BTech / BCA Track8 Weeks CohortTopic-Linked Attendance Enabled
Machine Learning — Advanced
Master advanced ML and deep learning techniques. Covers Random Forests, XGBoost, LightGBM, PCA, Neural Networks with Keras/TensorFlow, SMOTE for imbalanced data, and FastAPI model deployment.
Key Skills You Will Master:
XGBoostLightGBMPCA & t-SNENeural NetworksKeras/TensorFlowFastAPI Deployment
Lead Instructor
Vikramaditya Iyer
Ex-Tech Lead & STEM Mentor
Total Program Fee (Full Cohort + Materials)
₹3,999₹5,999Save 33%
Choose Your CohortLive Interactive
Next cohort starting next weekend • 5:00 PM IST
10 Live Hybrid Interactive Sessions
10 Granular Tracked Topics
Downloadable datasets, cheatsheets & Jupyter notebooks
Verifiable Certificate upon 85%+ topic completion
Syllabus Breakdown
Course Structure & Tracked Topics
Click on any module to view live sessions and the exact list of topics tested & tracked for attendance.
Session 1
Session 1: Random Forests & Bagging
90 mins
Attendance-Tracked Topics (1):
1Bootstrap Aggregation, Feature Randomness, OOB Error
Session 2
Session 2: Gradient Boosting Fundamentals
90 mins
Attendance-Tracked Topics (1):
1AdaBoost & Gradient Boosted Decision Trees (GBDT)
Session 3
Session 3: Modern XGBoost & LightGBM
90 mins
Attendance-Tracked Topics (1):
1Histogram Binning, Early Stopping & GPU Training
Beginner Milestone: Competitive Tabular Prediction Benchmark
Train and fine-tune Random Forest, XGBoost, and LightGBM models on a Kaggle-style challenge dataset.
Deliverable: Benchmark report and cross-validation logs.
Session 4
Session 4: Advanced Clustering (DBSCAN)
90 mins
Attendance-Tracked Topics (1):
1Density-based Clustering, eps, min_samples, Noise Detection
Session 5
Session 5: PCA & t-SNE Dimensionality Reduction
90 mins
Attendance-Tracked Topics (1):
1Eigenvectors, Explained Variance, 2D/3D Data Projections
Session 6
Session 6: Neural Networks & Perceptrons
90 mins
Attendance-Tracked Topics (1):
1Perceptron, Activation Functions (ReLU, Softmax), Forward Pass
Session 7
Session 7: Deep Models with Keras / TensorFlow
90 mins
Attendance-Tracked Topics (1):
1Sequential Models, Dense Layers, Loss Functions & Adam
Intermediate Milestone: High-Dimensional Image & Anomaly Classifier
Apply PCA for dimensionality reduction followed by a Keras Deep Neural Network classifier.
Deliverable: Keras model pipeline with training loss and accuracy plots.
Session 8
Session 8: Handling Class Imbalance with SMOTE
90 mins
Attendance-Tracked Topics (1):
1Synthetic Minority Over-sampling (SMOTE) & Class Weights
Session 9
Session 9: Model Serialization & FastAPI Deployment
90 mins
Attendance-Tracked Topics (1):
1joblib Serialization & Real-Time FastAPI Microservices
Session 10
Session 10: Final Production Capstone Showcase
90 mins
Attendance-Tracked Topics (1):
1Fraud Detection API Microservice Defense
Graduation Capstone
Production Real-Time Fraud Detection API Microservice
Build an XGBoost + Neural Network fraud detection service with SMOTE imbalance handling and containerized FastAPI endpoints.
Deliverable:
FastAPI Microservice + Docker Container + Live Swagger UI
What You Will Be Able To Do
Train gradient-boosted ensemble models (XGBoost/LightGBM) on tabular challenges
Implement PCA and t-SNE for high-dimensional data reduction
Build and train Deep Neural Networks with Keras, Adam optimizers, and dropout
Package and deploy ML models as real-time REST API microservices with FastAPI
Prerequisites
Machine Learning Basic and Python proficiency.
Unsure if this fits your current grade?
Schedule a 10-minute discovery call with our academic advisor.