Artificial Intelligence

From statistics and pandas to end-to-end projects — the complete foundation for turning raw data into decisions.

Neural networks end to end: backprop, PyTorch, CNNs, RNNs, LSTMs and transformers — from perceptron to attention.

Supervised and unsupervised learning with scikit-learn: regression, trees, ensembles, SVMs, clustering and the math underneath.

From pixels to perception: image processing, CNNs, detection, segmentation, pose, tracking, OCR and vision transformers.

Natural language processing: tokenization, embeddings, classification, NER, sequence models, BERT and transformers.

Design agents that reason, use tools and act: agent loops, tool use, memory, planning, multi-agent systems and agent frameworks.

Generative AI end to end: LLMs, prompting, fine-tuning, RAG, agents, diffusion, VLMs and running GenAI in production.

Build with large language models: tokenization, embeddings, RAG, fine-tuning, evals, agents and production LLM systems.

Get the best out of language models: system prompts, few-shot, chain-of-thought, structured outputs, and evaluation.

Understand the risks of AI systems and the practices that keep them aligned, robust and fair — from evals to governance.

Operationalize machine learning: lifecycle, versioning, pipelines, experiment tracking, serving, Kubernetes and drift monitoring.

From MDPs and dynamic programming to DQN, PPO and multi-agent systems — the complete guide to agents that learn from outcomes.