Welcome to Neural Network Modeling. I’m Robert Blanchard. I teach Advanced Analytics at SAS. We’re at an exciting time because the rise of big data parallels impressive advancements in machine learning.
The neural network course you’re about to embark on will cover key machine learning concepts. You’ll learn theoretical and practical issues for fitting a neural network that include how to choose an appropriate neural network architecture and how to determine the relevant training method.
We’ll begin the course with an introduction to neural networks. Then we’ll discuss network architecture, followed by an examination of the learning process used by neural networks. This is an advanced course, but don’t worry. I’ll give you practical business tips whenever possible. Let’s get started.
Course Curriculum
| Neural Network Modeling- Course Overview | |||
| Neural Network Modeling- Course Overview | 00:00:00 | ||
| Important notes about the Demonstrations and Exercises in this course File | |||
| Important notes about the Demonstrations and Exercises in this course File | 00:00:00 | ||
| 1.1a- Introduction to Neural Networks- Introduction | |||
| 1.1a- Introduction to Neural Networks- Introduction | 00:00:00 | ||
| 1.1b- Introduction to Neural Networks- Objectives | |||
| 1.1b- Introduction to Neural Networks- Objectives | 00:00:00 | ||
| 1.2a- Biological Brain | |||
| 1.2a- Biological Brain | 00:00:00 | ||
| 1.2b- Types of Artificial Neural Networks | |||
| 1.2b- Types of Artificial Neural Networks | 00:00:00 | ||
| 1.2c- Artificial Neuron | |||
| 1.2c- Artificial Neuron | 00:00:00 | ||
| 1.2d- Learning Rules | |||
| 1.2d- Learning Rules | 00:00:00 | ||
| 1.2e- Perceptron | |||
| 1.2e- Perceptron | 00:00:00 | ||
| 1.2f- Truth Tables and Linear Separability | |||
| 1.2f- Truth Tables and Linear Separability | 00:00:00 | ||
| 1.2g- Generalized Delta Rule | |||
| 1.2g- Generalized Delta Rule | 00:00:00 | ||
| 1.2h- Mixture-of-Experts Networks | |||
| 1.2h- Mixture-of-Experts Networks | 00:00:00 | ||
| 1.3a- Modeling Nonlinearities with Traditional Methods | |||
| 1.3a- Modeling Nonlinearities with Traditional Methods | 00:00:00 | ||
| 1.3b- Nonlinear Regression | |||
| 1.3b- Nonlinear Regression | 00:00:00 | ||
| 1.3c- Demo Nonlinear Regression, Part 1 | |||
| 1.3c- Demo Nonlinear Regression, Part 1 | 00:00:00 | ||
| 1.3d- Demo Nonlinear Regression, Part 2 | |||
| 1.3d- Demo Nonlinear Regression, Part 2 | 00:00:00 | ||
| 1.3e- Nonparametric Regression | |||
| 1.3e- Nonparametric Regression | 00:00:00 | ||
| 1.3f- Demo Nonparametric Regression | |||
| 1.3f- Demo Nonparametric Regression | 00:00:00 | ||
| 1.3g- Limitations of Traditional Approaches | |||
| 1.3g- Limitations of Traditional Approaches | 00:00:00 | ||
| 1.4a- Deciding Whether to Use a Neural Network | |||
| 1.4a- Deciding Whether to Use a Neural Network | 00:00:00 | ||
| 1.4b- Advantages of Neural Networks | |||
| 1.4b- Advantages of Neural Networks | 00:00:00 | ||
