Principles of Data Science
An introduction to data science covering the data lifecycle, statistics, machine learning, deep learning basics, neural networks and ethical considerations in data-driven work.
Search titles, authors, subjects and dates from across the DARE African Knowledge Repository.
16 resources found in the repository.
An introduction to data science covering the data lifecycle, statistics, machine learning, deep learning basics, neural networks and ethical considerations in data-driven work.
An accessible, comprehensive introduction to machine learning for beginners. The book demonstrates fundamental techniques in data collection, integration, cleansing and transformation, model development and deployment, with a strong emphasis on responsible and explainable AI, MLOps and practical step-by-step examples,…
An applied data-analytics text covering descriptive, predictive and prescriptive analytics, big data, optimisation and prediction, with a dedicated chapter on machine learning and artificial intelligence in analytics.
A widely used introductory text on neural networks and deep learning covering backpropagation, improving neural-network learning, overfitting, regularisation and deep convolutional networks, with hands-on code examples.
A technical overview of artificial intelligence technologies and systems from Huawei's research programme, covering algorithms, platforms, hardware and applications.
The first comprehensive overview of automated machine learning: tutorial-level methods, in-depth descriptions of AutoML systems, neural architecture search, optimisation and the international AutoML challenges.
A state-of-the-art overview of machine-learning research and its exploitation in real products and services, with sections on theory, methods and industrial application areas.
Lecture series delivered for the African Masters in Machine Intelligence at AIMS Kigali, Rwanda, covering statistics and probability, machine-learning foundations and related topics, with lecture slides and notebooks used in the programme.
An introduction to neural networks and classical machine learning with a personal, historically grounded perspective on the shallow/deep distinction and foundational learning algorithms.
A hands-on guide to applying machine learning in science-education research, with theoretical foundations, case studies in formal and informal settings, executable code and a chapter on bias and ethical considerations.
An introduction to informed machine learning that integrates scientific knowledge and domain constraints into learning systems, with use cases from healthcare, manufacturing and materials science and coverage of physics-informed neural networks and small-data regimes.
A four-chapter applied research book on artificial intelligence and natural-language processing in health, including text classification of COVID-19-related conversations using support vector machines and random forests.