•Predictive Modeling: Regression and Classification Algorithms, Supervised and Unsupervised Algorithms, Performance Measures and Metrics
•Convolutional Neural Networks, Gradient Descent Algorithm, Pretrained CNNs: Feature Extraction and Fine Tuning, Sequence Models – RNN, Word Embeddings
•Implementation of ML algorithms using Python-centric Libraries.

•Introduction to Generative AI
•Variational autoencoders (VAEs)
•Transformer Architecture 
•Encoder only Models - BERT
•Decoder only Models - Llama, ChatGPT
•Encoder and Decoder model - T5 and BERT
•LLMOps Lifecycle

•MLOps Vs. DevOps
•ML Project Life Cycle
•ML Production Infrastructure
•MLOps Architecture
•MLOps on Cloud 
•MLOps Data Processing Life Cycle with Data Storage

•Review of Operating System Concepts
•Basic Principles of Containerisation
•Concepts of Version Management System and CI/CD in Data Pipelines
•Introduction to Docker
•Dockerfiles, Images, and Containers
•Docker Networking
•Docker Compose
•Introduction to Kafka and its Implementation
•Introduction to Apache Airflow
•Implementation of Pipeline using Ray