| 1.4c- Disadvantages of Neural Networks | |||
| 1.4c- Disadvantages of Neural Networks | 00:00:00 | ||
| 1.4d- Demo Two-Spirals Problem | |||
| 1.4d- Demo Two-Spirals Problem | 00:00:00 | ||
| 2.1a- Network Architecture- Introduction | |||
| 2.1a- Network Architecture- Introduction | 00:00:00 | ||
| 2.1b-Network Architecture- Objectives | |||
| 2.1b-Network Architecture- Objectives | 00:00:00 | ||
| 2.2a- Linear Perceptron | |||
| 2.2a- Linear Perceptron | 00:00:00 | ||
| 2.2b- Demo Modeling Assorted Target Distributions, Part 1 | |||
| 2.2b- Demo Modeling Assorted Target Distributions, Part 1 | 00:00:00 | ||
| 2.2c- Demo Modeling Assorted Target Distributions, Part 2 | |||
| 2.2c- Demo Modeling Assorted Target Distributions, Part 2 | 00:00:00 | ||
| 2.3a- Multilayer Perceptron with a Single Hidden Layer | |||
| 2.3a- Multilayer Perceptron with a Single Hidden Layer | 00:00:00 | ||
| 2.3b- Multilayer Perceptron with Multiple Hidden Layers | |||
| 2.3b- Multilayer Perceptron with Multiple Hidden Layers | 00:00:00 | ||
| 2.3c- Sigmoid | |||
| 2.3c- Sigmoid | 00:00:00 | ||
| 2.3d- Optimal Number of Hidden Units | |||
| 2.3d- Optimal Number of Hidden Units | 00:00:00 | ||
| 2.3e- Demo Compositional Data, Part 1 | |||
| 2.3e- Demo Compositional Data, Part 1 | 00:00:00 | ||
| 2.3f- Demo Compositional Data, Part 2 | |||
| 2.3f- Demo Compositional Data, Part 2 | 00:00:00 | ||
| 2.3h- Exercise Constructing a Multilayer Perceptron Using PROC NLIN | |||
| 2.3h- Exercise Constructing a Multilayer Perceptron Using PROC NLIN | 00:00:00 | ||
| 2.3h- Exercise Solution- Constructing a Multilayer Perceptron Using PROC NLIN | |||
| 2.3h- Exercise Solution- Constructing a Multilayer Perceptron Using PROC NLIN | 00:00:00 | ||
| 2.4a- Overview of Radial Basis Functions | |||
| 2.4a- Overview of Radial Basis Functions | 00:00:00 | ||
| 2.4b- Inside the Radial Basis Function | |||
| 2.4b- Inside the Radial Basis Function | 00:00:00 | ||
| 2.4c- Ordinary Radial Basis Function2.4c- Ordinary Radial Basis Function | |||
| 2.4c- Ordinary Radial Basis Function | 00:00:00 | ||
| 2.4d- Normalized Radial Basis Function | |||
| 2.4d- Normalized Radial Basis Function | 00:00:00 | ||
| 2.4e- Demo Plotting Basis Functions | |||
| 2.4e- Demo Plotting Basis Functions | 00:00:00 | ||
| 2.4g- Exercise Comparing Architectures | |||
| 2.4g- Exercise Comparing Architectures | 00:00:00 | ||
| 2.4g- Exercise Solution- Comparing Architectures | |||
| 2.4g- Exercise Solution- Comparing Architectures | 00:00:00 | ||
| 3.1a- Learning- Introduction | |||
| 3.1a- Learning- Introduction | 00:00:00 | ||
| 3.1b- Learning- Objectives | |||
| 3.1b- Learning- Objectives | 00:00:00 | ||
| 3.2a- Global and Local Minimal | |||
| 3.2a- Global and Local Minimal | 00:00:00 | ||
| 3.2b- Initialization Procedure | |||
| 3.2b- Initialization Procedure | 00:00:00 | ||
| 3.2c- Preliminary Training | |||
| 3.2c- Preliminary Training | 00:00:00 | ||
