PHASE 0 — Foundations
Module 0.1 — Introduction to AI, ML & Deep Learning
Articles
- What is AI vs ML vs Deep Learning?
- Real-world applications of ML
- Types of Machine Learning
- Supervised Learning
- Unsupervised Learning
- Reinforcement Learning
- Traditional Programming vs Machine Learning
- ML Pipeline Overview
- How Companies Actually Use ML
- AI Roles & Career Paths
- Machine Learning Lifecycle
Module 0.2 — Python for Machine Learning
Articles
- Python basics for ML
- Functions, OOPs & Modules
- NumPy complete guide
- Pandas complete guide
- Data visualization using Matplotlib & Seaborn
- Jupyter Notebook tutorial
- Virtual environments and package management
- File handling
- Exception handling
Practicals
- Data cleaning mini project
- Exploratory data analysis project
- CSV/Excel data processing
Module 0.3 — SQL for Data & ML (need to discussion)
Articles
- Introduction to SQL
- SELECT, WHERE, ORDER BY
- GROUP BY & Aggregations
- JOINs
- Subqueries
- Window Functions
- Common Table Expressions (CTEs)
- SQL for analytics
- SQL interview questions
Module 0.4 — Mathematics for Machine Learning
Linear Algebra
- Scalars, vectors, matrices, tensors
- Matrix operations
- Dot product
- Eigenvalues & eigenvectors
- Matrix decomposition intuition
Calculus
- Functions & derivatives
- Partial derivatives
- Gradients
- Chain rule
- Gradient descent intuition
Probability & Statistics
- Mean, median, variance
- Standard deviation
- Probability basics
- Bayes theorem
- Probability distributions
- Central Limit Theorem
- Hypothesis testing
- Confidence intervals
- P-value
- A/B testing
- Correlation vs causation
Optimization
- Cost functions
- Convex optimization intuition
- Bias-variance tradeoff
PHASE 1 — Data Preprocessing & ML Workflow
Module 1.1 — Data Preprocessing
Articles
- Data collection methods
- Missing value handling
- Outlier detection
- Feature scaling
- Normalization vs Standardization
- Encoding categorical data
- Feature engineering
- Feature selection
- Date-time features
- Text features
- Data augmentation basics
- Train-test-validation split
- Data leakage
- Imbalanced datasets
Module 1.2 — Exploratory Data Analysis (EDA)
Articles
- Why EDA matters
- Univariate analysis
- Bivariate analysis
- Multivariate analysis
- Correlation heatmaps
- Feature importance intuition
- Detecting patterns in data
PHASE 2 — Supervised Learning
Regression Algorithms
Module 2.1 — Linear Regression
Articles
- Intuition behind regression
- Simple linear regression
- Multiple linear regression
- Cost function
- Gradient descent
- Assumptions of linear regression
- Overfitting & underfitting
Evaluation Metrics
- MAE
- MSE
- RMSE
- R² Score
Advanced
- Polynomial regression
- Regularization
- Ridge
- Lasso
- ElasticNet
Module 2.2 — Logistic Regression
Articles
- Classification problems
- Sigmoid function
Sigmoid function:
- Logistic regression intuition
- Decision boundary
- Cross entropy loss
- Confusion matrix
- Precision, Recall, F1-score
- ROC-AUC
Module 2.3 — K-Nearest Neighbors (KNN)
Articles
- KNN intuition
- Distance metrics
- Choosing K
- Curse of dimensionality
Module 2.4 — Decision Trees
Articles
- Entropy
- Information gain
- Gini index
- Tree pruning
- Advantages & limitations
Module 2.5 — Ensemble Learning
Articles
- What is ensemble learning?
- Bagging
- Random Forest
- Boosting intuition
- AdaBoost
- Gradient Boosting
- XGBoost
- LightGBM
- CatBoost
- Feature importance in ensembles
Module 2.6 — Support Vector Machines (SVM)
Articles
- Hyperplanes
- Margins
- Kernel trick
- Linear vs non-linear SVM
PHASE 3 — Unsupervised Learning
Module 3.1 — Clustering
Articles
- What is clustering?
- K-Means
- Elbow method
- Hierarchical clustering
- DBSCAN
- Gaussian Mixture Models
Module 3.2 — Dimensionality Reduction
Articles
- Curse of dimensionality
- PCA intuition
- t-SNE
- UMAP
- Feature selection methods
Module 3.3 — Association Rule Learning
Articles
- Apriori algorithm
- Market basket analysis
PHASE 4 — Model Evaluation & ML Engineering
Module 4.1 — Model Evaluation
Articles
- Cross-validation
- Hyperparameter tuning
- Grid Search
- Random Search
- Bayesian Optimization
- Bias-variance tradeoff deep dive
Module 4.2 — APIs for ML
Articles
- What is API?
