▪ 現代的なDNNではバッチ正規化(とその後継)を多用 ▪ ドロップアウトを一部代替 「USA to ブラジル」 が検索上位に GAN https://www.whichfaceisreal.com/ 「ブラジル to USA 」 が検索上位に Transformer https://blog.google/products/search/search-language-understanding-bert/ - 49 -
Duchi, J., Hazan, E., & Singer, Y. (2011). Adaptive subgradient methods for online learning and stochastic optimization. JMLR, 12(7). 4. Zeiler, M. D. (2012). Adadelta: an adaptive learning rate method. arXiv preprint arXiv:1212.5701. 5. Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. 6. Glorot, X., & Bengio, Y. (2010). Understanding the difficulty of training deep feedforward neural networks. In Proc. AISTATS (pp. 249-256). 7. He, K., Zhang, X., Ren, S., & Sun, J. (2015). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proc. IEEE ICCV (pp. 1026-1034). - 55 -