Liner Regression: Loss, Parameters, Gradient Descent, HyperParameters & Programming

Logistic Regression: Calculating a Probability, Loss, and regularization

Classification: Thresholds and the Confusion matrix, Accuracy, Recall, Precision, and related metrics, ROC and AUC, Prediction bias, Multi-class classification, and programming.

Numerical Data: The model ingests data with feature vectors, programming, normalization, binning, scratching, and qualities of good numerical features and polynomial transforms.

Categorical Data: Vocabulary and One-hot encoding, common issues with categorical data, Feature crosses(Exercise).

Datasets, generalization, and Overfitting: Data characteristics, Labels, Imbalances datasets, Dividing the original dataset, Transforming Data, Generalization, Overfitting, Model complexity, L2 regularization, Interpreting loss curves.

Neural Networks: Nodes and hidden layers, Activation functions, Training using backpropagation, Interactive Exercise, and Multi-class classification.

Embeddings: Embedding space and static embeddings and Obtain embeddings.

Large Language Models: Fine-tuning, distillation, and prompt engineering.

Production ML Systems: Static vs dynamic(training, inference), Transforming data, Deployment testing, and Monitoring pipelines.

Automated Machine Learning: Benefits and Limitations.

Fairness: bias(Types, Identifying, Mitigation, and Evaluation), Demographic parity, Equality of opportunity, Counterfactual fairness & fairness.

Problem Framing: Understanding and Framing an ML problem, implementing a model.

Managing ML Projects: Development phases, Assembling a team, Working with stakeholders, Feasibility, Planning, Measuring success, ML pipelines, and Productionization.