Machine Learning Practice
Applied ML with scikit-learn and modern tooling — features, pipelines, evaluation, and end-to-end model building.
§ 1Calendar
- Quiz 1—
- Quiz 2—
- End-term examination—
§ 2Previous Year Questions
No papers uploaded yet.
§ 3Resources
Course material2
-
Supplementary content (Drive folder)
drive.google.comIITM login required
-
Course YouTube channel
youtube.com
Notes3
-
Course notes
Notes and study material for this course.
iitmbsdegree.inby IITM BS Students' Corner -
Topic-wise notes
Topic-wise notes on ML Study Hub.
degreedost.comby ML Study Hub -
MLP notes on Medium
Written notes for the Machine Learning Practice course.
medium.comby Pratham Bhalla
Syllabus
The official course syllabus, transcribed from the IITM BS Data Science & Applications course booklet.
§ 1Course Description
This course introduces students to scikit-learn, a widely used Python machine learning library, providing hands-on problem solving experience with the methods and models covered in the theory course.
Lectures-Tutorials-Practicals-Credits: 4-0-0-4
§ 2Faculty
- Prof. Ashish Tendulkar, Google Research (Visiting Asst. Professor, Department of Computer Science and Engineering, IIT Madras)
§ 3Week-by-week
Week 1: Pandas - dataframes, selection, manipulation; Statistics.
Week 2: Scikit-learn - data loading, preprocessing (missing data, scaling, outliers); Feature selection; PCA.
Week 3: Pipelines and transformers; Preprocessing (imputation, scaling); Feature selection and PCA; Class imbalance; Demonstrations.
Week 4: Regression and evaluation; Regularisation and tuning; Classification (NB, KNN, SVM, trees); Ensembles; Neural networks.
Week 5: Regression on California housing - linear, KNN, trees; Ensembles; MLP; Baselines and demonstrations.
Week 6: Classification - evaluation; Models (SGD, logistic, NB, KNN, SVM, trees); Ensembles; Applications (MNIST, abalone, iris).
Week 7: Evaluation metrics - confusion matrix, accuracy, precision, recall, F1; Multiclass; Large-scale ML.
Week 8: Support Vector Machines using scikit-learn
Week 9: Clustering (K-means, HAC); Neural networks (MLP); ML workflow; Recommender systems.
Week 10: Decision Trees, Ensemble Learning and Random Forests (Continued)
Week 11: Transfer learning (theory and practice); Neural networks recap.
Week 12: Unsupervised learning
OPPE
Practice material for the Machine Learning Practice online proctored programming exams. No practice material has been shared for it yet. If you have some, please send it in.