Knowledge / Artificial Intelligence and Data Science
Artificial Intelligence and Data Science notes
Free study notes for Artificial Intelligence and Data Science (B.E./B.Tech) students in India: 59 topics across 7 subjects - Programming and data, Mathematics and statistics for AI, Machine learning, Deep learning, AI applications, Data engineering and deployment and Advanced learning methods. Each note explains the concept, works the examples with the numbers done, gives the Indian standards, codes and laws in force today, and ends with interview questions and the mistakes examiners look for - for semester exams, competitive exams, campus placements and job interviews.
Programming and data
- Python for data analysis: NumPy and pandas
- Data visualisation
- Data cleaning and feature engineering
- Data collection and web scraping
- Python ML libraries: scikit-learn, PyTorch and TensorFlow
Mathematics and statistics for AI
- Linear algebra for machine learning
- Probability distributions
- Descriptive statistics
- Hypothesis testing
- Calculus and gradient descent
- Bayesian statistics
- Causal inference basics
- Experiment design and A/B testing
- Optimisation for machine learning
- Statistical inference and estimation
Machine learning
- Machine learning workflow
- Linear and logistic regression
- Decision trees and random forests
- Support vector machines and k-nearest neighbours
- Clustering: k-means and hierarchical
- Dimensionality reduction and PCA
- Model evaluation metrics
- Overfitting, bias-variance and regularisation
- Anomaly detection
- Association rules and market basket analysis
- Ensemble methods and gradient boosting
- Feature selection and model interpretability
- Naive Bayes and probabilistic models
- Reinforcement learning basics
Deep learning
- Neural networks and backpropagation
- Convolutional neural networks
- Recurrent networks and LSTMs
- Transformers and attention
- Generative models: GANs, VAEs and diffusion
- Graph neural networks basics
- Training deep networks: optimisers, normalisation and regularisation
- Transfer learning and fine-tuning
AI applications
- Natural language processing basics
- Large language models and prompt engineering
- Computer vision basics
- Recommender systems
- Time series forecasting
- AI agents and tool use
- Edge AI and model optimisation
- Object detection and segmentation
- Retrieval-augmented generation and vector databases
- Speech recognition and audio AI
- Text embeddings and semantic search
Data engineering and deployment
- Big data: Hadoop and Spark
- Data warehousing and ETL
- MLOps and model deployment
- AI ethics, bias and responsible AI
- AI regulation and governance
- Cloud data platforms: BigQuery, Snowflake and Databricks
- Data lakes and lakehouses
- Data pipelines: Airflow and Kafka