All Learning Tracks

The core ML algorithms every engineer must know. Covers linear regression, classification, trees, boosting, SVM, clustering, anomaly detection, time series, and hyperparameter optimization.

Practical programming for data, engineering, and web. Covers Python, SQL, Shell, Excel, C/C++, Perl, and JavaScript — with AI learning prompts for each topic.

Prompt engineering, RAG architecture, fine-tuning with LoRA, embeddings, vector databases, LLM evaluation, HuggingFace, and Kaggle competition workflows.

Neural network basics, CNNs, RNNs and LSTMs, autoencoders, GANs, transformers, multimodal vision-language models, transfer learning, and model compression.

How to build agents that plan, use tools, and remember. Covers LangGraph, CrewAI, MCP protocol, OpenAI Assistants API, multi-agent patterns, and safety guardrails.

EDA with Pandas, Matplotlib, Seaborn, Plotly interactive charts, storytelling with data, and Tableau/Power BI overview.

Airflow orchestration, Spark, MLflow experiment tracking, Kubernetes for ML, SageMaker, Docker containers, and CI/CD pipelines for machine learning models.

Agent-environment interaction, Q-learning, Deep Q-Networks, policy gradients, PPO, and real-world RL applications in recommendation and optimization.

GPU training on Kaggle & Colab (free), AWS EC2 with GPU, TensorFlow vs PyTorch hands-on, Jupyter best practices, Git for ML, environment management, and model benchmarking.