Steps to Train Neural Network
1. Randomly initialize weights (theta)
2. For any input/feature set, get the value obtained from hypothesis using forward propagation (Getting activation terms)
3. Compute cost function
4. Compute partial derivatives using backward propagation (Getting delta terms)
5. Gradient checking: Compare derivative values obtained via backward propagation wrt the values obtained using numerical estimation. Disable gradient checking if there is no significant difference.
6. Use any optimization algorithm to minimize cost function.
References -
1. https://www.coursera.org/learn/machine-learning
1. Randomly initialize weights (theta)
2. For any input/feature set, get the value obtained from hypothesis using forward propagation (Getting activation terms)
3. Compute cost function
4. Compute partial derivatives using backward propagation (Getting delta terms)
5. Gradient checking: Compare derivative values obtained via backward propagation wrt the values obtained using numerical estimation. Disable gradient checking if there is no significant difference.
6. Use any optimization algorithm to minimize cost function.
References -
1. https://www.coursera.org/learn/machine-learning
No comments:
Post a Comment