Revisit Lmser from a Deep Learning Perspective
Proposed in 1991, Least Mean Square Error Reconstruction for self-organizing network, shortly Lmser, was a further development of the traditional auto-encoder (AE) by folding the architecture with respect to the central coding layer and thus leading to the features of Duality in Connection Weight (DCW) and Duality in Paired Neurons (DPN), as well as jointly supervised and unsupervised learning which is called Duality in Supervision Paradigm (DSP). However, its advantages were only demonstrated in a one-hidden-layer implementation due to the lack of computing resources and big data at that time. In this paper, we revisit Lmser from the perspective of deep learning, develop Lmser network based on multiple fully-connected layers, and confirm several Lmser functions with experiments on image recognition, reconstruction, association recall, and so on. Experiments demonstrate that Lmser indeed works as indicated in the original paper, and it has promising performance in various applications.
KeywordsAutoencoder Lmser Bidirectional deep learning
This work was supported by the Zhi-Yuan Chair Professorship Start-up Grant (WF220103010), and Startup Fund (WF220403029) for Youngman Research, from Shanghai Jiao Tong University.
- 1.Ballard, D.H.: Modular learning in neural networks. In: Proceedings of the Sixth National Conference on Artificial Intelligence, AAAI 1987, vol. 1, pp. 279–284 (1987)Google Scholar
- 3.Goodfellow, I., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: International Conference on Learning Representations (2015). http://arxiv.org/abs/1412.6572
- 4.He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
- 7.Huang, G., Liu, Z., Weinberger, K.Q.: Densely connected convolutional networks. CoRR abs/1608.06993 (2016). http://arxiv.org/abs/1608.06993
- 8.Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR abs/1412.6980 (2014). http://arxiv.org/abs/1412.6980
- 9.LeCun, Y., Cortes, C., Burges, C.: MNIST handwritten digit database, vol. 2. AT&T Labs (2010). http://yann.lecun.com/exdb/mnist/
- 10.Mao, X., Shen, C., Yang, Y.B.: Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. In: Advances in Neural Information Processing Systems, pp. 2802–2810 (2016)Google Scholar
- 11.Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28CrossRefGoogle Scholar
- 12.Xiao, H., Rasul, K., Vollgraf, R.: Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. CoRR abs/1708.07747 (2017)Google Scholar
- 13.Xu, L.: Least MSE reconstruction for self-organization: (i)&(ii). In: Proceedings of 1991 International Joint Conference on Neural Networks, pp. 2363–2373 (1991)Google Scholar