INFORMATION THEORY, INFERENCE, AND LEARNING ALGORITHMS, by David J. C. MacKay, Cambridge University Press, Cambridge, 2003, hardback, xii + 628 pp., ISBN 0-521-64298-1 (£30.00)

By Alex M. Andrew. 2004

93 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

Citations in the corpus

• signSGD: compressed optimisation for non-convex problems (2018, neutral): “This means that the parameter server is essentially receiving a repetition code RM and the majority vote decoder is known to drive down the failure probability of a repetition code exponentially in the number of repeats (MacKay, 2002).”
• Estimating relatedness via data compression (2006, unknown): “We will require the following standard result from Information Theory due to Shannon, McMillan, and Breiman; we will more or less follow MacKay’s (MacKay, 2002) exposition: Theorem 1 (Asymptotic Equipartition Prop-Estimating erty).”
• A Hierarchical Bayesian Model for Unsupervised Induction of Script Knowledge (2014, unknown): “For sampling the other parameters of our model, ranking dispersion parameters ρ and the language model parameters η and ξ , we use slice sampling (MacKay, 2002).”