Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
1. Grasping Classification via Nearest Neighbors
- The kNN algorithm
- Distance calculation
- Selecting an optimal k value
- Data preparation for kNN
- Why is the kNN algorithm considered lazy?
2. Grasping Naive Bayes
- Fundamental concepts of Bayesian methods
- Probability
- Joint probability
- Conditional probability using Bayes' theorem
- The Naive Bayes algorithm
- Naive Bayes classification
- The Laplace estimator
- Applying numeric features with Naive Bayes
3. Grasping Decision Trees
- Divide and conquer strategy
- The C5.0 decision tree algorithm
- Selecting the optimal split
- Pruning the decision tree
4. Grasping Classification Rules
- Separate and conquer approach
- The One Rule algorithm
- The RIPPER algorithm
- Deriving rules from decision trees
5. Grasping Regression
- Simple linear regression
- Ordinary least squares estimation
- Correlations
- Multiple linear regression
6. Grasping Regression Trees and Model Trees
- Integrating regression into trees
7. Grasping Neural Networks
- From biological to artificial neurons
- Activation functions
- Network topology
- Determining the number of layers
- The direction of information flow
- Specifying the number of nodes per layer
- Training neural networks via backpropagation
8. Grasping Support Vector Machines
- Classification using hyperplanes
- Identifying the maximum margin
- Scenarios with linearly separable data
- Scenarios with non-linearly separable data
- Employing kernels for non-linear spaces
9. Grasping Association Rules
- The Apriori algorithm for association rule learning
- Evaluating rule interest – support and confidence
- Constructing a rule set using the Apriori principle
10. Grasping Clustering
- Clustering as a machine learning task
- The k-means clustering algorithm
- Utilizing distance for cluster assignment and updates
- Determining the appropriate number of clusters
11. Evaluating Performance for Classification
- Handling classification prediction data
- Examining confusion matrices in detail
- Assessing performance using confusion matrices
- Beyond accuracy – alternative performance metrics
- The kappa statistic
- Sensitivity and specificity
- Precision and recall
- The F-measure
- Visualizing performance trade-offs
- ROC curves
- Estimating future performance
- The holdout method
- Cross-validation
- Bootstrap sampling
12. Optimizing Base Models for Enhanced Performance
- Utilizing caret for automated parameter tuning
- Developing a basic tuned model
- Customizing the tuning workflow
- Enhancing model performance through meta-learning
- Understanding ensemble methods
- Bagging
- Boosting
- Random forests
- Training random forests
- Evaluating random forest performance
13. Deep Learning
- Three Categories of Deep Learning
- Deep Autoencoders
- Pre-trained Deep Neural Networks
- Deep Stacking Networks
14. Discussion of Specific Application Domains
21 Hours
Testimonials (1)
Very flexible.
