Guides & series
Learn AI
Engineering guides across classical ML, deep learning, recommendation systems, search, and agentic AI — each balancing the math with production practice.
Classical Machine Learning
Master fundamental ML algorithms from regression to gradient boosting
Logistic Regression
Master binary classification with logistic regression, sigmoid functions, and gradient descent
Decision Trees
Understand tree-based models, CART algorithm, information gain, and entropy
Random Forest
Learn ensemble methods, bagging, and feature importance with random forests
XGBoost
Master gradient boosting with XGBoost for AdTech and production ML
K-Means Clustering
Explore unsupervised learning with K-means, centroid-based clustering, and elbow method
Deep Learning Foundations
Build deep learning expertise from neural networks to transformers
Deep Neural Networks
Build deep learning foundations with multi-layer perceptrons and backpropagation
Recurrent Neural Networks
Master sequential data processing with RNNs, LSTM, and GRU
Transformers
Understand self-attention, multi-head attention, and transformer architecture
BERT
Master bidirectional encoders, masked language modeling, and pre-training
Recommendation Systems: Basics
Build recommender systems from collaborative filtering to deep learning models
Collaborative Filtering
Build recommender systems with user-based and item-based collaborative filtering
Factorization Machines & DeepFM
Learn feature interactions, CTR prediction, and hybrid models for RecSys
Wide & Deep + DIN
Master memorization vs generalization and attention mechanisms for RecSys
Recommendation Systems: Deep Learning
Advanced deep learning architectures for modern recommendation systems
Two-Tower Models
Modern retrieval models with dual encoders and contrastive learning
Sequential Recommendations
Session-based recommendations with GRU4Rec and Transformer4Rec
Multi-Task Learning for RecSys
Optimize multiple objectives with MMoE and ESMM architectures
Cold-Start Solutions
Tackle cold-start problems with hybrid approaches and transfer learning
Building Search Engines
From BM25 to hybrid search with neural retrievers and rerankers
BM25 & Inverted Index
Classical search with BM25 algorithm and inverted index architecture
Dense Retrieval & Vector Search
Neural search with bi-encoders, embedding models, and vector databases
Hybrid Search & Reranking
Production search systems with multi-stage retrieval and cross-encoder rerankers
Query Understanding & Expansion
NLP for search with intent classification, spell correction, and query expansion
Learning to Rank (LTR)
ML-based ranking with LambdaMART, feature engineering, and evaluation metrics
Agentic AI & RAG Development
Build production-ready AI agents with LangGraph, RAG, and MCP
Introduction to LangGraph
Build agent workflows with LangGraph state management and conditional routing
RAG Patterns & Best Practices
Master retrieval augmented generation with chunking, reranking, and evaluation
Agent Tools & MCP
Extend agents with tools, Model Context Protocol, and custom integrations
Production Agent Workflows
Deploy production agents with observability, cost optimization, and guardrails
Multi-Agent Systems
Build collaborative multi-agent systems with coordination and task delegation