Practical ML Program

The aim of this module is to provide an introduction to statistical analysis and its relevance to Machine Learning (ML) for data analysts. In this module, students will learn the basic concepts of descriptive and inferential statistics that are used to extract useful insights from data.

• Understanding the role of statistical analysis in data analysis
• Types of data and measurement scales
• Descriptive statistics: measures of central tendency and variability

The aim of this module is to provide an in-depth understanding of the various types of data distributions encountered in machine learning and how they can be used to make informed data-driven decisions

• Understanding and visualising data distributions
• Skewness and kurtosis
• The normal distribution

Point Estimates and Confidence Intervals are commonly used in scientific research, business, and other fields to make inferences about population parameters based on sample data. Understanding them is essential for making accurate and informed decisions based on statistical analyses.

• Point estimates and their interpretation
• Confidence intervals and their interpretation
• Using confidence intervals for hypothesis testing

Hypothesis testing is a statistical method used to determine whether there is a significant difference between two or more groups or datasets. Hypothesis testing is commonly used in scientific research and data analysis to draw conclusions and make decisions based on statistical evidence.

• The principles of hypothesis testing
• The null and alternative hypothesis
• Types of errors in hypothesis testing

The module on T-Tests and ANOVA covers statistical methods for comparing means between two or more groups. This module will cover the concepts of T-tests and ANOVA, as well as their practical application in machine learning and data analysis

• One-sample t-test
• Two-sample t-test
• ANOVA

The Correlations module is focused on statistical methods for examining the relationships between variables in a dataset. This module will cover the concepts of correlation analysis, including correlation coefficients, scatter plots, and other visualisations. It will also cover practical applications of correlation analysis in machine learning and data analysis.

• Understanding correlation
• Pearson correlation coefficient

The Chi-Squared Tests module is focused on statistical methods for testing the independence of categorical variables. This module will cover the concepts of these tests, including types of tests and their practical applications in machine learning and data analysis

• Chi-squared test for goodness of fit
• Chi-squared test for independence
• Chi-squared test for homogeneity

This module will cover the basic concepts of machine learning, including supervised and unsupervised learning, and the differences between them.

In this module we will also cover the concepts of linear regression, including simple and multiple regression, model evaluation, and prediction. The module will include hands-on exercises and practical applications of linear regression in machine learning, such as feature selection, model selection, and evaluation.

• What is machine learning?
• Types of machine learning: supervised, unsupervised, and reinforcement learning
• Linear regression: theory and implementation
• Evaluating regression models

The Logistic Regression module is focused on a popular machine learning technique for classification problems.

This module will cover the concepts of logistic regression, including the logistic function, the maximum likelihood estimation method, and model evaluation. It will also cover practical applications of logistic regression in machine learning and data analysis.

• Introduction to classification problems
• Binary and multi-class logistic regression
• Model evaluation and interpretation

The Decision Trees module is focused on a popular machine learning technique for both classification and regression problems. Decision trees are a supervised learning algorithm that is used to predict an outcome based on a set of predictors.

This module will cover the concepts of decision trees, including the process of building a tree, pruning techniques, and model evaluation. It will also cover practical applications of decision trees in machine learning and data analysis

• Decision tree theory and implementation
• Overfitting and pruning
• Ensemble methods: bagging and boosting

The Unsupervised Learning with K-Means module is focused on a popular machine learning technique for clustering problems. We will cover the concepts of K-Means, including how the algorithm works, choosing the optimal number of clusters, and model evaluation.

• Overview of unsupervised learning
• Clustering problems and K-Means algorithm

• Evaluating clustering performance
• Real-world examples of clustering

Density-Based Spatial Clustering of Applications with Noise (DBSCAN) is a clustering algorithm that groups together points that are close to each other in a high-density region, while identifying and ignoring points that are isolated or lie in low-density regions. 

This module will cover the concepts of DBSCAN, including how the algorithm works, choosing the optimal hyperparameters, and model evaluation. It will also cover practical applications of DBSCAN in machine learning and data analysis, such as clustering and outlier detection. 

• Introduction to density-based clustering
• DBSCAN algorithm and implementation
• Evaluating clustering performance

The Advanced Topics in Machine Learning module covers a range of advanced machine learning concepts and techniques that are used to improve the performance and accuracy of machine learning models. 

• Data splitting and cross-validation
• Scaling and normalization
• Regularization and overfitting prevention
• Hyperparameter tuning and grid search
• Gradient descent and optimization algorithms