Run this notebook: Open in Colab Open in Kaggle

Phase 10: AI Specializations — Start Here

Go deep in Computer Vision, Natural Language Processing, and AI Agents — the three core specialization tracks.

Three Tracks

Track

Directory

Topics

Computer Vision

computer-vision/

CLIP, CNNs, object detection, segmentation

NLP

nlp/

NER, translation, summarization, classification

AI Agents

ai-agents/

Tool use, LangGraph, ReAct, multi-agent

Computer Vision Track

Notebook

Topic

01_image_classification.ipynb

ResNet, ViT, zero-shot with CLIP

02_object_detection.ipynb

YOLO, DETR, bounding boxes

03_semantic_segmentation.ipynb

SAM, DeepLab, pixel-level classification

04_image_generation.ipynb

Stable Diffusion overview

05_cv_pipelines.ipynb

End-to-end production CV pipelines

06_advanced_cv.ipynb

Multi-scale features, self-supervised learning

NLP Track

Notebook

Topic

01_text_classification.ipynb

Sentiment, topic, intent classification

02_named_entity_recognition.ipynb

spaCy, transformers-based NER

03_machine_translation.ipynb

Helsinki-NLP, MarianMT models

04_text_summarization.ipynb

Extractive vs. abstractive summarization

05_question_answering.ipynb

Extractive QA, reading comprehension

06_advanced_nlp.ipynb

Cross-lingual transfer, zero-shot NLP

AI Agents Track

Notebook

Topic

01_langchain_basics.ipynb

LangChain chains, prompts, memory

02_function_calling.ipynb

OpenAI/Anthropic tool/function use

03_react_agents.ipynb

ReAct pattern (Reason + Act)

04_langgraph_workflows.ipynb

Stateful agent graphs with LangGraph

05_multi_agent.ipynb

Multi-agent systems, coordination

06_custom_tools.ipynb

Build and register custom agent tools

07_agent_evaluation.ipynb

Evaluating agent reliability

Prerequisites

  • RAG Systems (Phase 08)

  • Embeddings (Phase 05)

  • Neural Networks basics (Phase 06) for the CV track