FreeCoursesOnline Me MANNING Grokking Deep Learning in Motion FCO

1. 01 - Introduction.mp490.98MB
2. 02 - What you need to get started.mp475.23MB
3. 03 - What is Deep Learning and Machine Learning.mp482.64MB
4. 04 - Supervised vs. unsupervised learning.mp474.87MB
5. 05 - Parametric vs. non-parametric learning.mp4100.17MB
6. 06 - Making a prediction.mp490.36MB
7. 07 - What does a Neural Network do.mp445.68MB
8. 08 - Multiple inputs.mp495.21MB
9. 09 - Multiple outputs and stacking predictions.mp474.21MB
10. 10 - Primer on NumPy.mp463.64MB
11. 11 - Compare and learn.mp482.56MB
12. 12 - Why measure error.mp458.61MB
13. 13 - Hot and cold learning.mp485.75MB
14. 14 - Gradient descent.mp480.72MB
15. 15 - Learning with gradient decent.mp482.45MB
16. 16 - The secret to learning.mp483.02MB
17. 17 - How to use a derivative to learn.mp4105.82MB
18. 18 - Alpha.mp477.21MB
19. 19 - Gradient descent learning with multiple inputs.mp480.31MB
20. 20 - Several steps of learning.mp445.96MB
21. 21 - Gradient descent with multiple outputs.mp439.29MB
22. 22 - Visualizing weight values.mp492.57MB
23. 23 - The streetlight problem.mp480.72MB
24. 24 - Building our neural network.mp496.47MB
25. 25 - Up and down pressure.mp4137.95MB
26. 26 - Correlation and backpropagation.mp492.68MB
27. 27 - Linear vs. non-linear.mp468MB
28. 28 - Our first 'deep' neural network.mp489.14MB
29. 29 - Simplifying.mp486.64MB
30. 30 - Simplified visualization.mp473.08MB
31. 31 - Seeing the network predict.mp480.17MB
32. 32 - 3-layer network on MNIST.mp4121.89MB
33. 33 - Overfitting in Neural Networks.mp484.43MB
34. 34 - Regularization - Early Stopping and Dropout.mp4185.54MB
35. 35 - Activation Function Constraints.mp489.94MB
36. 36 - Standard Activation Functions.mp4127.35MB
37. 37 - Softmax and implementation in code.mp4172.77MB
38. 38 - Where to go from here.mp473.09MB