Notes on machine learning.

Data

• Synthetic Data Generation
  • Using Synthetic data with SDV and Gaussian copulas, Synthetic data with SDV and CTGAN and Synthetic data with SDV and CopulaGAN.

Explainabilty

• Explainability

Drift

• Introduction to Concept Drift in Machine Learning
• Model drift
• Data drift

Time-series

• Time-series analysis
• Streaming anomaly detection

Clustering

• K-means clustering

Fairness

• Fairness in Machine Learning
• Model fairness

Metrics

Error metrics

• Distance metrics

Performance

• Model performance metrics

Transformations

• Feature scaling

Optimisation

• Gradient descent
• Stochastic Gradient Descent
• Stochastic Gradient descent with momentum
• Mini-Batch Gradient Descent
• Adagrad
• RMSProp
• AdaDelta
• Adam
• Gradient-free optimisation

RNN

• LSTM

Statistics

• Statistics

• Streaming statistics

• Thompson sampling

• Statistical dependence

Model selection

• Cross-validation

Kernel functions

Kernels can be interpreted as “similarity functions”. Typically they are functions that take two $n$-dimensional points and produce a scalar. In the following sections we look at some well-known kernels and their typical applications.

• Kernel functions

Unsupervised methods

• Self-organising maps

Supervised methods

Methods pertaining to Supervised learning.

Techniques such as:

• Random Forest

Regression

• Gaussian Process Regression

Frameworks

• Cookiecutter Data Science
• Scikit-learn
• Model serving

Theory

• The difference between AI and Machine Learning