Course Outline
Machine Learning
Introduction to Machine Learning for Government
- Applications of machine learning in public sector workflows and governance
- Supervised versus unsupervised learning
- Machine learning algorithms
- Regression
- Classification
- Clustering
- Recommender System
- Anomaly Detection
- Reinforcement Learning
Regression for Government
- Simple & Multiple Regression
- Least Square Method
- Estimating the Coefficients
- Assessing the Accuracy of the Coefficient Estimates
- Assessing the Accuracy of the Model
- Post Estimation Analysis
- Other Considerations in Regression Models
- Qualitative Predictors
- Extensions of Linear Models
- Potential Problems
- Bias-variance trade-off (under-fitting/over-fitting) for regression models
Resampling Methods for Government
- Cross-Validation
- The Validation Set Approach
- Leave-One-Out Cross-Validation
- k-Fold Cross-Validation
- Bias-Variance Trade-Off for k-Fold
- The Bootstrap
Model Selection and Regularization for Government
- Subset Selection
- Best Subset Selection
- Stepwise Selection
- Choosing the Optimal Model
- Shrinkage Methods/Regularization
- Ridge Regression
- Lasso & Elastic Net
- Selecting the Tuning Parameter
- Dimension Reduction Methods
- Principal Components Regression
- Partial Least Squares
Classification for Government
Logistic Regression for Government
- The Logistic Model Cost Function
- Estimating the Coefficients
- Making Predictions
- Odds Ratio
- Performance Evaluation Matrices
- Sensitivity/Specificity/PPV/NPV
- Precision
- ROC Curve
- Multiple Logistic Regression
- Logistic Regression for >2 Response Classes
- Regularized Logistic Regression
Linear Discriminant Analysis for Government
- Using Bayes’ Theorem for Classification
- Linear Discriminant Analysis for p=1
- Linear Discriminant Analysis for p>1
Quadratic Discriminant Analysis for Government
K-Nearest Neighbors for Government
- Classification with Non-Linear Decision Boundaries
Support Vector Machines for Government
- Optimization Objective
- The Maximal Margin Classifier
- Kernels
- One-Versus-One Classification
- One-Versus-All Classification
Comparison of Classification Methods for Government
Deep Learning for Government
Introduction to Deep Learning for Government
Artificial Neural Networks (ANNs) for Government
- Biological neurons and artificial neurons
- Non-linear Hypothesis
- Model Representation
- Examples & Intuitions
- Transfer Function/Activation Functions
- Typical Classes of Network Architectures
- Feedforward ANN
- Multi-layer Feedforward Networks
- Backpropagation Algorithm
- Backpropagation - Training and Convergence
- Functional Approximation with Backpropagation
- Practical and Design Issues of Backpropagation Learning
Deep Learning for Government
- Artificial Intelligence & Deep Learning for Government
- Softmax Regression for Government
- Self-Taught Learning for Government
- Deep Networks for Government
- Demos and Applications for Government
Lab: Getting Started with R for Government
- Introduction to R for Government
- Basic Commands & Libraries for Government
- Data Manipulation for Government
- Importing & Exporting Data for Government
- Graphical and Numerical Summaries for Government
- Writing Functions for Government
Regression Lab for Government
- Simple & Multiple Linear Regression for Government
- Interaction Terms for Government
- Non-Linear Transformations for Government
- Dummy Variable Regression for Government
- Cross-Validation and the Bootstrap for Government
- Subset Selection Methods for Government
- Penalization (Ridge, Lasso, Elastic Net) for Government
Classification Lab for Government
- Logistic Regression, LDA, QDA, and KNN for Government
- Resampling & Regularization for Government
- Support Vector Machine for Government
Notes:
- For ML algorithms, case studies will be used to discuss their application, advantages, and potential issues in the context of government operations.
- Analysis of different datasets will be performed using R for government.
Requirements
- A basic understanding of statistical concepts is desirable.
Audience for Government
- Data scientists
- Machine learning engineers
- Software developers with an interest in artificial intelligence
- Researchers focused on data modeling
- Professionals seeking to implement machine learning solutions in business or industry contexts
Testimonials (6)
We had an overview about Machine Learning, Neural Networks, AI with practical examples.
Catalin - DB Global Technology SRL
Course - Machine Learning and Deep Learning
Last day with the AI
Ovidiu - DB Global Technology SRL
Course - Machine Learning and Deep Learning
The examples that were picked, shared with us and explained
Cristina - DB Global Technology SRL
Course - Machine Learning and Deep Learning
I really enjoyed the coverage and depth of topics.
Anirban Basu
Course - Machine Learning and Deep Learning
The training provided the right foundation that allows us to further to expand on, by showing how theory and practice go hand in hand. It actually got me more interested in the subject than I was before.
Jean-Paul van Tillo
Course - Machine Learning and Deep Learning
We have gotten a lot more insight in to the subject matter. Some nice discussion were made with some real subjects within our company.
