Z., Yujie, W., Lei, D., Yifan, H., Guoqi, L.: Going deeper with directly-trained larger spiking neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 11062–11070 (2021)
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: Advances in Neural Information Processing Systems, pp. 6626–6637 (2017)
Kamata, H., Mukuta, Y., Harada, T.: Fully spiking variational autoencoder. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 7059–7067 (2022)
Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: International Conference on Learning Representations (2014)
Kotariya, V., Ganguly, U.: Spiking-GAN: a spiking generative adversarial network using time-to-first-spike coding. In: 2022 International Joint Conference on Neural Networks (IJCNN), pp. 1–7 (2022)
Lee, S., Ha, J., Zhang, D., Kim, G.: A neural Dirichlet process mixture model for task-free continual learning. arXiv preprint arXiv:2001.00689 (2020)
Li, Y.: Research and application of deep learning in image recognition. In: 2022 IEEE 2nd International Conference on Power, Electronics and Computer Applications (ICPECA), pp. 994–999. IEEE (2022)
Lopez-Paz, D., Ranzato, M.A.: Gradient episodic memory for continual learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Maass, W.: Networks of spiking neurons: the third generation of neural network models. Neural Netw. 10(9), 1659–1671 (1997)
Otter, D.W., Medina, J.R., Kalita, J.K.: A survey of the usages of deep learning for natural language processing. IEEE Trans. Neural Networks Learn. Syst. 32(2), 604–624 (2020)
Ramapuram, J., Gregorova, M., Kalousis, A.: Lifelong generative modeling. Neurocomputing 404, 381–400 (2020)
Rebuffi, S.A., Kolesnikov, A., Sperl, G., Lampert, C.H.: iCaRL: incremental classifier and representation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2001–2010 (2017)
Vitter, J.S.: Random sampling with a reservoir. ACM Trans. Math. Software (TOMS) 11(1), 37–57 (1985)
Yamazaki, K., Vo-Ho, V.K., Bulsara, D., Le, N.: Spiking neural networks and their applications: a review. Brain Sci. 12(7), 863 (2022)
Ye, F., Bors, A.G.: Lifelong compression mixture model via knowledge relationship graph. In: AAAI Conference on Artificial Intelligence. AAAI Press (2023)
Zhang, J., Fan, W., Liu, X.: Spiking generative networks in lifelong learning environment. In: Fujita, H., Wang, Y., Xiao, Y., Moonis, A. (eds.) IEA/AIE 2023. LNCS, vol. 13925, pp. 353–364. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-36819-6_31
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhang, J., Fan, W., Liu, X. (2024). An ANN-Guided Approach to Task-Free Continual Learning with Spiking Neural Networks. In: Liu, Q., et al. Pattern Recognition and Computer Vision. PRCV 2023. Lecture Notes in Computer Science, vol 14432. Springer, Singapore. https://doi.org/10.1007/978-981-99-8543-2_18
Download citation
DOI: https://doi.org/10.1007/978-981-99-8543-2_18
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8542-5
Online ISBN: 978-981-99-8543-2
eBook Packages: Computer ScienceComputer Science (R0)