21 modules, 79 lessons — from beginner to expert.
Core math, Python, and conceptual building blocks for AI/ML
NumPy, Pandas, and data visualization for ML
Master classical ML algorithms, evaluation, and pipelines with scikit-learn
Neural networks, TensorFlow, Keras — from basics to production
The research-first deep learning framework — tensors, models, and training
Image classification, object detection, segmentation, and generative models
Text processing, embeddings, transformers, and modern NLP
Transformers library, model hub, datasets, tokenizers, and PEFT
Vector databases, RAG pipelines, LangChain, and building AI agents
Agents, environments, Q-learning, and policy gradients
Classical and deep learning methods for temporal data
Collaborative filtering, content-based, and deep learning recommendations
Model deployment, serving, monitoring, and ML pipelines
Designing, scaling, and governing enterprise AI systems
Large language models, RAG, agents, and prompt engineering
Ethics, governance, privacy, and building trustworthy AI systems
AWS SageMaker, Google Vertex AI, and Azure ML
Model optimization, quantization, and deployment to mobile and IoT
SHAP, LIME, feature importance, and model interpretability
Feature stores, data versioning, and quality pipelines
Automated model selection, tuning, and architecture design