AI & Machine Learning
Program Summary
-
Applied AI & Machine Learning Foundations
- AI vs Machine Learning vs Deep Learning
- The ML workflow: data → model → evaluation → deployment
- Data cleaning, exploratory data analysis and visualization
- Regression, classification and clustering algorithms
- Model evaluation, overfitting and regularization
- Neural network fundamentals: forward propagation, backpropagation, gradient descent
- CNN architectures, transfer learning and fine-tuning
- Object detection and segmentation (YOLO, U-Net)
- RNN and LSTM for sequential and text data
- Introduction to Transformers and modern LLM architecture
- AI agent architecture and design patterns
- Tool use, function calling and Retrieval-Augmented Generation (RAG)
- Agent memory and multi-agent systems
- Agent deployment, guardrails and evaluation
- End-to-end ML/DL model or AI agent application, built from problem statement to deployment
- Evaluation, tuning and performance analysis
- Industry-style documentation, demo and mock interview
Tools / Software / Hardware
-
Software
- Python 3.x
- NumPy, Pandas, Matplotlib, scikit-learn
- TensorFlow / Keras or PyTorch
- OpenCV, NLTK / spaCy, Hugging Face Transformers
- LangChain / LlamaIndex, FAISS / ChromaDB
- FastAPI, Streamlit
- Laptop/Desktop (Minimum 8 GB RAM)
- Jupyter / Google Colab (GPU access)
- Internet Connectivity
Industry Job Roles
- Machine Learning Engineer
- Data Scientist
- Deep Learning Engineer
- Computer Vision Engineer
- NLP Engineer
- AI Agent / LLM Application Engineer
- AI Research Engineer
- MLOps Engineer
Pre-requisites
- Basic Python programming
- Fundamentals of mathematics and basic statistics (helpful)
- Familiarity with APIs and JSON (helpful)
- Interest in data and problem solving — no prior ML/DL background required
