In this step, we calculate the gradients of the loss function f(y, y_hat) with respect to A, W, and b called dA, dW, and db. Using these gradients, we update the values of the parameters from the last layer to the first.
- Title Page
- Copyright and Credits
- About Packt
- Contributors
- Preface
- Quantifying Learning Algorithms
- Statistical models
- Learning curve
- Curve fitting
- Statistical modeling – the two cultures of Leo Breiman
- Training data development data – test data
- Bias-variance trade off
- Regularization
- Cross-validation and model selection
- Model selection using cross-validation
- 0.632 rule in bootstrapping
- Model evaluation
- Receiver operating characteristic curve
- H-measure
- Dimensionality reduction
- Summary
- Evaluating Kernel Learning
- Performance in Ensemble Learning
- Training Neural Networks
- Time Series Analysis
- Natural Language Processing
- Temporal and Sequential Pattern Discovery
- Probabilistic Graphical Models
- Selected Topics in Deep Learning
- Causal Inference
- Advanced Methods
- Other Books You May Enjoy
Backward propagation
-
No Comment
..................Content has been hidden....................
You can't read the all page of ebook, please click here login for view all page.