Guest
Part 12 (1:38:41) ============ Part 02-Module 02-Lesson 03_Recurrent Neural Networks 0:00:00 03. LSTM Basics-gjb68a4XsqE 0:03:02 04. LSTM Architecture-ycwthhdx8ws 0:03:55 05. Learn Gate-aVHVI7ovbHY 0:05:37 06. Forget Gate-iWxpfxLUPSU 0:06:25 07. Remember Gate-0qlm86HaXuU 0:06:52 08. LSTM 7 Use Gate-5Ifolm1jTdY 0:07:54 09. Putting It All Together-IF8FlKW-Zo0 0:09:12 10. Other Architectures-MsxFDuYlTuQ 0:10:33 12. 02 Time Series Prediction V2-xV5jHLFfJbQ 0:16:59 13. 03 Training Memory V1-sx7T_KP5v9I 0:21:29 14. Character-Wise RNN-dXl3eWCGLdU 0:23:38 15. Sequence-Batching-Z4OiyU0Cldg 0:25:05 17. 04 Implementing CharRNN V2-MMtgZXzFB10 0:31:55 18. 05 Batching Data V1-9Eg0wf3eW-k 0:34:59 19. 06 Defining Model V2-_LWzyqq4hCY 0:38:27 20. 07 CharRNN Solution V1-ed33qePHrJM 0:45:15 21. 08 Making Predictions V3-BhrpV3kwATo Part 02-Module 02-Lesson 04_Training Neural Networks 0:50:33 02. Training Optimization-UiGKhx9pUYc 0:51:01 03. Testing-EeBZpb-PSac 0:52:44 04. Underfitting And Overfitting-xj4PlXMsN-Y 0:57:51 05. Model Complexity Graph-NnS0FJyVcDQ 1:01:31 06. DL 53 Q Regularization-KxROxcRsHL8 1:02:24 07. Regularization-ndYnUrx8xvs 1:08:24 08. Dropout-Ty6K6YiGdBs 1:11:33 09. Local Minima-gF_sW_nY-xw 1:12:15 10. Random Restart-idyBBCzXiqg 1:12:32 11. Vanishing Gradient-W_JJm_5syFw 1:13:36 12. Other Activation Functions-kA-1vUt6cvQ 1:15:26 13. Batch vs Stochastic Gradient Descent-2p58rVgqsgo 1:18:31 14. Learning Rate-TwJ8aSZoh2U 1:19:15 15. Momentum-r-rYz_PEWC8 1:21:01 16. Error Functions Around the World-34AAcTECu2A Part 02-Module 02-Lesson 05_Embeddings Word2Vec 1:21:54 01. M4L51 HSA Word Embeddings V3 RENDER V1-ZsLhh1mly9k 1:23:35 02. M4L52 HSA Embedding Weight Matrix V3 RENDER V2-KVCcG5v8fi0 1:26:14 03. 3 Word2Vec Notebook V2-4cWzv3YiF_w 1:30:26 06. 4 Data Subsampling V1-7SJXv2BQzZA 1:36:50 07. 5 Subsampling Solution V1-YXruURuFD7g
