人工智能 | MIT公开课2019深度学习最新技术

版权声明：本文为博主原创文章，未经博主允许不得转载。转载注明文章出处！！！ https://blog.csdn.net/u011344545/article/details/90204652

博主github：https://github.com/MichaelBeechan
博主CSDN：https://blog.csdn.net/u011344545

下载链接：https://download.csdn.net/download/u011344545/11170869

deeplearning.mit.edu
MIT：https://github.com/lexfridman/mit-deep-learning
MIT：https://github.com/lexfridman

1、自然语言处理

More details: http://jalammar.github.io/illustrated-transformer/

Vaswani, Ashish, et al. “Attention is all you need.” Advances in Neural Information Processing Systems. 2017.




Devlin, Jacob, et al. “Bert: Pre-training of deep bidirectional transformers for language understanding.” (2018).
翻译：https://blog.csdn.net/muumian123/article/details/84031163

2、特斯拉自动驾驶仪硬件v2+:大规模神经网络

3、AdaNet：自动集成电路

4、AutoAugment： 深度RL数据增强

5、用合成数据训练深度网络

Tremblay, Jonathan, et al. “Training deep networks with synthetic data: Bridging the reality gap by domain randomization.” (2018).

6、多边形RNN ++分割注释

Acuna, David, et al. “Efficient Interactive Annotation of Segmentation Datasets With Polygon-RNN++.” CVPR 2018.

7、DAWNBench: Training Fast and Cheap

Details: http://bit.ly/2H6yv6H

8、BigGAN：图像合成的最新技术

Brock, Andrew, Jeff Donahue, and Karen Simonyan. “Large scale gan training for high fidelity natural image synthesis.” (2018).

9、Video-to-Video Synthesis

Wang, Ting-Chun, et al. “Video-to-video synthesis.” (2018)

10、语义分割

Tutorial: https://github.com/lexfridman/mit-deep-learning

11、AlphaZero & OpenAI Five

12、深度学习框架

• Videos and slides posted on the website
• Code posted on GitHub: https://github.com/lexfridman/mit-deep-learning