video thumbnail 6:55
Neural Networks Demystified [Part 3: Gradient Descent]

2014-11-21

[public] 377K views, 5.42K likes, 42.0 dislikes audio only

Neural Networks Demystified

@stephencwelch

Supporting Code:

https://github.com/stephencwelch/Neural-Networks-Demystified

Link to Yann's Talk:

http://videolectures.net/eml07_lecun_wia/

In this short series, we will build and train a complete Artificial Neural Network in python. New videos every other friday.

Part 1: Data + Architecture

Part 2: Forward Propagation

Part 3: Gradient Descent

Part 4: Backpropagation

Part 5: Numerical Gradient Checking

Part 6: Training

Part 7: Overfitting, Testing, and Regularization


pass in our normalized data x using our forward method
/youtube/video/5u0jaA3qAGk?t=18.039
find the ideal value for our weight
/youtube/video/5u0jaA3qAGk?t=100.78
exploit the convex nature of quadratic equations
/youtube/video/5u0jaA3qAGk?t=355.82001