skip to page content SBU
Carnegie Mellon University
95-897 Machine Learning Technologies
 Spring 2026
Home
Syllabus
Assignments
Notes

Course Syllabus (download as pdf)


LECTURES:

I will provide slides for the lectures. Those will be uploaded to Canvas before each lecture. Feel free to print them and bring them to class with you for annotating.

I will also assign optional readings from various book chapters per lecture. While those are optional, they are highly recommended for deepening your understanding. The recommended books are listed under Resources (see left tab). To stay on track, you are advised to attend all lectures, read the assigned book chapters (optional), and follow up with questions in lectures, office hours, recitations, and/or Piazza.

PART I. ML Fundamentals and Core Concepts

Week 1: ML Foundations & Classical Models I

  • Definition, Types, Applications of ML
  • The Machine Learning Workflow
  • Data Preprocessing and Feature Engineering
  • Classical Models I: **Linear Regression & Logistic Regression**

Week 2: Model Selection & Classical Models II

  • Model Evaluation, Selection, Generalization
  • Bias-Variance Trade-off, Overfitting, Underfitting
  • Metrics, Train-Test Split, Cross-Validation, **HPO**
  • Classical Models II: **Decision Trees**

Week 3: Classical Models II & Important Model Concepts

  • Classical Models II: **Ensemble Models** (RFs, Boosted DTs: XGBoost, LightGBM)
  • Important Model Concepts: **Uncertainty Estimation & Calibration**
  • Model **Interpretability** (Built-in vs. Post-hoc: SHAP, LIME)
  • **Robustness** (Adversarial/Shortcut learning), **Fairness**

Week 4: Important Model Concepts & Learning Paradigms

  • Learning Paradigms: **Supervised, Semi-supervised, Self-supervised Learning**
  • **Unsupervised Learning:** Clustering, Outlier Detection, Dim. Reduction
    • Clustering: k-means, DBSCAN
    • Outlier detection: kNN, IsolationForest, DeepSVDD, AEs
    • Dim. Reduction: PCA/Kernel PCA, t-SNE
  • Other Paradigms:
    • Active, Reinforcement, Meta, Continual, Federated, Transfer Learning

PART II. Advanced/Modern Models

Week 5: Neural Networks & Modern Architectures

  • Neural Networks (NN) (tabular data)
  • Other Architectures: **CNN/ResNet, RNN, LSTM** (image, sequence data)
  • Advanced Architectures: **Attention, Transformer**

PART III. ML on Specialized Data Modalities

Week 6: Tabular & Graph ML Models

  • **ML on Tabular Data (i.i.d.):**
    • Foundation models: TabPFN, FoM0D
  • **ML on Graphs (non-i.i.d.):**
    • Node embeddings (for node classification / link prediction)
    • Graph neural networks / transformers / foundation models

Week 7: Temporal, Text & Image ML Models

  • **ML on Temporal/Seq. Data:**
    • Models: ARIMA (classic), LSTM/TFT (modern), foundation models.
    • Tasks: Forecasting, anomaly detection, classification.
  • **ML on Text & Image:**
    • LLMs: BERT, GPTs for text generation / representation
    • ViT, DALL-E for image representation / generation
  • **Multimodal Learning:**
    • CLIP
    • BLIP-2: image captioning and visual QA, image-grounded dialogue

Final Exam