| 3.2d- Convergence Criteria | |||
| 3.2d- Convergence Criteria | 00:00:00 | ||
| 3.2e- Improving Generalization | |||
| 3.2e- Improving Generalization | 00:00:00 | ||
| 3.2f- Demo Early Stopping, Part 1 | |||
| 3.2f- Demo Early Stopping, Part 1 | 00:00:00 | ||
| 3.2g- Demo Early Stopping, Part 2 | |||
| 3.2g- Demo Early Stopping, Part 2 | 00:00:00 | ||
| 3.2i- Exercise Network Initialization | |||
| 3.2i- Exercise Network Initialization | 00:00:00 | ||
| 3.2i- Exercise Solution Network Initialization | |||
| 3.2i- Exercise Solution Network Initialization | 00:00:00 | ||
| 3.3a- Ordinary Least Squares Estimation | |||
| 3.3a- Ordinary Least Squares Estimation | 00:00:00 | ||
| 3.3b- Maximum Likelihood Estimation | |||
| 3.3b- Maximum Likelihood Estimation | 00:00:00 | ||
| 3.3c- Deviance | |||
| 3.3c- Deviance | 00:00:00 | ||
| 3.3d- Robust Estimation and Appropriate Network Function Combinations | |||
| 3.3d- Robust Estimation and Appropriate Network Function Combinations | 00:00:00 | ||
| 3.3e- Demo Robust Networks | |||
| 3.3e- Demo Robust Networks | 00:00:00 | ||
| 3.3g- Exercise Modeling Count Data | |||
| 3.3g- Exercise Modeling Count Data | 00:00:00 | ||
| 3.3g- Exercise SOlution Modeling Count Data | |||
| 3.3g- Exercise SOlution Modeling Count Data | 00:00:00 | ||
| 3.4a- Iterative Updating | |||
| 3.4a- Iterative Updating | 00:00:00 | ||
| 3.4b- Propagation Optimization Methods | |||
| 3.4b- Propagation Optimization Methods | 00:00:00 | ||
| 3.4c- Other Optimization Methods | |||
| 3.4c- Other Optimization Methods | 00:00:00 | ||
| 3.4d- Demo Training Tracks | |||
| 3.4d- Demo Training Tracks | 00:00:00 | ||
| 4.1a- The Neural Procedure- Introduction | |||
| 4.1a- The Neural Procedure- Introduction | 00:00:00 | ||
| 4.1b- The Neural Procedure- Objectives | |||
| 4.1b- The Neural Procedure- Objectives | 00:00:00 | ||
| 4.2a- Using PROC NEURAL | |||
| 4.2a- Using PROC NEURAL | 00:00:00 | ||
| 4.2b- Demo Linear Perceptrons Using PROC NEURAL | |||
| 4.2b- Demo Linear Perceptrons Using PROC NEURAL | 00:00:00 | ||
| 4.3a- Using Weights to Select Useful Inputs | |||
| 4.3a- Using Weights to Select Useful Inputs | 00:00:00 | ||
| 4.3b- Demo Variable Importance | |||
| 4.3b- Demo Variable Importance | 00:00:00 | ||
| 4.3c- Sensitivity-Based Pruning | |||
| 4.3c- Sensitivity-Based Pruning | 00:00:00 | ||
| 4.3d- Demo Sensitivity-Based Pruning | |||
| 4.3d- Demo Sensitivity-Based Pruning | 00:00:00 | ||
| 4.3f- Exercise Sensitivity-Based Pruning (Bernoulli Distributed Target) | |||
| 4.3f- Exercise Sensitivity-Based Pruning (Bernoulli Distributed Target) | 00:00:00 | ||
| 4.3f- Exercise Solution Sensitivity-Based Pruning (Bernoulli Distributed Target) | |||
| 4.3f- Exercise Solution Sensitivity-Based Pruning (Bernoulli Distributed Target) | 00:00:00 | ||
| 4.4a- Sequential Network Construction | |||
| 4.4a- Sequential Network Construction | 00:00:00 | ||
| 4.4b- Demo Sequential Network Construction | |||
