The GD method has some drawbacks, namely that it requires the gradient 
to be defined. The gradient may also be expensive to compute, and GD may approach the optimum too slowly.
- Title Page
- Copyright and Credits
- Dedication
- Packt Upsell
- Contributors
- Preface
- A Quick Refresher
- Building Our First Neural Network Together
- Decision Trees and Random Forests
- Face and Motion Detection
- Training CNNs Using ConvNetSharp
- Training Autoencoders Using RNNSharp
- Replacing Back Propagation with PSO
- Function Optimizations: How and Why
- Technical requirements
- Getting started
- Function minimization and maximization
- Hyperparameters and tuning
- Understanding visualizations
- Plotting results
- Adding new optimization functions
- Summary
- Finding Optimal Parameters
- Object Detection with TensorFlowSharp
- Time Series Prediction and LSTM Using CNTK
- GRUs Compared to LSTMs, RNNs, and Feedforward networks
- Activation Function Timings
- Function Optimization Reference
- The Currin Exponential function
- The Webster function
- The Oakley & O'Hagan function
- The Grammacy function
- Franke's function
- The Lim function
- The Ackley function
- The Bukin function N6
- The Cross-In-Tray function
- The Drop-Wave function
- The Eggholder function
- The Holder Table function
- The Levy function
- The Levy function N13
- The Rastrigin function
- The Schaffer function N.2
- The Schaffer function N.4
- The Shubert function
- The Rotated Hyper-Ellipsoid function
- The Sum Squares function
- The Booth function
- The Mccormick function
- The Power Sum function
- The Three-Hump Camel function
- The Easom function
- The Michalewicz function
- The Beale function
- The Goldstein-Price function
- The Perm function
- The Griewank function
- The Bohachevsky function
- The Sphere function
- The Rosenbrock function
- The Styblinski-Tang function
- Summary
- Keep reading
- Other Books You May Enjoy
Drawbacks
-
No Comment
..................Content has been hidden....................
You can't read the all page of ebook, please click here login for view all page.