University Data Science
University Data Science is a forthcoming textbook by Nayyar Zaidi. This page will provide chapter information, supplementary material, lecture slides, datasets, code notebooks, exercise solutions, ordering information, and citation details.
Supplementary material
Supplementary material will be released gradually. Planned resources include lecture slides, exercise solutions, datasets, Python notebooks, implementation examples, and instructor-facing teaching material. Links below are placeholders and will be activated as material becomes available.
Chapters
The chapter list below reflects the current draft structure. Each chapter will eventually include links to slides, exercise solutions, datasets, code notebooks, and other supporting resources.
-
Chapter 1 — Introduction
Foundations of the field
Data science genesis, process, models, data, scale, machine learning components, and the road ahead.
-
Chapter 1b — Foundations of Data Science
Mathematical and computational foundations
Linear algebra, probability, optimisation, programming, data structures, algorithms, databases, and NoSQL.
-
Chapter 1c — Data Science Activity: First Look
First practical activity
A first look at Naive Bayes, logistic regression, k-nearest neighbours, and an introductory data science activity.
-
Chapter 2 — Machine Learning I
Supervised learning foundations
Estimation, maximum likelihood, MAP, Bayesian inference, linear regression, logistic regression, Naive Bayes, decision trees, k-nearest neighbours, decision theory, and learning theory.
-
Chapter 3 — Model Selection
Choosing and evaluating models
Bias-variance analysis, Bayesian and empirical model selection, regularisation, feature selection, kernels, evaluation metrics, cross-validation, bootstrapping, and model comparison.
-
Chapter 4 — Feature Engineering
Representation and model-driven features
Forms and principles of feature engineering, manual feature construction, GLMs, GAMs, neural models, transformers, factorisation models, kernels, graphical models, ensembles, and hybrid models.
-
Chapter 5 — Machine Learning II
Unsupervised learning and data preparation
Similarity measures, metric learning, approximate similarities, clustering, data preparation, dimensionality reduction, anomaly detection, association rules, and sampling.
-
Chapter 6 — Broad Machine Learning
Graphical models
Joint distributions, Bayesian networks, Markov networks, directed-undirected graph relationships, exact inference, belief propagation, junction trees, loopy belief propagation, and variational methods.
-
Chapter 7 — Deep Machine Learning
Neural-network foundations
Artificial neural networks, back-propagation, modern training methods, regularisation, optimisation, autodiff, batch normalisation, autoencoders, embeddings, transfer learning, and adversarial learning.
-
Chapter 8 — Structured Data Analysis I
Images and convolutional models
Image representations, convolutional neural networks, CNN architectures, object learning, face learning, CNN interpretation, and n-dimensional convolutions.
-
Chapter 9 — Structured Data Analysis II
Sequence models and transformers
Hidden Markov models, conditional random fields, recurrent neural networks, sequence applications, attention, and transformers.
-
Chapter 10 — Reinforcement Learning I
Tabular and planning methods
Markov processes, Markov decision processes, value functions, policy iteration, value iteration, Monte Carlo methods, temporal-difference learning, planning, Dyna-Q, rollout algorithms, and Monte Carlo tree search.
-
Chapter 11 — Reinforcement Learning II
Approximate and deep RL
Approximate methods, deep reinforcement learning, DQN variants, batch RL, eligibility traces, policy gradients, actor-critic methods, hierarchical RL, meta-RL, imitation learning, bandits, and POMDPs.
-
Chapter 12 — Generative Models
Modern data generation
Autoregressive models, variational autoencoders, normalising flows, diffusion models, generative adversarial learning, tabular data generation, and large language models.
-
Chapter 13 — Bayesian Analysis
Bayesian modelling
Bayes rule, priors, conjugacy, Bayesian inference, Bayesian versions of common machine learning models, Dirichlet processes, Indian buffet processes, and Gaussian processes.
-
Chapter 14 — Causal Inference
Causality and counterfactual reasoning
Potential outcomes, causal models, do-operator, identification, backdoor and front-door adjustment, do-calculus, causal estimation, causal discovery, interventions, and counterfactuals.
-
Chapter 15 — Artificial Intelligence
Search, planning, and reasoning
Classical search, informed search, local search, adversarial search, constraint satisfaction, knowledge representation, planning, and neuro-symbolic reasoning.
-
Chapter 16 — Tensor Data Analysis
Tensors and recommender systems
Tensor decompositions, matrix factorisation, recommender systems, content-based recommendation, collaborative filtering, and latent-factor methods.
-
Chapter 17 — Stream Data Analysis
Learning from streams
Stream mining tasks, sampling, filtering, distinct-element estimation, counting, sketches, market-basket analysis, stream clustering, stream classification, evaluation, and deployability.
-
Chapter 18 — Graph Data Analysis
Graph algorithms and graph learning
Graph representation, connectivity, centrality, graph search, shortest paths, graph clustering, link analysis, node classification, link prediction, graph embeddings, graph neural networks, and scalable GNNs.
-
Chapter 19 — Time Series Data Analysis
Temporal modelling
Forecasting, stationarity, seasonality, ARIMA, forecasting as regression, dynamic time warping, time-series classification, anomaly detection, and similarity search.
-
Chapter 20 — Further Topics in Machine Learning
Trustworthy and adaptive ML
Uncertainty analysis, benchmarking, data drift, interpretable machine learning, fairness, privacy-preserving analytics, distributed learning, and federated learning.
-
Chapter 21 — Big Data Engineering
Databases and data systems
Relational databases, SQL, database internals, indexing, query optimisation, transactions, business intelligence, information retrieval, NoSQL, and large-scale data products.
-
Chapter 22 — Large-Scale Data Processing Platforms
Spark and scalable analytics
Spark overview, DataFrames, transformations, aggregations, joins, Spark SQL, RDDs, streaming, Spark machine learning, deployment, monitoring, and debugging.
-
Chapter 23 — Machine Learning Engineering I
Infrastructure and deployment foundations
Hardware, GPUs, TPUs, software environments, versioning, Docker, Kubernetes, cloud platforms, pipeline engineering, model development, and model deployment.
-
Chapter 24 — Machine Learning Engineering II
Development and production error analysis
Data analysis, bad and good data, training/validation/test splits, error analysis, evaluation metrics, labelled data, human-level performance, prototyping, and production shift.
-
Chapter 25 — Data Visualization
Visual analysis and reporting
Visualising numbers, distributions, associations, proportions, matrices, high-dimensional data, model behaviour, clustering, reinforcement learning, recommender systems, Bayesian analysis, and dashboards.
-
Chapter 26 — Further Topics in Data Science
Responsible and future-facing data science
Managing data science projects, ethical machine learning, data science governance, knowledge-guided machine learning, quantum computing, data curation, and AI 2.0.
Ordering information
Ordering information will be added when the book becomes available. This section will include publisher links, institutional ordering information, and any available electronic or print editions.
How to cite
Citation details will be updated after publication. For now, please use the following provisional citation.
Nayyar Zaidi. University Data Science. Forthcoming textbook.
BibTeX:
@book{zaidi-university-data-science,
author = {Zaidi, Nayyar},
title = {University Data Science},
note = {Forthcoming textbook},
year = {forthcoming}
}