- REST APIs
- JSON basics
- Request-response cycle
- API testing using Postman
- FastAPI basics
Module 4.3 — Production ML Basics
Articles
- ML lifecycle
- Pipelines
- Feature stores
- Batch vs real-time inference
- Model monitoring
- Drift detection
PHASE 5 — Deep Learning
Module 5.1 — Neural Network Foundations
Articles
- Biological neuron vs artificial neuron
- Perceptron
- Activation functions
- Forward propagation
- Backpropagation
- Loss functions
- Optimizers
- SGD
- Adam
- RMSProp
Module 5.2 — Deep Neural Networks
Articles
- Vanishing gradients
- Batch normalization
- Dropout
- Weight initialization
- Regularization in DL
Module 5.3 — TensorFlow & PyTorch
Articles
- Introduction to TensorFlow
- Introduction to PyTorch
- Building first neural network
- Training custom models
PHASE 6 — Natural Language Processing (NLP)
Module 6.1 — Classical NLP
Articles
- What is NLP?
- Text preprocessing
- Tokenization
- Stemming vs Lemmatization
- Bag of Words
- TF-IDF
- N-grams
- Sentiment analysis
Module 6.2 — Deep Learning NLP
Articles
- Word embeddings
- Word2Vec
- GloVe
- RNNs
- LSTMs
- GRUs
- Seq2Seq models
- Attention mechanism
Module 6.3 — Transformers & LLMs (Critical Today)
Articles
- Transformer architecture
- Self-attention
- BERT
- GPT models
- Fine-tuning LLMs
- Prompt engineering
- Retrieval-Augmented Generation (RAG)
- Vector databases
- LangChain basics
- LangGraph basics
- AI agents overview
- Hugging Face
- OpenAI APIs
- Ollama
- LoRA fine-tuning
- Quantization
Projects
- AI chatbot
- Resume screening system
- RAG application
- PDF Q&A system
PHASE 7 — Computer Vision
Module 7.1 — OpenCV Basics
Articles
- What is computer vision?
- Image fundamentals
- Reading & displaying images
- Image transformations
- Filtering & smoothing
- Edge detection
- Thresholding
- Contours
- Morphological operations
- Object tracking basics
Module 7.2 — Deep Learning for CV
Articles
- CNN intuition
- Convolution operation
- Pooling layers
- CNN architectures
- LeNet
- AlexNet
- VGG
- ResNet
- Transfer learning
- Object detection
- YOLO
- R-CNN
- Image segmentation
- Face recognition
PHASE 8 — Reinforcement Learning
Articles
- What is RL?
- Agent-environment interaction
- Rewards & policies
- Markov Decision Process
- Q-Learning
- Deep Q Networks
- Policy Gradient Methods
PHASE 9 — Specialized Advanced Topics
Advanced ML Topics
Articles
- Time Series Forecasting
- Anomaly Detection
- Recommendation Systems
- Graph Neural Networks
- Federated Learning
- AutoML
- Explainable AI (XAI)
- Responsible AI
- AI Ethics & Bias
- Multimodal AI
PHASE 10 — MLOps & Deployment
Articles
- Model deployment basics
- Flask/FastAPI for ML
- Docker for ML
- CI/CD for ML
- MLflow
- Kubernetes basics for ML
- Deploying models on cloud
- Monitoring production models
Cloud for ML
Articles
- AWS basics
- GCP basics
- Azure basics
- Amazon S3
- EC2
- SageMaker basics
- Vertex AI basics
PHASE 11 — ML System Design
Articles
- Designing recommendation systems
- Scalable ML pipelines
- Real-time inference systems
- Data pipelines
- Vector search systems
- Distributed ML systems
PHASE 12 — Portfolio, Kaggle & Career Preparation
Module 12.1 — Portfolio Building
Articles
- Building ML portfolio
- GitHub portfolio
- Writing project case studies
- Creating technical blogs
Module 12.2 — Kaggle & Open Source
Articles
- Kaggle basics
- Participating in competitions
- Notebook optimization
- Open-source contribution basics
Module 12.3 — Interview Preparation
Articles
- ML interview questions
- Python interview prep
- SQL interview prep
- Statistics interview prep
- ML system design interview
- Resume building
- LinkedIn optimization
- Mock interviews
Final Learning Strategy
Follow This Sequence for Every Topic
- Learn theory
- Understand intuition
- Implement from scratch
- Use libraries/frameworks
- Build projects
- Deploy projects
- Add to portfolio
- Prepare for interviews
Tools & Technologies
Programming
- Python
- SQL
Libraries
- NumPy
- Pandas
- Scikit-learn
- TensorFlow
- PyTorch
- OpenCV
- Hugging Face
Deployment
- FastAPI
- Docker
- MLflow
- Kubernetes
Cloud
- AWS
- GCP
- Azure
AI Engineering
- LangChain
- LangGraph
- Vector Databases
- RAG Pipelines
- AI Agents