Machine Learning
Go deep into ML algorithms, model optimization, and deep learning fundamentals with hands-on projects.
Who This Course Is For
- Data analysts/scientists wanting to specialize in ML
- Software developers moving into ML engineering
- Graduates with Python and basic stats background
Prerequisites
- Working knowledge of Python and pandas/NumPy
- Basic statistics (covered in a refresher module)
Full Curriculum
7 modules · 100 hours of live instruction
1ML Foundations & Math Refresher~10 hrs
- Linear algebra and calculus essentials
- Probability refresher
- Bias-variance tradeoff
2Supervised Learning~20 hrs
- Linear/logistic regression
- Decision trees, Random Forest, SVM
- Gradient boosting (XGBoost, LightGBM)
3Unsupervised Learning~12 hrs
- K-means and hierarchical clustering
- Dimensionality reduction (PCA)
- Anomaly detection basics
4Model Evaluation & Tuning~10 hrs
- Cross-validation strategies
- Hyperparameter tuning (GridSearch, Optuna)
- Handling imbalanced datasets
5Deep Learning Fundamentals~20 hrs
- Neural networks with TensorFlow/Keras
- CNNs for image data
- RNNs/LSTMs for sequence data
6MLOps Basics & Deployment~12 hrs
- Model serialization
- Serving models via FastAPI/Flask
- Basic model monitoring
7Capstone Projects~16 hrs
- End-to-end ML pipeline on a real dataset
- Deep learning image/text project
- Portfolio and interview preparation
Tools & Technologies Covered
Hands-On Projects
Credit Risk Prediction Model
Gradient-boosted classification model predicting loan default risk with full evaluation report.
Image Classification with CNNs
Convolutional neural network trained to classify images across multiple categories.
Customer Segmentation
Unsupervised clustering project segmenting customers for targeted marketing strategy.
What You'll Be Able to Do
Frequently Asked Questions
Do I need Data Science course before this one?
Not mandatory, but recommended if you are new to Python/pandas/statistics — this course assumes that foundation and moves faster into algorithms.
How much math is really required?
A working understanding of linear algebra, calculus, and probability is refreshed in Module 1 — you do not need a math degree, but comfort with the concepts is expected.
What is the batch schedule?
Weekday batches run 7-9 PM IST; weekend batches run Saturday-Sunday 10 AM-1 PM IST, recorded for lifetime access.
Does this cover Generative AI/LLMs?
This course covers classical ML and deep learning foundations (CNNs/RNNs); LLMs, prompt engineering, and RAG are covered in our dedicated AI & Generative AI course.
Is placement support included?
Yes — resume building, mock interviews, and referrals to our hiring partner network are included.
What salary can I expect after this course?
ML engineer/data scientist roles for candidates with strong project portfolios typically start at ₹7-12 LPA depending on prior experience.
Related Courses in Data Science & AI
Ready to Start Machine Learning?
Next batch enrolling now — live online, with placement support included.