📚 Syllabus & Course Curriculum
AI & Machine Learning in Healthcare
Module-by-module breakdown of Artificial Intelligence and Machine Learning Essentials, from foundations to a certified capstone project.
Framing
• Supervised, unsupervised and reinforcement learning and the problems each suits
• Recognising a problem that does not need machine learning at all
• Data requirements and the label cost that decides most projects
Workflow
• NumPy, pandas and scikit-learn as the working toolchain
• Train, validation and test splits, and the leakage that inflates every beginner result
• Cross-validation and the difference between tuning and evaluating
Algorithms
• Linear and logistic regression as interpretable baselines that are hard to beat
• Decision trees, random forests and gradient boosting on tabular data
• k-means and PCA for structure and dimensionality reduction
Evaluation
• Accuracy, precision, recall, F1 and ROC AUC and when each misleads
• Class imbalance and why accuracy is meaningless for a rare outcome
• Overfitting, underfitting and reading a learning curve
Deep Learning
• Perceptrons, backpropagation and gradient descent conceptually
• CNNs for images and transformers for sequences, and when each is warranted
• Transfer learning as the practical route when data is limited
Earn government-registered certification in Artificial Intelligence and Machine Learning Essentials
e-Certificate and e-Marksheet issued on successful completion.
