1. On the importance of single directions for generalization.
https://arxiv.org/abs/1803.06959v4
. Accessed 23 May 2018
2. Goodfellow, I., Le, Q., Saxe, A., Lee, H., Ng, A.: Measuring invariances in deep networks. In: Proceedings of the 22nd International Conference on Neural Information Processing Systems, NIPS 2009, Vancouver, British Columbia, Canada, pp. 646–654 (2009)
3. Tan, B., Zhang, Y., Pan, S., Yang, Q.: Distant domain transfer learning. In: AAAI, pp. 2604–2610 (2017)
4. Yoon, Y., Lee, L.-K., Oh, S.-Y.: Semi-rotation invariant feature descriptors using Zernike moments for MLP classifier. In: Proceedings of 2016 International Joint Conference on Neural Networks, IJCNN 2016, pp. 3990–3994. IEEE, Vancouver (2016)
5. Malashin, R., Kadykov, A.: Investigation of the generalizing capabilities of convolutional neural networks in forming rotation-invariant attributes. J. Opt. Technol. 82(8), 509–515 (2015)