Dive into Deep Learning
An interactive deep learning textbook covering neural network foundations, convolutional and recurrent networks, attention, transformers and modern training practice.
Search titles, authors, subjects and dates from across the DARE African Knowledge Repository.
50 resources found in Artificial Intelligence & Machine Learning.
Scoped to Artificial Intelligence & Machine Learning · Search all DARE
An interactive deep learning textbook covering neural network foundations, convolutional and recurrent networks, attention, transformers and modern training practice.
Teaching notes on generative artificial intelligence for library and information science, covering large language models, prompt use, evaluation and professional implications.
The textbook for CS 188: Introduction to Artificial Intelligence at UC Berkeley. It introduces the full range of artificial intelligence topics with emphasis on the core competences of intelligent systems — problem solving, reasoning, decision making and learning — and on the logical and probabilistic foundations of th…
A 70-page critical reflection on how AI ecosystems across Africa evolved since 2023: infrastructure, regulatory frameworks, capacity building and sectoral innovation, together with enduring structural disparities. It documents AI in agriculture, health, law and the creative economy, from crop failure and disease survei…
High-school statistics textbook developed with practising teachers: sampling and data, descriptive statistics, probability, random variables, the normal distribution, hypothesis testing and collaborative labs.
A 302-page edited volume on machine-learning methods for sensor data and imaging, covering acquisition, processing, feature extraction and applied recognition tasks.
An introduction to exploratory data analysis, data structures, causality, machine-learning principles and introductory Python programming using Jupyter notebooks.
A one-semester business statistics text covering core statistical concepts with practical business, economics and finance examples; includes probability, distributions, hypothesis testing, regression and analysis of variance.
An edited collection on applied machine learning: problem conceptualisation, data representation, feature engineering, model selection and interpretation, with sections on computer vision, teaching and learning, social media, forecasting and core ML problems.
A 406-page edited collection surveying deep-learning algorithms and architectures and their applications across recognition, vision and data-intensive domains.
Foundational data-science methods including kernel density estimation, LOWESS, data fusion, probabilistic reasoning, causality, naive Bayes, k-nearest neighbours, feature selection and association analysis.
A 200-page collection covering machine-learning advances in image recognition, speech processing and natural language processing, with pattern-recognition methods and applications.