Step03
ClimbedIntermediateWorkshop
Machine Learning from Scratch
Regression to Classification
- Saturday, 19 September 2026
- 9:30 am – 4:30 pm IST
- Main Seminar Hall, Block A, College of Engineering Kidangoor
No black boxes on this step. You'll implement linear and logistic regression from first principles, watch the loss curve fall, then graduate to scikit-learn pipelines, cross-validation and the metrics that actually matter when a model goes to production.
You'll be able to…
- Implement gradient descent in NumPy
- Train and evaluate regression and classification models
- Choose between accuracy, precision, recall and F1
- Avoid data leakage with proper train/test splits
Prerequisites
- Step 02 or comfortable with NumPy & Pandas
- High-school algebra
What to bring
- Laptop (8 GB RAM recommended) and charger
- Python 3.11+ installed
- A Google account for Colab
- Curiosity — plenty of it
Agenda
- 09:30Check-in & coffeeGrab your badge, find a seat, connect to Wi-Fi.
- 10:00Learning = minimising a loss
- 11:30Short break
- 11:45Guided walkthroughLive coding with the speaker — follow along on your laptop.
- 13:00Lunch
- 14:00Predict KSRTC bus delays challengeWork in pairs. Mentors float between tables.
- 16:00Show & tellThree teams demo what they built.
- 16:30Wrap-up & next step preview
Speaker
Dr. Meera Krishnan
Assistant Professor, CSE, College of Engineering Kidangoor
Meera researches interpretable machine learning and fairness in healthcare models. She has supervised 20+ student ML projects.
Resources
Winners
- 1stGradient GangBus delay predictor (MAE 3.2 min)
- 2ndOverfit ClubFeature-engineered random forest
Highlights
- Photo · Step 03
- Photo · Step 03
Venue
Main Seminar Hall, Block A, College of Engineering Kidangoor
Kidangoor South P.O., Kottayam, Kerala 686583, India