| 4.4b- Demo Sequential Network Construction | 00:00:00 | ||
| 4.4d- Exercise Sequential Network Construction | |||
| 4.4d- Exercise Sequential Network Construction | 00:00:00 | ||
| 4.4d- Exercise Solution Sequential Network Construction | |||
| 4.4d- Exercise Solution Sequential Network Construction | 00:00:00 | ||
| 4.5a- Self Study | |||
| 4.5a- Self Study | 00:00:00 | ||
| 4.6a- Gradient Descent | |||
| 4.6a- Gradient Descent | 00:00:00 | ||
| 4.6b- Demo Mini-Batch Gradient Descent, Part 1 | |||
| 4.6b- Demo Mini-Batch Gradient Descent, Part 1 | 00:00:00 | ||
| 4.6c- Demo Mini-Batch Gradient Descent, Part 2 | |||
| 4.6c- Demo Mini-Batch Gradient Descent, Part 2 | 00:00:00 | ||
| 5.1a-Augmented Networks- Introduction | |||
| 5.1a-Augmented Networks- Introduction | 00:00:00 | ||
| 5.1b-Augmented Networks Objectives | |||
| 5.1b-Augmented Networks Objectives | 00:00:00 | ||
| 5.2a- Time Series | |||
| 5.2a- Time Series | 00:00:00 | ||
| 5.2b- Neural Networks for Time Series | |||
| 5.2b- Neural Networks for Time Series | 00:00:00 | ||
| 5.2c- Long Short-Term Memory | |||
| 5.2c- Long Short-Term Memory | 00:00:00 | ||
| 5.2d- Reservoir Computing | |||
| 5.2d- Reservoir Computing | 00:00:00 | ||
| 5.2e- Demo Implementing a Time Delay Neural Network, Part 1 | |||
| 5.2e- Demo Implementing a Time Delay Neural Network, Part 1 | 00:00:00 | ||
| 5.2f- Demo Implementing a Time Delay Neural Network, Part 2 | |||
| 5.2f- Demo Implementing a Time Delay Neural Network, Part 2 | 00:00:00 | ||
| 5.3a- Surrogate Models | |||
| 5.3a- Surrogate Models | 00:00:00 | ||
| 5.3b- Demo Interpreting a Neural Network with a Continuous Target | |||
| 5.3b- Demo Interpreting a Neural Network with a Continuous Target | 00:00:00 | ||
| 5.3c- Self-Study Demo Interpreting a Neural Network with a Categorical Target | |||
| 5.3c- Self-Study Demo Interpreting a Neural Network with a Categorical Target | 00:00:00 | ||
| 6.1a- Hp Neural Code- Introduction | |||
| 6.1a- Hp Neural Code- Introduction | 00:00:00 | ||
| 6.1b- Hp Neural Code- Objectives | |||
| 6.1b- Hp Neural Code- Objectives | 00:00:00 | ||
| 6.2a- Thriving in the Big Data Era | |||
| 6.2a- Thriving in the Big Data Era | 00:00:00 | ||
| 6.2b- SAS High-Performance Analytics | |||
| 6.2b- SAS High-Performance Analytics | 00:00:00 | ||
| 6.3a- HP Neural Node | |||
| 6.3a- HP Neural Node | 00:00:00 | ||
| 6.3b- Demo Comparing One- and Two-Layer Networks, Part 1 | |||
| 6.3b- Demo Comparing One- and Two-Layer Networks, Part 1 | 00:00:00 | ||
| 6.3c- Demo Comparing One- and Two-Layer Networks, Part 2 | |||
| 6.3c- Demo Comparing One- and Two-Layer Networks, Part 2 | 00:00:00 | ||
| Chapter 7: The AutoNeural Node (Self Study) | |||
| Chapter 7: The AutoNeural Node (Self Study) | 00:00:00 | ||
| Course Notes: Neural Network Modeling File | |||
| Course Notes: Neural Network Modeling File | 00:00:00 | ||
Course Reviews
No Reviews found for this course.
0 STUDENTS ENROLLED
